CN118483169B - Hair quality detection method and system for cosmetology and hairdressing - Google Patents
Hair quality detection method and system for cosmetology and hairdressing Download PDFInfo
- Publication number
- CN118483169B CN118483169B CN202410940114.8A CN202410940114A CN118483169B CN 118483169 B CN118483169 B CN 118483169B CN 202410940114 A CN202410940114 A CN 202410940114A CN 118483169 B CN118483169 B CN 118483169B
- Authority
- CN
- China
- Prior art keywords
- matching
- points
- point
- spectrum curve
- matched
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/27—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands using photo-electric detection ; circuits for computing concentration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/55—Specular reflectivity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Evolutionary Biology (AREA)
- Chemical & Material Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
The invention relates to the technical field of hairiness detection based on spectral analysis, in particular to a hairiness detection method and a hairiness detection system for cosmetology and hairdressing. The method comprises the steps of firstly obtaining a hairiness spectrum curve of customer hair, matching the hairiness spectrum curve of the customer hair with hairdye spectrum curves of different hairdye to obtain matched pairs, correcting the matched pairs of different matched types by combining chemical spectrum properties of the hairiness and the hairdye, determining the fitness of the hairiness spectrum curve and the hairdye spectrum curve based on the matched distance of the corrected matched pairs, and inputting the hairiness spectrum curve, the fitness and the hairdye spectrum curve of the customer into a neural network to obtain the fitness of the hairiness spectrum curve and the hairdye spectrum curve. According to the invention, by combining the chemical spectrum properties of the hair and the hair dye, the hair and the hair dye are tested and analyzed, so that the corresponding adaptation degree can more accurately reflect whether the hair of a customer is matched with the hair dye.
Description
Technical Field
The invention relates to the technical field of hairiness detection based on spectral analysis, in particular to a hairiness detection method and a hairiness detection system for cosmetology and hairdressing.
Background
It is important to detect the quality of hair before it is used for hair dressing. The hair quality test can help to understand the current condition of the hair, including its oily, dry, neutral, etc. attributes, as well as the toughness, smoothness, and possible damage of the hair. Based on the detection results, appropriate care methods and hair styling products can be selected to avoid further damage to the hair. In the existing method, a hairiness spectrometer is often adopted to detect hairiness, and then data of various indexes which can be output by the spectrometer are obtained and are provided for reference. According to the data, whether the hair of the customer has insufficient moisture and has the problems of protein loss and the like can be seen, but when the hair of the customer can be dyed by adopting various hair dyes, one hair dye required by the customer is often selected according to experience, and whether a better dyeing effect can be achieved cannot be estimated in advance. When the selected hair dye is not matched with the hair quality of the customer or the matching degree is low, the dyeing effect after dyeing the hair of the customer is poor and the hair dye is easy to fade.
Disclosure of Invention
In order to solve the technical problem of poor dyeing effect caused by unmatched hair quality and hair dye, the invention aims to provide a hair quality detection method and system for cosmetology and hairdressing, and the adopted technical scheme is as follows:
in a first aspect, embodiments of the present invention provide a method for detecting hair quality for beauty treatment and hairdressing, the method comprising:
matching the hairiness spectrum curve with hairdye spectrum curves of different hairdyes by utilizing a dynamic time warping algorithm to obtain a matching pair consisting of matching points;
For the matching pairs of different matching types, the matching pairs of different matching types are corrected by combining the reflectivities of different points and corresponding matching points on the light-emitting spectrum curve, the reflectivities of points with the same wavelength on the hair dye spectrum curve, the positions of the matching points in the matching pairs and the associated points to be matched;
And inputting the hairiness spectrum curve, the fitness and the hairdye spectrum curve of the customer into a trained neural network to obtain the fitness of the hairiness spectrum curve and the different hairdye spectrum curves of the customer's hair.
Preferably, for the matching pairs of different matching types, the correcting the matching pairs of different matching types by combining the reflectivities of different points and corresponding matching points on the light emission spectrum curve, the reflectivities of points with the same wavelength on the hair dye spectrum curve, the positions of the matching points in the matching pairs and the associated points to be matched includes:
The matching types of the matching pairs are one-to-one matching, one-to-many matching and many-to-one matching;
For a matching pair matched one to one, determining matching probability by combining the reflectivities of different points and corresponding matching points on the luminous spectrum curve and the reflectivities of points with the same wavelength on the hair dye spectrum curve, and reserving the matching pair based on the matching probability;
for one-to-many matching pairs, correcting the matching pairs by analyzing the positions of the matching points and the matching probability;
and for the matching pairs matched in many pairs and one, correcting the matching pairs by analyzing the positions of the matching points and the associated points to be matched.
Preferably, the determining the matching probability for the matching pair of one-to-one matching, combining the reflectivities of different points and corresponding matching points on the light emission spectrum curve and the reflectivities of the points with the same wavelength on the hair dye spectrum curve, includes:
Taking any point on the light emission spectrum curve as a point to be analyzed, acquiring a matching pair to which the point to be analyzed belongs and matching points in the matching pair, and acquiring a point with the same wavelength as the point to be analyzed on the hair dye spectrum curve as the point to be matched;
taking a normalized value of the difference of the reflectivities of the point to be analyzed and the corresponding point to be matched as a first analysis value;
Taking a normalized value of the difference between the point to be analyzed and the matching point in the corresponding matching pair as a second analysis value;
And weighting the normalized value of the difference between the first analysis value and the second analysis value by taking the first analysis value as a weight to obtain the matching probability of the matching pair.
Preferably, the reserving the matching pair based on the matching probability includes:
and reserving the matching pairs with the corresponding matching probabilities larger than the preset matching threshold.
Preferably, the correcting the matching pair by analyzing the position of the matching point and the matching probability for the matching pair of one-to-many matching includes:
Calculating the matching probability of each point to be analyzed and the corresponding matching point, and marking the matching probability as a first matching probability;
calculating a matching point corresponding to each point to be analyzed and a normalized value of a position difference value of the point to be matched;
sorting the matching points corresponding to the points to be analyzed according to the order of the order values to obtain a standard sequence;
sorting the matching points corresponding to the points to be analyzed according to the order of the first matching probability to obtain a matching sequence;
calculating the position difference of the same element in the standard sequence and the matching sequence, and determining a matching probability difference value;
combining the matching probability difference and the normalized value of the position difference value to determine a second matching type correction;
and correcting the matching pair based on the second matching type correction.
Preferably, the correcting the matching pair by analyzing the position of the matching point and the associated point to be matched for the matching pair of many-to-one matching includes:
calculating the sequence difference between the matching points of the points to be analyzed and the points to be matched;
Acquiring the number of matching pairs corresponding to the points to be matched, and recording the number as the number to be matched;
combining the sequence difference and the quantity to be matched, and determining a third matching type correction;
And correcting the matching pair based on the third matching type correction.
Preferably, the correcting the matching pair based on the third matching type correction includes:
And when the third matching type correction is larger than the preset correction threshold, connecting the point to be analyzed and the point to be matched to obtain a corresponding matching pair.
Preferably, the determining the fitness of the hairiness spectrum curve and the different hairdye spectrum curves based on the corrected matching distance of the matching pair includes:
and regarding the hairdye spectrum curve of any hairdye, taking the corrected negative correlation normalized mapping value of the mean value of the dynamic time warping distances of each matched pair as the fitness of the hairiness spectrum curve and the hairdye spectrum curve.
Preferably, after the matching degree of the hairiness spectrum curve of the customer hair and the different hairdye spectrum curves is obtained, the method further comprises:
And taking the hair dye corresponding to the hair dye spectrum curve with the largest fitting degree as the hair dye which is most suitable for the hair of the customer.
In a second aspect, there is provided a hair quality detection system for cosmetic and hair styling, the system comprising the following modules:
the hair quality spectrum curve of the customer hair is matched with the hair dye spectrum curves of different hair dyes by utilizing a dynamic time warping algorithm, so that a matching pair formed by matching points is obtained;
The spectrum analysis module is used for correcting the matching pairs of different matching types by combining the reflectivities of different points and corresponding matching points on the light-emitting spectrum curve, the reflectivities of the points with the same wavelength on the hair dye spectrum curve, the positions of the matching points in the matching pair and the associated points to be matched;
and the adaptation degree analysis module is used for determining the adaptation degree of the hairiness spectrum curve and the different hair dye spectrum curves based on the corrected matching distance of the matching pair, inputting the hairiness spectrum curve, the adaptation degree and the hair dye spectrum curve of the customer into the trained neural network, and obtaining the adaptation degree of the hairiness spectrum curve and the different hair dye spectrum curves of the customer.
In a third aspect, embodiments of the present invention provide an electronic device, including a memory and a processor, where the memory stores executable code, and where the processor executes the executable code to implement embodiments as possible in the first aspect.
In a fourth aspect, embodiments of the present invention provide a computer program product comprising computer program code which, when run on a computer, causes the computer to perform the method of the first aspect or any one of the possible implementations of the first aspect.
In a fifth aspect, embodiments of the present invention provide a computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the embodiments as possible in the first aspect.
The embodiment of the invention has at least the following beneficial effects:
According to the invention, the hairiness spectrum curve of the hair of a customer and the hairdye spectrum curves of different hairdyes are matched through the existing dynamic time warping algorithm, but the dynamic time warping algorithm is the matching of calculation trends, but the matching of corresponding wave bands is to be realized in the embodiment, so that the matching result determined through the dynamic time warping algorithm needs to be corrected within a reasonable range. For matching pairs of different matching types, the matching pairs of different matching types are corrected by combining the chemical spectrum properties of the hair and the hair dye and analyzing the hair spectrum curve and the hair dye spectrum curve. And determining the fitness of the hair dye spectrum curve through the corrected matching distance of the matching pair, wherein the fitness is obtained through objective analysis of data. And then inputting the hairiness spectrum curve, the fitness and the hair dye spectrum curve of the customer into a trained neural network to obtain the hairiness spectrum curve of the customer hair and the fitness of different hair dye spectrum curves, and carrying out test analysis on the hairiness and the hair dye by combining the chemical spectrum properties of the hairiness and the hair dye to obtain the corresponding fitness which can more accurately reflect the situation that whether the hairiness of the customer is matched with the hair dye or not, so that the problem of poor dyeing effect caused by mismatching of the hairiness of the customer and the hair dye is avoided.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for detecting hair quality for cosmetology and hairdressing according to an embodiment of the present invention;
FIG. 2 is a schematic diagram showing DTW matching of a hairiness spectrum curve and a hairdye spectrum curve of a hairdye according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method for correcting matching pairs of different matching types according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of matching pairs of one-to-many matching types according to one embodiment of the present invention;
FIG. 5 is a schematic diagram of matching pairs of many-to-one matching types according to one embodiment of the present invention;
fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following description refers to the specific implementation, structure, characteristics and effects of a hair quality detection method and system for hairdressing and beauty according to the invention in combination with the accompanying drawings and the preferred embodiment.
In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
In the description of the embodiment of the present invention, unless otherwise indicated, "/" means or, for example, a/B may mean a or B, "and/or" in the text is only one association relationship describing the association object, and it means that there may be three relationships, for example, a and/or B, three cases where a exists alone, a and B exist together, and B exists alone, and further, "a plurality" means two or more in the description of the embodiment of the present invention.
The terms "first," "second," and the like, are used below for descriptive purposes only and are not to be construed as implying or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
Embodiments of the present invention will be described below with reference to the accompanying drawings. As one of ordinary skill in the art can know, with the development of technology and the appearance of new scenes, the technical scheme provided by the embodiment of the invention is also applicable to similar technical problems.
The embodiment of the invention provides a specific implementation method of a hair quality detection method and a system for cosmetology and hairdressing, and the method is suitable for a hair quality detection scene. The spectrum of hair dye is collected through the professional spectrometer under this scene, and the hairiness spectral curve of customer is collected through the hairpath spectrometer. The hairgallery spectrometer is a specialized testing instrument and can comprehensively analyze the hair of a customer. Calibration is required prior to use of the spectrometer. Calibration can ensure the accuracy of the test results. Only accurate test results can help the hairsalon to better understand the hairiness of the customer, providing more personalized services. In calibrating the spectrometer, an automatic calibration or a manual calibration mode can be adopted. After calibrating the spectrometer, the position of the test hair is aligned with the detection head of the spectrometer and the test key is pressed. The following should be noted when testing hair:
(1) The test is performed in a dry state, preferably in a natural air-dried state after shampooing, without drying the hair.
(2) To better derive the test results, the hair may be divided into multiple parts for testing. The hair is generally separated into top, sides and back three portions for testing, respectively, to obtain more accurate results. In the embodiment of the invention, in order to facilitate analysis, test analysis is performed on hair at one position.
After the test results are obtained, analysis of the test results is required. The spectrometer outputs data of various indexes and is used for reference.
The following specifically describes a specific scheme of a hair quality detection method and system for beauty and hairdressing with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a method for detecting hair quality for cosmetology according to an embodiment of the present invention is shown, the method includes the steps of:
And step S100, acquiring a hairiness spectrum curve of the hair of a customer, and matching the hairiness spectrum curve with hairdye spectrum curves of different hairdye by utilizing a dynamic time warping algorithm to obtain a matching pair formed by matching points.
Under the scene, when the hairdresser has various similar hair color selections for the current hair condition and requirement of the customer, the hair dyeing effect is estimated by calculating the matching condition of the hair spectrum and the spectrums of different hair dyes, and a reference suggestion is provided for the customer to select the hair dyes. It can be seen through spectral matching which hair dye can achieve a more desirable hair dye color for the hair of the customer, wherein if the absorption peak of the dye is similar or complementary to the absorption peak of the natural pigment in the hair, this means that the pigment in the dye can be effectively combined with the pigment in the hair of the customer, thereby being more easily colored. If the spectrum of the customer's hair shows a lower reflectance, this tends to mean that the hair surface is rougher and the dye tends to penetrate and adhere more easily.
The spectral curve of each hair dye is obtained by measuring the spectral curve of a sample of each hair dye through a professional spectrometer, and the hairiness spectral curve of the hair of a customer is obtained through a hairline spectrometer for the customer with the need of dyeing.
When there are various choices of hair colors for the current hair of the customer, it is possible to see which hair dye can achieve a more desirable hair dyeing color by spectral matching, wherein if the absorption peak of the coloring agent is close to or complementary to the natural pigment absorption peak in the hair, this means that the pigment in the coloring agent can be effectively combined with the pigment in the hair, thereby being more easily colored. Thus, the matching of the overall trend of the hair spectrum and the dye spectrum is first calculated here.
And matching the hairiness spectrum curve with hairdye spectrum curves of different hairdye to obtain a matching pair formed by matching points.
And matching data points on the hair spectrum curve and the hair dye spectrum curve by using a dynamic time warping algorithm to obtain a matching pair formed by matching points, wherein the matching points respectively belong to the hair spectrum curve and the hair dye spectrum curve.
More specifically, a plurality of matching pairs are obtained by taking a hairiness spectrum curve and a hairdye spectrum curve of a hairdye as inputs of a dynamic time warping algorithm (DYNAMIC TIME WARPING, DTW). Referring to fig. 2, fig. 2 is a schematic diagram showing DTW matching of a hairiness spectrum curve and a hairdye spectrum curve of a hairdye. In fig. 2, the upper curve is a hairiness spectrum curve, and the lower curve is a hairdye spectrum curve. The points on the two curves connected by a straight line between the two curves are pairs of matching points.
Referring to fig. 2, the matching pairs in the figure have one-to-one, one-to-many and many-to-one relationships, and are referred to as matching pairs of different matching types.
Step S200, for the matching pairs with different matching types, the matching pairs with different matching types are corrected by combining the reflectivities of different points and corresponding matching points on the light-emitting spectrum curve, the reflectivities of points with the same wavelength on the hair dye spectrum curve, the positions of the matching points in the matching pairs and the associated points to be matched.
Because the existing matching based on the DTW algorithm is matching of calculation trend, but matching of corresponding wave bands is desirable in the embodiment of the invention, the matching result based on the DTW algorithm needs to be corrected within a reasonable range. When the spectral intensity of the dye is high, which means that the pigment concentration is high, the original color of the hair is easy to be covered, especially when dark color dyeing is needed. If the spectrum of hair shows a lower reflectance, this tends to mean that the hair surface is rougher and the dye tends to penetrate and adhere more easily.
In some embodiments, for matching pairs of different matching types, the invention modifies matching pairs of different matching types by combining the reflectivities of different points and corresponding matching points on the light emission spectrum curve, the reflectivities of points of the same wavelength on the hair dye spectrum curve, the positions of the matching points in the matching pair, and the associated points to be matched.
In some embodiments, the correction is performed on the matching pairs of different matching types, that is, the step S200 described above may be implemented by the steps shown in fig. 3:
The matching types of the matching pairs are one-to-one matching pairs, one-to-many matching pairs and many-to-one matching pairs.
Step S210, for a matching pair matched one to one, determining matching probability by combining reflectivities of different points and corresponding matching points on the light emission spectrum curve and reflectivities of points with the same wavelength on the hair dye spectrum curve, and reserving the matching pair based on the matching probability.
For the matching pairs matched one by one, firstly, matching pairs with inconsistent wavelengths are screened out, and it should be noted that the inconsistent wavelengths refer to that the wavelengths corresponding to two data points in the matching pairs are different. And calculating the probability that the point data belonging to the hair wave band on each matched pair can be connected with the point data of the same wave band on the hair dye spectral curve by taking the hair wave spectrum as a standard.
Taking any point on the light emission spectrum curve as a point to be analyzed, acquiring a matching pair to which the point to be analyzed belongs and matching points in the matching pair, and acquiring a point on the hair dye spectrum curve, which has the same wavelength as the point to be analyzed, as the point to be matched.
Taking a normalized value of the difference of the reflectivity of the point to be analyzed and the corresponding matching point as a first analysis value;
As an embodiment of the present invention, an absolute value of a difference between reflectances of a point to be analyzed and a corresponding point to be matched may be used as a numerator, a maximum value of reflectances of the point to be analyzed and the corresponding point to be matched may be used as a denominator, and a ratio formed by the numerator and the denominator may be used as a normalized value of the difference, that is, a first analysis value.
In another embodiment of the present invention, the absolute value of the difference between the reflectances of the point to be analyzed and the corresponding point to be matched may be normalized by a maximum and minimum normalization method, so as to obtain the first analysis value.
And taking the normalized value of the difference between the point to be analyzed and the matching point in the corresponding matching pair as a second analysis value.
As an embodiment of the present invention, the absolute value of the difference in the reflectances of the points to be analyzed and the matching points within the corresponding matching pair may be used as a numerator, the maximum value of the reflectances of the points to be analyzed and the matching points within the corresponding matching pair may be used as an denominator, and the ratio composed of the numerator and the denominator may be used as a second analysis value.
As another embodiment of the present invention, the absolute value of the difference between the reflectances of the points to be analyzed and the matching points in the corresponding matching pairs may be normalized by a maximum-minimum normalization method, so as to obtain a second analysis value.
And weighting the normalized value of the difference between the first analysis value and the second analysis value by taking the first analysis value as a weight to obtain the matching probability.
As an alternative embodiment of the present invention, the absolute value of the difference between the first analysis value and the second analysis value may be used as a numerator, the maximum value of the first analysis value and the second analysis value may be used as a denominator, and the ratio of the numerator and the denominator may be used as a normalized value of the difference between the first analysis value and the second analysis value.
And taking the first analysis value as the weight of the normalized value of the difference between the first analysis value and the second analysis value, and weighting the normalized value of the difference between the first analysis value and the second analysis value to obtain the matching probability.
As an embodiment of the present invention, the calculation formula of the matching probability is:
;
Wherein, A is the reflectivity corresponding to the point to be analyzed, b is the reflectivity of the point to be matched with the same wavelength corresponding to the point to be analyzed; And the reflectivity corresponding to the matching point in the matching pair corresponding to the point to be analyzed is the maximum value taking function.
If the reflectivity difference between the point data of the hair spectrum curve on the matched pair matched one to one and the point data of the same wave band on the hair dye spectrum curve is larger than the reflectivity difference of the matched pair, the greater the difference degree is, the more the point data belonging to the hair spectrum curve on the matched pair can be connected with the point of the same wave length on the hair dye spectrum curve, and then the original matched pair is cancelled. The calculation can embody logic, particularly when dyeing is needed, the corresponding points are corrected, and further the corresponding points with large difference are reserved, so that the dyeing needs can be embodied.
After the matching probabilities of the matching pairs on the luminescent and hair dye spectra are obtained, the matching pairs are retained based on the obtained matching probabilities. More specifically, when the matching probability of the matching pair is larger than a preset matching threshold, the corresponding matching pair is reserved. In the embodiment of the present invention, the preset matching threshold value is 0.6, and in other embodiments, the value is adjusted by the practitioner according to the actual situation.
Step S220, for the matching pairs of one-to-many matching, correcting the matching pairs by analyzing the positions of the matching points and the matching probability.
For the calculated matching pair of one-to-many matching, namely, the matching pair of the plurality of points on the hairdye spectral curve corresponding to one point on the hairdye spectral curve, or the matching pair of the plurality of points on the hairdye spectral curve corresponding to one point on the hairdye spectral curve, the correction process is as follows:
For each match, if there is a data point of the same wavelength as the point f on the emission spectrum curve in the matching points on the hair dye spectrum curve that match the point f on the emission spectrum curve, no correction is required for the matching points of the same wavelength. If there is a data point having a wavelength different from that of the point f on the light emission spectrum curve among the matching points on the hair dye spectrum curve which match the point f on the light emission spectrum curve, it is necessary to correct the matching points having different wavelengths. Therefore, firstly, screening out the matching points which are matched with the point f on the light-emitting spectrum curve and are different from the wavelength of the point f on the light-emitting spectrum curve, and correcting the matching points.
Referring to fig. 4, fig. 4 is a schematic diagram of matching pairs of a one-to-many matching type. The upper point in fig. 4 is a point on the hair dye spectrum curve, the lower point in fig. 4 is a point on the hair dye spectrum curve, the black point and the point connected with the black point through a line segment form a one-to-many match, and the gray point form a one-to-one match. The gray points are points on the hair dye spectrum curve, which have the same wavelength as the black points, and the points on the hair dye spectrum curve, which have the same wavelength as the luminescent spectrum curve, are connected by a dotted line.
Similarly, any point on the light-emitting spectrum curve is used as a point to be analyzed, a matching pair to which the point to be analyzed belongs and a matching point in the matching pair are obtained, and a point on the hair dye spectrum curve, which has the same wavelength as the point to be analyzed, is obtained as the point to be matched.
In fig. 4, if a black point is taken as a point to be analyzed, a point corresponding to the black point and communicated with the black point through a line segment is a matching point, and a point corresponding to the black point and communicated with the black point through a dotted line is a point to be matched.
The smaller the sequence difference between the matching point of the current point to be analyzed and the point to be matched is, the larger the probability is, and after the point to be matched is matched with the current analysis point, the smaller the influence on the overall matching is, the more can be corrected.
Each matching point and the point to be analyzed can obtain a matching probability, and when the matching probability of the matching point which is closer to the point to be matched is smaller, the more obvious the matching effect is after the point to be matched is matched with the current point to be analyzed, the more the current point to be analyzed and the point to be matched can be connected, namely, the more the current matching pair needs to be corrected.
Firstly, forming a first matching pair by the points to be analyzed and the corresponding matching points, and calculating a first matching probability by analyzing each first matching pair and each first matching pair, namely calculating the matching probability of each point to be analyzed and the corresponding matching point and marking the first matching probability as the first matching probability.
Calculating absolute values of sequence differences of the matching points and the points to be matched corresponding to each point to be analyzed to obtain sequence differences of the matching points and the points to be matched, taking the average value of the sequence differences of the matching points and the points to be matched corresponding to each point to be analyzed as a position difference value, and normalizing the position difference value to obtain normalized values of the position difference values of the matching points and the points to be matched corresponding to each point to be analyzed.
Sorting the matching points corresponding to the points to be analyzed according to the order of the order values of the matching points to obtain a standard sequence;
sorting the matching points corresponding to the points to be analyzed according to the order of the first matching probability to obtain a matching sequence;
As an embodiment of the present invention, when the arrangement is performed in order of magnitude of the order value of the matching points and in order of magnitude of the first matching probability, the arrangement is performed in order from small to large. As other embodiments of the present invention, when the arrangement is performed in the order of the magnitude of the order value of the matching points and the arrangement is performed in the order of the magnitude of the first matching probability, the arrangement may be performed in the order from large to small.
And calculating the position difference of the same element in the standard sequence and the matching sequence, and determining the matching probability difference value. For example, the difference between the order value of the first element in the matching sequence and the order value in the standard sequence is first noted as the first element position difference for the first element in the standard sequence, the difference between the order value of the second element in the matching sequence and the order value in the standard sequence is noted as the second element position difference for the second element in the standard sequence, and the difference between the order value of the third element in the matching sequence and the order value in the standard sequence is noted as the third element position difference for the third element in the standard sequence.
Normalizing the element position difference of each element, recording the normalized element position difference as the position difference of each element, and calculating the average value of the position differences of the same element in the standard sequence and the matching sequence as the matching probability difference value.
And determining the second matching type correction by combining the normalized values of the matching probability difference and the position difference.
And the normalized values of the matching probability difference and the position difference are in negative correlation with the second matching type correction. Because when the matching difference is larger and the position difference is larger, the feasibility of the corresponding matching pair is larger, and the repairability of the point to be analyzed and the matching point, namely the feasibility of connecting the point to be analyzed and the point to be analyzed, is reflected through the second matching type repairability. It should be noted that, in the normalization in the embodiment of the present invention, the normalization of the value to be normalized may be achieved by the ratio of the value to be normalized to the corresponding maximum value, or may be achieved by other existing normalization algorithms.
As an embodiment of the present invention, the calculation formula of the second matching type correction is: wherein x1 is the second matching type correction, e is a natural constant, n is the number of matching points corresponding to the points to be analyzed; The element position difference is the element position difference of the ith element, j is a position difference value; a normalized value for the position difference value; Is the difference in matching probabilities.
And obtaining the repairability of the current point to be analyzed and the matching point through calculation, namely the feasibility of connecting the point to be matched with the current analysis point.
After the second match type correction of each one-to-many match pair is obtained, the match pair is corrected based on the second match type correction. More specifically, when the second matching type correction is larger than a preset correction threshold, connecting the point to be analyzed and the point to be matched to obtain a corresponding matching pair. In the embodiment of the invention, the preset correction threshold value is 0.7, and in other embodiments, the value can be adjusted by an implementer according to actual conditions.
In step S230, for many-to-one matching pairs, the matching pairs are corrected by analyzing the positions of the matching points and the associated points to be matched.
Referring to fig. 5, fig. 5 is a schematic diagram of matching pairs of many-to-one matching types. The upper point in fig. 5 is a point on the hair dye spectrum curve, the lower point in fig. 5 is a point on the hair dye spectrum curve, the black point and the point connected with the black point through a line segment form a many-to-one match, and the gray point form a one-to-one match. The gray points are points on the hair dye spectrum curve, which have the same wavelength as the black points, and the points on the hair dye spectrum curve, which have the same wavelength as the luminescent spectrum curve, are connected by a dotted line.
Similarly, any point on the light-emitting spectrum curve is used as a point to be analyzed, a matching pair to which the point to be analyzed belongs and a matching point in the matching pair are obtained, and a point on the hair dye spectrum curve, which has the same wavelength as the point to be analyzed, is obtained as the point to be matched.
In fig. 5, if a black point is taken as a point to be analyzed, a point corresponding to the black point and communicated with the black point through a line segment is a matching point, and a point corresponding to the black point and communicated with the black point through a dotted line is a point to be matched.
The smaller the sequence difference between the matching point of the current point to be analyzed and the point to be matched is, the larger the probability is, after the point to be matched is matched with the current analysis point, the smaller the influence on the overall matching is, and the more can be corrected.
The fewer the corresponding hair points to be connected with the matching points, the less the current analysis point is connected with the matching points, and the less the influence on the overall matching is, the more the correction can be performed.
And obtaining the number of matching pairs corresponding to the points to be matched, and recording the number as the number to be matched. And combining the sequence difference and the quantity to be matched to determine a third matching type correction.
As an embodiment of the present invention, the calculation formula of the third matching type correction is: Wherein x2 is a third matching type correction, e is a natural constant, a is the sequence difference between the matching points of the points to be analyzed and the points to be matched, and b is the number of the matching pairs corresponding to the points to be matched.
The third matching type correction reflects the correction property when the current point to be analyzed belongs to the many-to-one condition. And after the calculation formula of the third matching type correction is obtained, correcting the matching pair based on the third matching type correction. More specifically, when the third matching type correction is larger than a preset correction threshold, connecting the point to be analyzed and the point to be matched to obtain a corresponding matching pair. In the embodiment of the invention, the preset correction threshold value is 0.7, and in other embodiments, the value can be adjusted by an implementer according to actual conditions.
And step S300, determining the fitness of the hairiness spectrum curve and the different hair dye spectrum curves based on the corrected matching distance of the matching pair, and inputting the hairiness spectrum curve, the fitness and the hair dye spectrum curve of the customer into a trained neural network to obtain the fitness of the hairiness spectrum curve and the different hair dye spectrum curves of the customer' S hair.
After the corrected matching pair is obtained, the fitness of the hairiness spectrum curve and the different hairdye spectrum curves is determined based on the matching distance of the corrected matching pair. As an embodiment of the present invention, a hair dye spectrum curve for an arbitrary hair dye. And (3) marking the average value of the matching distances between all matching pairs in the hairiness spectrum curve and the hairdye spectrum curve, namely the average value of the DTW distance, namely the negative correlation normalized mapping value of the average value of the dynamic time warping distance, and marking the negative correlation normalized mapping value of the average value of the matching distances as fitness.
And analyzing the hairiness spectrum curve and the hairdye spectrum curve in the neural network training set to determine the corresponding fitness. And the matching degree scoring is carried out on the hairiness spectrum curve and the hairdye spectrum curve through the analysis by the expert artificially, and the matching degree of the hairiness of the customer is higher as the hairiness of the customer is matched with the hairdye. The neural network is trained through the hairiness spectrum curve and the hair dye spectrum curve in the neural network training set, the corresponding fitness and the corresponding fitness, so that after the calculated fitness, the hair spectrum and the hair dye spectrum data are input into the trained neural network, the corresponding fitness can be obtained, and the expert is not required to perform artificial labeling. And the subjective and objective combination is realized by scoring the fitness obtained by combining the data analysis and the fitness manually evaluated by the expert, so that the fitness of the hair dye which is more matched with the hair of the customer is obtained.
In constructing a convolutional neural network (Convolutional Neural Networks, CNN) model, the calculated fitness, hairiness and hair dye spectral curves are used as inputs to the trained neural network, and these input data are subjected to appropriate pre-processing, such as normalization and dimensional adjustment, to ensure that they can be processed efficiently by the network. It is an object of embodiments of the present invention to predict a scalar value, i.e. fitness, from this convolutional neural network model, which quantifies the compatibility between a particular hair dye and a hair sample.
The loss function of the convolutional neural network is a cross entropy loss function, because the output is a scalar value, and the cross entropy loss function is suitable for the classification problem of the scalar value, so that the difference between the predicted value and the true value can be effectively measured. The output layer of the convolutional neural network is designed to have only one neuron, which outputs a value between 0 and 1 by activating a function, representing the probability of fitness. In the training process, the weight and bias of the network are continuously adjusted to minimize the cross entropy loss between the prediction adaptation degree and the actual adaptation degree, so that the prediction accuracy of the model is improved. Furthermore, to enhance the generalization ability of the model, regularization techniques, such as random inactivation (dropout) or L2 regularization, can be introduced in the convolutional neural network to prevent overfitting. In this way, it is expected that the trained model will perform well not only on training data, but also on new, unseen data to make accurate fitness predictions.
According to the invention, the user can also use the hair dye corresponding to the hair quality spectrum curve of the user hair to be detected, which has the largest adaptation degree, as the best-fit hair dye, and make corresponding recommendation to the user, and can select the hair dye which is arranged from top to bottom according to the sequence of the adaptation degree from top to bottom, and the hair dye with the largest adaptation degree ranks the most front.
The embodiment of the invention provides a hair quality detection system for cosmetology and hairdressing, which comprises the following modules:
the hair quality spectrum curve of the customer hair is matched with the hair dye spectrum curves of different hair dyes by utilizing a dynamic time warping algorithm, so that a matching pair formed by matching points is obtained;
The spectrum analysis module is used for correcting the matching pairs of different matching types by combining the reflectivities of different points and corresponding matching points on the light-emitting spectrum curve, the reflectivities of the points with the same wavelength on the hair dye spectrum curve, the positions of the matching points in the matching pair and the associated points to be matched;
and the adaptation degree analysis module is used for determining the adaptation degree of the hairiness spectrum curve and the different hair dye spectrum curves based on the corrected matching distance of the matching pair, inputting the hairiness spectrum curve, the adaptation degree and the hair dye spectrum curve of the customer into the trained neural network, and obtaining the adaptation degree of the hairiness spectrum curve and the different hair dye spectrum curves of the customer.
Alternatively, the transmission medium may be a wired link, such as, but not limited to, coaxial cable, fiber optic, and digital subscriber lines, etc., or a wireless link, such as, but not limited to, wireless internet (WIRELESS FIDELITY, WIFI), bluetooth, and mobile device networks, etc.
It should be noted that, in the apparatus provided in the above embodiment, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to perform all or part of the functions described above. In addition, the shopping guide device provided in the above embodiment and the image extension method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which is not described herein again.
Fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present invention. Illustratively, as shown in FIG. 6, the computer device 600 includes a memory 610, a processor 620, and a computer program 630 stored in the memory 610 and running on the processor 620, wherein execution of the computer program 630 by the processor 620 causes the computer device to perform any of the previously described methods of hair quality detection for cosmesis.
In addition, the embodiment of the invention also protects a device, which can comprise a memory and a processor, wherein executable program codes are stored in the memory, and the processor is used for calling and executing the executable program codes to execute the hair quality detection method for hairdressing and beauty.
The embodiment of the invention can divide the functional modules of the device according to the method example, for example, the functional modules can be corresponding, or two or more functions can be integrated into one processing module, and the integrated modules can be realized in a hardware form. It should be noted that, in this embodiment, the division of the modules is schematic, only one logic function is divided, and another division manner may be implemented in actual implementation.
In the case of dividing the respective modules by the respective functions, the apparatus may further include a signal uploading module, a determining module, an adjusting module, and the like. It should be noted that, all relevant contents of each step related to the above method embodiment may be cited to the functional description of the corresponding functional module, which is not described herein.
It should be understood that the apparatus provided by the embodiment of the present invention is used to perform the above-described method for detecting hair quality for beauty and hairdressing, and thus the same effects as those of the above-described implementation method can be achieved.
In case of an integrated unit, the apparatus may comprise a processing module, a memory module. When the device is applied to equipment, the processing module can be used for controlling and managing the actions of the equipment. The memory module may be used to support devices executing inter-program code, etc. Wherein a processing module may be a processor or controller that may implement or execute the various illustrative logical blocks, modules, and circuits described in connection with the present disclosure. A processor may also be a combination of computing functions, including for example one or more microprocessors, digital Signal Processing (DSP) and microprocessor combinations, etc., and a memory module may be a memory.
In addition, the device provided by the embodiment of the invention can be a chip, a component or a module, and the chip can comprise a processor and a memory which are connected, wherein the memory is used for storing instructions, and when the processor calls and executes the instructions, the chip can be made to execute the hair quality detection method for hairdressing and beauty.
Embodiments of the present invention also provide a computer-readable storage medium having stored therein computer program code which, when run on a computer, causes the computer to perform the above-described related method steps to implement a hair quality detection method for beauty treatment and hairdressing provided in the above-described embodiments.
The embodiment of the invention also provides a computer program product, which when run on a computer, causes the computer to execute the relevant steps so as to realize the hair quality detection method for hairdressing and beauty.
The apparatus, the computer readable storage medium, the computer program product, or the chip provided by the embodiments of the present invention are used to execute the corresponding method provided above, so that the beneficial effects thereof can be referred to the beneficial effects in the corresponding method provided above, and will not be described herein. It will be appreciated by those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to perform all or part of the functions described above. In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners.
The above-described apparatus embodiments are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another apparatus, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
It should also be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
It should be noted that the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention.
Claims (3)
1. A method for detecting hair quality for beauty treatment and hairdressing, comprising the steps of:
matching the hairiness spectrum curve with hairdye spectrum curves of different hairdyes by utilizing a dynamic time warping algorithm to obtain a matching pair consisting of matching points;
For the matching pairs of different matching types, the matching pairs of different matching types are corrected by combining the reflectivities of different points and corresponding matching points on the light-emitting spectrum curve, the reflectivities of points with the same wavelength on the hair dye spectrum curve, the positions of the matching points in the matching pairs and the associated points to be matched;
The matching distance of the corrected matching pair is based on the matching distance, and the fitness of the hairiness spectrum curve and the hairdye spectrum curve of different hairdye is determined;
wherein, for the matching pairs of different matching types, the matching pairs of different matching types are corrected by combining the reflectivities of different points and corresponding matching points on the light emission spectrum curve, the reflectivities of points with the same wavelength on the hair dye spectrum curve, the positions of the matching points in the matching pairs and the associated points to be matched, and the method comprises the following steps:
The matching types of the matching pairs are one-to-one matching, one-to-many matching and many-to-one matching;
For a matching pair matched one to one, determining matching probability by combining the reflectivities of different points and corresponding matching points on the luminous spectrum curve and the reflectivities of points with the same wavelength on the hair dye spectrum curve, and reserving the matching pair based on the matching probability;
for one-to-many matching pairs, correcting the matching pairs by analyzing the positions of the matching points and the matching probability;
for many-to-one matching pairs, correcting the matching pairs by analyzing the positions of the matching points and the associated points to be matched;
Wherein, for the matching pair of one-to-one matching, the matching probability is determined by combining the reflectivities of different points and corresponding matching points on the light emission spectrum curve and the reflectivities of the points with the same wavelength on the hair dye spectrum curve, and the method comprises the following steps:
Taking any point on the light emission spectrum curve as a point to be analyzed, acquiring a matching pair to which the point to be analyzed belongs and matching points in the matching pair, and acquiring a point with the same wavelength as the point to be analyzed on the hair dye spectrum curve as the point to be matched;
taking a normalized value of the difference of the reflectivities of the point to be analyzed and the corresponding point to be matched as a first analysis value;
Taking a normalized value of the difference between the point to be analyzed and the matching point in the corresponding matching pair as a second analysis value;
Weighting the normalized value of the difference between the first analysis value and the second analysis value by taking the first analysis value as a weight to obtain the matching probability of a matching pair;
wherein the reserving the matching pairs based on the matching probability includes:
reserving the matching pairs with the corresponding matching probabilities larger than the preset matching threshold;
Wherein, for the matching pair of one-to-many matching, the matching pair is corrected by analyzing the position of the matching point and the matching probability, including:
Calculating the matching probability of each point to be analyzed and the corresponding matching point, and marking the matching probability as a first matching probability;
calculating a matching point corresponding to each point to be analyzed and a normalized value of a position difference value of the point to be matched;
sorting the matching points corresponding to the points to be analyzed according to the order of the order values to obtain a standard sequence;
sorting the matching points corresponding to the points to be analyzed according to the order of the first matching probability to obtain a matching sequence;
calculating the position difference of the same element in the standard sequence and the matching sequence, and determining a matching probability difference value;
combining the matching probability difference and the normalized value of the position difference value to determine a second matching type correction;
Correcting the matching pair based on the second matching type correction;
The correcting the matching pair by analyzing the position of the matching point and the associated point to be matched comprises the following steps:
calculating the sequence difference between the matching points of the points to be analyzed and the points to be matched;
Acquiring the number of matching pairs corresponding to the points to be matched, and recording the number as the number to be matched;
combining the sequence difference and the quantity to be matched, and determining a third matching type correction;
Correcting the matching pair based on the third matching type correction;
wherein the correcting the matching pair based on the third matching type correction includes:
When the third matching type correction is larger than a preset correction threshold, connecting the point to be analyzed and the point to be matched to obtain a corresponding matching pair;
Wherein, based on the matching distance of the matched pair after correction, the fitness of the hairiness spectrum curve and different hair dye spectrum curves is determined, comprising:
and regarding the hairdye spectrum curve of any hairdye, taking the corrected negative correlation normalized mapping value of the mean value of the dynamic time warping distances of each matched pair as the fitness of the hairiness spectrum curve and the hairdye spectrum curve.
2. The method for detecting hair quality for cosmetology and hairdressing according to claim 1, wherein after the matching degree of the hairiness spectrum curve and the different hairdye spectrum curves of the customer's hair is obtained, further comprising:
And taking the hair dye corresponding to the hair dye spectrum curve with the largest fitting degree as the hair dye which is most suitable for the hair of the customer.
3. A hair quality detection system for cosmetic and hairdressing comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of a hair quality detection method for cosmetic and hairdressing according to any one of claims 1-2 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410940114.8A CN118483169B (en) | 2024-07-12 | 2024-07-12 | Hair quality detection method and system for cosmetology and hairdressing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410940114.8A CN118483169B (en) | 2024-07-12 | 2024-07-12 | Hair quality detection method and system for cosmetology and hairdressing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118483169A CN118483169A (en) | 2024-08-13 |
| CN118483169B true CN118483169B (en) | 2024-11-29 |
Family
ID=92192438
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410940114.8A Active CN118483169B (en) | 2024-07-12 | 2024-07-12 | Hair quality detection method and system for cosmetology and hairdressing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118483169B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7523018B2 (en) * | 2005-02-28 | 2009-04-21 | Seethrough Ltd. | Hair coloring system |
| US7463356B2 (en) * | 2006-01-10 | 2008-12-09 | Seethrough Ltd. | Method for analyzing hair |
| WO2010004565A2 (en) * | 2008-07-10 | 2010-01-14 | Seethrough Ltd. | Forecasting of treated skin colors |
| JP6474615B2 (en) * | 2011-03-21 | 2019-02-27 | コロライト エルティーディー．ＣｏｌｏＲｉｇｈｔ Ｌｔｄ． | System for custom coloring |
| WO2015166340A2 (en) * | 2014-04-27 | 2015-11-05 | Coloright Ltd. | Apparatus and method for analyzing hair and/or predicting an outcome of a hair-coloring treatment |
| US20180125206A1 (en) * | 2016-11-09 | 2018-05-10 | Farouk Systems, Inc. | Method and apparatus for analyzing and treating hair |
-
2024
- 2024-07-12 CN CN202410940114.8A patent/CN118483169B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN118483169A (en) | 2024-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7463356B2 (en) | Method for analyzing hair | |
| CN110383805B (en) | Method and system for capturing a measurement image of a measured object | |
| US6314372B1 (en) | Method and apparatus for hair color characterization and treatment | |
| CN112740266B (en) | Method and system for determining the properties of a keratin surface and method and system for treating said keratin surface | |
| US7489816B2 (en) | Advanced cosmetic color analysis system and methods therefor | |
| US6888963B2 (en) | Image processing apparatus and image processing method | |
| EP1531720A2 (en) | Hair color measurement and treatment | |
| US20200221995A1 (en) | System and method for determining the condition of hair | |
| CN102985943A (en) | Color image processing method, color image processing device, and color image processing program | |
| US11896114B2 (en) | System for managing hair condition information and method for optimizing a cosmetic consultation system | |
| CN112580433A (en) | Living body detection method and device | |
| JP7141509B2 (en) | Pulse wave detection device, pulse wave detection method, and information processing program | |
| CN118483169B (en) | Hair quality detection method and system for cosmetology and hairdressing | |
| CN116824171A (en) | Band selection method and related devices for traditional Chinese medicine hyperspectral tongue images | |
| CN113252585B (en) | Method and device for judging gold surface coating based on hyperspectral image | |
| EP3671183A1 (en) | Method for determining a composition of pigments in a hair fiber | |
| EP4409242A1 (en) | Systems and method for skin color determination | |
| CN118076286A (en) | Method and apparatus for analyzing images of hair and skin on a subject's body | |
| MXPA97009591A (en) | Method and apparatus for characterization of color and treatment of the cabe |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |