CN116363021A - Intelligent collection system for nursing and evaluating wound patients - Google Patents
Intelligent collection system for nursing and evaluating wound patients Download PDFInfo
- Publication number
- CN116363021A CN116363021A CN202310644224.5A CN202310644224A CN116363021A CN 116363021 A CN116363021 A CN 116363021A CN 202310644224 A CN202310644224 A CN 202310644224A CN 116363021 A CN116363021 A CN 116363021A
- Authority
- CN
- China
- Prior art keywords
- noise
- value
- gray
- probability
- pixel points
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Physical Education & Sports Medicine (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to an intelligent collection system for nursing and evaluating a wound patient. The system comprises: the system comprises an acquisition module, a first processing module, a second processing module and a denoising module, wherein the acquisition module, the first processing module, the second processing module and the denoising module are used for determining initial noise pixel points and further determining initial noise influence coefficients; performing region growth on the initial noise pixel points to obtain a growth region; obtaining an area noise influence coefficient of a growth area; determining noise probability of an initial noise pixel point; determining a target growth area according to the noise probability; determining a noise adjustment factor by combining the target growth area and other growth areas; determining a noise suppression factor according to the noise adjustment factor and the regional noise influence coefficient; and carrying out wiener filtering denoising on the gray level image of the ward of the previous frame according to the noise suppression factor to obtain a denoised image. The method can effectively solve the phenomenon of excessive smoothness, enhance the image definition after denoising the ward gray level image, and improve the denoising effect.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an intelligent collection system for nursing and evaluating a wound patient.
Background
In intensive care units and postoperative recovery ward, real-time monitoring is usually needed for patients, and the round-trip inspection of related doctors and nurses can influence the rest of the patients, so that a camera device is usually installed in the ward to ensure that the conditions in the ward can be acquired in real time, but white noise is usually generated when the camera device outputs image information, and the output image definition is low.
In the related art, the output image is filtered by using the wiener filtering mode, so that the wiener filtering can not only reduce the noise of the image, but also eliminate the image blurring caused by the reasons of motion and the like.
Disclosure of Invention
In order to solve the technical problems of low image definition after denoising and poor denoising effect caused by excessive smoothing, the invention provides an intelligent acquisition system for nursing and evaluating a wound patient, which adopts the following technical scheme:
the invention provides an intelligent collection system for nursing and evaluating a wound patient, which comprises the following components:
the acquisition module is used for acquiring two adjacent frames of ward gray level images, wherein pixel points which are at the same position in the two adjacent frames of ward gray level images and have different gray level values are used as differential pixel points, initial noise pixel points are determined from the differential pixel points according to the gray level values of the pixel points in the previous frame of ward gray level image and the gray level values of the differential pixel points, and initial noise influence coefficients are determined according to the number of the initial noise pixel points and the number of all the pixel points in the previous frame of ward gray level image;
the first processing module is used for carrying out region growth on the initial noise pixel points in the gray level image of the ward of the previous frame to obtain at least one growth region; determining a regional noise influence coefficient of the growing region according to the initial noise influence coefficient, the gray value of the pixel point in the gray image of the ward of the previous frame and the gray value of the pixel point in the growing region;
the second processing module is used for determining the noise probability of the initial noise pixel point according to the gray value of the pixel point in the growth area and the gray value difference between the initial noise pixel point and the surrounding neighborhood pixel points; determining a target growth area according to the noise probability average value of the initial noise pixel points in each growth area; determining a noise adjustment factor according to the noise probability average value of the initial noise pixel points in the target growth area and the noise probability average value of all the initial noise pixel points except the initial noise pixel points in the target growth area;
the denoising module is used for determining a noise suppression factor according to the noise adjustment factor and the regional noise influence coefficient; and carrying out wiener filtering denoising on the ward gray level image of the previous frame according to the noise suppression factor to obtain a denoised image.
Further, the determining an initial noise pixel point from the differential pixel points according to the gray value of the pixel point in the ward gray image of the previous frame and the gray value of the differential pixel point includes:
calculating the gray value average value of all pixel points in the gray image of the ward of the previous frame as a first average value;
and taking the differential pixel point with the gray value larger than the first average value as an initial noise pixel point.
Further, the number of the differential pixel points and the initial noise influence coefficient are in positive correlation, the number of all the pixel points in the gray level image of the ward of the previous frame and the initial noise influence coefficient are in negative correlation, the number of the initial noise pixel points and the initial noise influence coefficient are in positive correlation, and the value of the initial noise influence coefficient is a normalized value.
Further, the determining the area noise influence coefficient of the growing area according to the initial noise influence coefficient, the gray value of the pixel point in the gray image of the ward of the previous frame and the gray value of the pixel point in the growing area includes:
respectively calculating the gray value average value of all pixel points in the growth area as a second average value of the corresponding growth area;
calculating an inverse proportion normalization value of the absolute value of the difference value between the second mean value and the first mean value as a mean value difference coefficient;
calculating the product of the mean difference coefficient and the initial noise influence coefficient as a noise correction weight of the growth area;
calculating gray value variances of all pixel points in the growing area, and obtaining an area noise influence coefficient of the growing area according to the gray value variances and the noise correction weight, wherein the noise correction weight and the area noise influence coefficient are in positive correlation, the gray value variances and the area noise influence coefficient are in positive correlation, and the value of the area noise influence coefficient is a normalized numerical value.
Further, the determining the noise probability of the initial noise pixel according to the gray value of the pixel in the growing area, the gray value difference between the initial noise pixel and the surrounding neighborhood pixel comprises:
taking the initial noise pixel point as a center, taking other pixel points in a neighborhood window with a preset size as neighborhood pixel points, and calculating the gray value difference absolute value of the initial noise pixel point and the neighborhood pixel points as gray value difference;
calculating a sum normalized value of gray value differences between the initial noise pixel point and each neighborhood pixel point respectively as a first probability factor;
calculating the absolute value of the difference between the gray value of the initial noise pixel point and the second average value as a second probability factor;
and obtaining noise probability according to the first probability factor and the second probability factor, wherein the first probability factor and the noise probability are in positive correlation, and the second probability factor and the noise probability are in positive correlation.
Further, the determining the target growing area according to the noise probability average value of the initial noise pixel point in each growing area includes:
respectively calculating the noise probability average value of all initial noise pixel points in each growing area as the area noise probability of the growing area;
and taking the growing area with the largest area noise probability as a target growing area.
Further, the determining a noise adjustment factor according to the noise probability average value of the initial noise pixel point in the target growth area and the noise probability average value of all the initial noise pixel points except the initial noise pixel point in the target growth area includes:
taking the noise probability average value of all the initial noise pixel points except the initial noise pixel point in the target growth area as other probability average values;
calculating the absolute value of the difference between the regional noise probability of the target growth region and the average value of other probabilities to be used as regional probability difference;
and calculating an inverse proportion normalization value of the regional probability difference as a noise adjustment factor.
Further, the noise adjustment factor and the noise suppression factor form a positive correlation, the maximum value of the noise influence coefficient of the corresponding region of the growth region and the noise suppression factor form a positive correlation, and the value of the noise suppression factor is a normalized value.
Further, the wiener filtering denoising is performed on the ward gray level image of the previous frame according to the noise suppression factor to obtain a denoised image, which comprises the following steps:
and taking the noise suppression factor as a minimum mean square error, and filtering and denoising the ward gray level image of the previous frame based on a wiener filtering algorithm to obtain a denoised image.
The invention has the following beneficial effects:
according to the method, the initial noise pixel points are determined through the differential pixel points, the pixel points with different gray values in the adjacent two frames of ward gray images can be effectively screened out, the initial noise pixel points are screened out according to the characteristics of the noise points, the accuracy of the initial noise pixel points is improved, the initial noise influence coefficient is further determined according to the number of the initial noise pixel points and the number of all the pixel points in the previous frame of ward gray image, after the area growth processing is carried out according to the initial noise pixel points, the gray values of the pixel points in the previous frame of ward gray image and the gray values of the pixel points in the growth area are combined, and therefore the area noise influence coefficient of the growth area can be effectively determined according to the gray value characteristics of the pixel points in different areas in the ward gray image; the method has the advantages that the reliability of the noise probability of the initial noise pixel point can be enhanced according to the characteristic that the noise point is usually an isolated point by combining the gray value distinction of the initial noise pixel point and the surrounding neighborhood pixel point, so that the obtained target growth area can represent the growth area which is affected by noise the greatest extent, the noise adjustment factor is determined according to the noise probability of the initial noise pixel point in the target growth area and the noise probability of all other initial noise pixel points, the reliability of the noise probability can be improved, excessive denoising of other areas caused by denoising according to the noise probability of the initial noise pixel point in the target growth area is avoided, the noise suppression factor is determined according to the noise adjustment factor and the regional noise influence coefficient, then the noise suppression factor is used for carrying out wiener filtering denoising on the gray image of the previous frame to obtain a denoising image, the noise situation in the ward gray image can be analyzed in a self-adaptive manner due to the combination of the noise adjustment factor and the regional noise influence coefficient, the excessive smoothing phenomenon caused in the wiener filtering process is effectively solved, the denoising image has better display effect, the denoising effect on the ward image is enhanced, and the denoising effect is ensured after the gray image is denoised, and the reliability of the image is improved.
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 block diagram of an intelligent collection system for wound patient care assessment, 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 detailed description refers to the specific implementation, structure, characteristics and effects of an intelligent collection system for wound patient care evaluation according to the invention, which is provided by the invention, with reference to 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.
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.
The following specifically describes a specific scheme of an intelligent collection system for nursing and evaluating wound patients provided by the invention with reference to the accompanying drawings.
Referring now to FIG. 1, a block diagram of a system for intelligent acquisition of wound patient care assessment, according to one embodiment of the present invention, is shown, the system 10 comprising: the device comprises an acquisition module 101, a first processing module 102, a second processing module 103 and a denoising module 104.
The acquisition module 101 is configured to acquire two adjacent frames of ward gray level images, wherein pixels with the same positions and different gray level values in the two adjacent frames of ward gray level images are used as differential pixels, determine initial noise pixels from the differential pixels according to the gray level value of the pixels in the previous frame of ward gray level image and the gray level value of the differential pixels, and determine an initial noise influence coefficient according to the number of the initial noise pixels and the number of all pixels in the previous frame of ward gray level image.
According to the embodiment of the invention, the monitoring equipment can be installed in an intensive care unit or a postoperative recovery unit, so that a nurse on duty can acquire the state of a patient in real time according to the monitoring picture, and it can be understood that the installation and the use of the monitoring equipment are agreed by related personnel, the acquisition process of the monitoring picture accords with related laws and regulations, and the public welcome is not violated.
In some embodiments of the present invention, the monitoring device may be used to periodically acquire images in a ward, for example, acquire images in a ward once a second, then extract ward images of two adjacent frames, and respectively perform grayscale processing on the ward images of two adjacent frames to obtain grayscale images of two adjacent frames of ward.
In other embodiments of the present invention, video data in a ward may be recorded in real time, and then, two continuous frames of video are extracted to obtain two adjacent frames of ward images, and gray-scale processing is performed on the two adjacent frames of ward images to obtain two adjacent frames of ward gray-scale images, which is not limited.
In the embodiment of the invention, the pixel points which are at the same position in the gray level images of two adjacent frames of ward and have different gray level values can be used as differential pixel points, namely, the gray level images of the two adjacent frames of ward are subjected to differential processing to obtain corresponding differential images, and the pixel points with the gray level values which are not 0 in the differential images are used as differential pixel points.
It can be understood that, for the ward gray level images of two adjacent frames, since the monitoring range is fixed, the change generated in the ward gray level images basically corresponds to the image change corresponding to the human activity and the change generated by the chaotic distribution of the noise, that is, the component parts of the differential pixel points comprise the pixel points and the noise pixel points generating the change of the human activity.
Optionally, in the embodiment of the present invention, determining, from the differential pixel points, an initial noise pixel point according to a gray value of the pixel point in the gray image of the ward of the previous frame and a gray value of the differential pixel point includes: calculating the gray value average value of all pixel points in the gray image of the ward of the previous frame as a first average value; and taking the differential pixel point with the gray value larger than the first average value as an initial noise pixel point.
In the embodiment of the invention, the first average value is the average value of gray values of all pixel points in the ward gray level image of the previous frame, and the gray characteristics of the pixel points in the gray level image of the previous frame are represented by the first average value, so that the method can be suitable for ward gray level images in different scenes, and as the noise is usually white, the differential pixel points with gray values larger than the first average value are correspondingly used as initial noise pixel points.
In the embodiment of the invention, the differential pixel points with the gray values larger than the first average value are screened as the initial noise pixel points, so that the differential pixel points generated by personnel activities and the corresponding white noise pixel points in the gray images of the ward of the next frame can be effectively screened, and the initial noise pixel points are ensured to be the noise pixel points of the gray images of the ward of the previous frame.
In the embodiment of the invention, the number of all pixel points in the gray level image of the ward of the previous frame and the initial noise influence coefficient are in a negative correlation relationship, the number of the initial noise pixel points and the initial noise influence coefficient are in a positive correlation relationship, and the value of the initial noise influence coefficient is a normalized value.
The positive correlation relationship indicates that the dependent variable increases along with the increase of the independent variable, the dependent variable decreases along with the decrease of the independent variable, and the specific relationship can be multiplication relationship, addition relationship, idempotent of an exponential function and is determined by practical application; the negative correlation indicates that the dependent variable decreases with increasing independent variable, and the dependent variable increases with decreasing independent variable, which may be a subtraction relationship, a division relationship, or the like, and is determined by the actual application.
In some embodiments of the present invention, a normalized value of a ratio of the number of initial noise pixels to the number of all pixels in the gray level image of the ward of the previous frame may be calculated as an initial noise influence coefficient, where the corresponding calculation formula is:
Because the ratio of the number of the initial noise pixels to the number of all pixels in the gray level image of the ward of the previous frame can represent the number ratio of the corresponding noise pixels to the number of all pixels in the gray level image of the ward of the previous frame, the larger the corresponding initial noise influence coefficient is, the more the number of the initial noise pixels can be represented, and the larger the gray level image of the ward of the previous frame is influenced by noise.
The first processing module 102 is configured to perform region growth on the initial noise pixel point in the gray level image of the ward of the previous frame to obtain at least one growth region; and determining the regional noise influence coefficient of the growing region according to the initial noise influence coefficient, the gray value of the pixel point in the gray image of the ward of the previous frame and the gray value of the pixel point in the growing region.
In the embodiment of the invention, the initial noise pixel points can be subjected to region growth based on the preset growth threshold in the gray level image of the ward of the previous frame to obtain at least one growth region, wherein the preset growth threshold is a threshold value of a gray level value corresponding to the region growth.
After the region growth is carried out on each initial noise pixel point, each initial noise pixel point can correspond to one initial growth region, and because the initial growth regions corresponding to the initial noise pixel points possibly have overlapped parts, the initial growth regions which are overlapped can be combined into one integral growth region, so that a final growth region is obtained.
Optionally, in the embodiment of the present invention, determining the area noise influence coefficient of the growth area according to the initial noise influence coefficient, the gray value of the pixel point in the gray image of the ward of the previous frame, and the gray value of the pixel point in the growth area includes: respectively calculating the gray value average value of all pixel points in the growth area as a second average value of the corresponding growth area; calculating an inverse proportion normalization value of the absolute value of the difference value between the second mean value and the first mean value as a mean value difference coefficient; calculating the product of the mean difference coefficient and the initial noise influence coefficient as a noise correction weight of the growth area; and calculating gray value variances of all pixel points in the growing area, and obtaining an area noise influence coefficient of the growing area according to the gray value variances and the noise correction weight, wherein the noise correction weight and the area noise influence coefficient are in positive correlation, the gray value variances and the area noise influence coefficient are in positive correlation, and the value of the area noise influence coefficient is a normalized value. The corresponding calculation formula is:
It will be appreciated that because the image is divided into different pixels, the larger the gray scale difference between the patient gray scale image and the growth area, the more likely the corresponding growth area is the patient moving area, the less likely the growth area is the growth area corresponding to noise, and the region noise influence coefficient is the index for representing the noise influence degree of the growth area, so the smaller the corresponding region noise influence coefficient is, that is, the larger the difference between the second average value and the first average value is, the smaller the average value difference coefficient is, the smaller the corresponding noise correction weight is, and the more the image is due to the first average value
The larger the initial noise influence coefficient of the gray level image of the frame ward, the characterization of the +.>
The more the frame ward gray level image is affected by noise, the larger the corresponding noise correction weight.
The larger the variance of the gray values of all the pixel points in the growing area, the larger the variation degree of the gray values in the ward gray image is, that is, the larger the variation degree of the texture of the growing area is, it can be understood that, because the noise is usually an isolated point, that is, the gray values in the growing area corresponding to the noise are different from the gray values in other growing areas, the difference of the corresponding gray values is larger when the area grows, the variance of the gray values is larger, and when the normal pixel points perform the area growth, the gray values of the growing area corresponding to the normal pixel points are obtained by forming the pixel points with similar gray values into the same growing area, that is, the gray values of the growing area corresponding to the normal pixel points are closer, and the variance of the gray values of the corresponding normal growing area is smaller.
The noise correction weight and the regional noise influence coefficient are in positive correlation, and the gray value variance and the regional noise influence coefficient are in positive correlation. By calculating the product of the noise correction weight and the gray value variance as the regional noise influence coefficient, the noise influence condition of the growing region can be represented according to the information such as the gray value numerical information of the pixel points in the growing region and the texture change degree, that is, when the regional noise influence coefficient is larger, the influence of the corresponding growing region by the noise pixel points is larger, and when the regional noise influence coefficient is smaller, the influence of the corresponding growing region by the noise pixel points is smaller.
A second processing module 103, configured to determine a noise probability of the initial noise pixel according to a gray value of the pixel in the growth area, a gray value difference between the initial noise pixel and surrounding neighboring pixels; determining a target growth area according to the noise probability average value of the initial noise pixel points in each growth area; and determining a noise adjustment factor according to the noise probability average value of the initial noise pixel points in the target growth area and the noise probability average value of all the initial noise pixel points except the initial noise pixel points in the target growth area.
Further, in some embodiments of the present invention, determining the noise probability of the initial noise pixel according to the gray value of the pixel in the growth area, the gray value difference between the initial noise pixel and the surrounding neighboring pixels includes: taking the initial noise pixel point as a center, taking other pixel points in a neighborhood window with a preset size as neighborhood pixel points, and calculating the gray value difference absolute value between the initial noise pixel point and the neighborhood pixel points as gray value difference; calculating a sum normalized value of gray value differences between the initial noise pixel point and each neighborhood pixel point respectively as a first probability factor; calculating the absolute value of the difference between the gray value of the initial noise pixel point and the second average value as a second probability factor; and obtaining noise probability according to the first probability factor and the second probability factor, wherein the first probability factor and the noise probability are in positive correlation, and the second probability factor and the noise probability are in positive correlation.
The preset size may be, for example, a size of 3×3, which is not limited in this embodiment of the present invention. The calculation formula corresponding to the noise probability of the initial noise pixel point is determined according to the gray value of the pixel point in the neighborhood window with the preset size, wherein the calculation formula is as follows:
It can be understood that when image denoising is performed, the most effective method is that noise points can be identified, then the noise pixel points are filled according to gray values of the neighborhood pixel points, so that pixel points can be prevented from being traversed on a global image, and detail information cannot be lost.
Further, in some embodiments of the present invention, determining the target growth region according to the noise probability average of the initial noise pixel point in each growth region includes: respectively calculating the noise probability average value of all initial noise pixel points in each growing area as the area noise probability of the growing area; and taking the growing area with the largest area noise probability as a target growing area.
In the embodiment of the invention, since the number of the initial noise pixel points in the growing area can be multiple, in order to effectively analyze the growing area, the average value of the noise probabilities of all the initial noise pixel points in the growing area can be used as the area noise probability of the growing area, wherein the area noise probability of the growing area is maximum, the growing area which is more likely to be the most densely distributed in noise can be represented, and the growing area with the maximum area noise probability can be used as the target growing area.
Further, in some embodiments of the present invention, determining the noise adjustment factor according to the noise probability average value of the initial noise pixel point in the target growth area and the noise probability average value of all the other initial noise pixel points except the initial noise pixel point in the target growth area includes: taking the noise probability average value of all the other initial noise pixel points except the initial noise pixel point in the target growth area as other probability average values; calculating the absolute value of the difference between the regional noise probability of the target growth region and the other probability mean value as regional probability difference; an inverse proportion normalization value of the region probability difference is calculated as a noise adjustment factor.
In the embodiment of the invention, all the initial noise pixel points except the initial noise pixel point in the target growth area can be used as other noise pixel points, so that a calculation formula corresponding to the noise adjustment factor is as follows:
In the embodiment of the invention, as the difference between the growth area with the largest noise influence and other growth areas is represented by the area probability difference, the noise probability of the different growth areas is different when denoising is performed, if the noise adjustment factor of the whole ward gray level image is determined directly according to the growth area with the largest noise probability, namely the target growth area, and denoising is performed, the phenomenon of excessive denoising of the other growth areas is caused, the ward gray level image is smoothed, and the display effect is poor, therefore, the embodiment determines the noise adjustment factor by calculating the difference absolute value of the area noise probability of the target growth area and the average value of other probabilities as the area probability difference and representing the noise probability difference between the area with the largest noise influence and the other areas according to the area probability difference, so that the whole ward gray level image can be denoising uniformly, and the quality of the whole denoised image is better.
The denoising module 104 is configured to determine a noise suppression factor according to the noise adjustment factor and the regional noise influence coefficient; and carrying out wiener filtering denoising on the gray level image of the ward of the previous frame according to the noise suppression factor to obtain a denoised image.
Further, the noise adjustment factor and the noise suppression factor form a positive correlation, the maximum value of the noise influence coefficient of the corresponding region of the growth region and the noise suppression factor form a positive correlation, and the value of the noise suppression factor is a normalized value. In some embodiments of the present invention, the corresponding calculation formula may be:
Of course, the implementer may also characterize the noise suppression factor by other forms of formulas, such as:
According to the embodiment of the invention, the noise suppression factor is obtained according to the noise adjustment factor and the regional noise influence factor, the noise influence factor is processed through the noise influence factor because the noise adjustment factor represents the noise influence condition of the image, the noise suppression factor is obtained, when the noise adjustment factor is larger, the regional probability difference is smaller, and because the regional probability difference is the absolute value of the difference between the regional noise probability of the target growth region and other probability mean values, the target growth region is the growth region with the largest regional noise probability, namely, the target growth region represents the region with the most serious noise influence, and the regional probability difference between the other probability mean values and the target growth region is smaller, so that the noise influence in the gray image of the whole ward is larger, the noise suppression factor is required to be larger, namely, the noise adjustment factor and the noise suppression factor are in positive correlation, and the maximum value of the regional noise influence factor is represented in the growth region because the maximum value of the regional noise influence factor is larger, namely, the maximum value of the regional noise influence factor corresponding to the growth region and the noise suppression factor are in positive correlation, and thus the noise suppression factor is calculated.
Further, in the embodiment of the present invention, wiener filtering denoising is performed on a gray level image of a ward of a previous frame according to a noise suppression factor, so as to obtain a denoised image, including: and taking the noise suppression factor as a minimum mean square error, and filtering and denoising the ward gray level image of the previous frame based on a wiener filtering algorithm to obtain a denoising image.
The wiener filtering is an existing algorithm for filtering according to minimum mean square error, and the noise suppression factor is used as the minimum mean square error in the wiener filtering, so that the adaptive denoising processing is performed on the gray level image of each frame ward through the adaptive noise suppression factor to obtain a denoising image.
It can be understood that after the denoising image is obtained, the denoising image can be displayed in a service desk or a monitoring room, so that relevant service personnel can perform corresponding services, such as dressing change, emergency treatment and the like, according to personnel performance and corresponding equipment states in a ward in the denoising image and by combining experience of the service personnel, and the denoising image is not limited.
According to the method, the initial noise pixel points are determined through the differential pixel points, the pixel points with different gray values in the adjacent two frames of ward gray images can be effectively screened out, the initial noise pixel points are screened out according to the characteristics of the noise points, the accuracy of the initial noise pixel points is improved, the initial noise influence coefficient is further determined according to the number of the initial noise pixel points and the number of all the pixel points in the previous frame of ward gray image, after the area growth processing is carried out according to the initial noise pixel points, the gray values of the pixel points in the previous frame of ward gray image and the gray values of the pixel points in the growth area are combined, and therefore the area noise influence coefficient of the growth area can be effectively determined according to the gray value characteristics of the pixel points in different areas in the ward gray image; the method and the device have the advantages that the reliability of the noise probability of the initial noise pixel point can be enhanced according to the characteristic that the noise point is usually an isolated point by combining the gray value distinction of the initial noise pixel point and the surrounding neighborhood pixel point, so that the obtained target growth area can represent the growth area with the largest influence of noise, the noise adjustment factor is determined according to the noise probability of the initial noise pixel point in the target growth area and the noise probability of all other initial noise pixel points, the reliability of the noise probability can be improved, excessive denoising of other areas caused by denoising according to the noise probability of the initial noise pixel point in the target growth area is avoided, the noise suppression factor is determined according to the noise adjustment factor and the regional noise influence coefficient, then the noise suppression factor is used for carrying out wiener filtering denoising on the gray image of the previous frame to obtain a denoising image, the noise situation in the ward gray image is analyzed in a self-adapting mode due to the combination of the noise adjustment factor and the regional noise influence coefficient, the phenomenon caused by wiener filtering is effectively solved, the denoising image has better display effect, the denoising effect is enhanced, and the denoising effect of the ward image after the gray image is denoised, and the reliability of the ward image is improved.
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.
Claims (9)
1. An intelligent collection system for wound patient care assessment, the system comprising:
the acquisition module is used for acquiring two adjacent frames of ward gray level images, wherein pixel points which are at the same position in the two adjacent frames of ward gray level images and have different gray level values are used as differential pixel points, initial noise pixel points are determined from the differential pixel points according to the gray level values of the pixel points in the previous frame of ward gray level image and the gray level values of the differential pixel points, and initial noise influence coefficients are determined according to the number of the initial noise pixel points and the number of all the pixel points in the previous frame of ward gray level image;
the first processing module is used for carrying out region growth on the initial noise pixel points in the gray level image of the ward of the previous frame to obtain at least one growth region; determining a regional noise influence coefficient of the growing region according to the initial noise influence coefficient, the gray value of the pixel point in the gray image of the ward of the previous frame and the gray value of the pixel point in the growing region;
the second processing module is used for determining the noise probability of the initial noise pixel point according to the gray value of the pixel point in the growth area and the gray value difference between the initial noise pixel point and the surrounding neighborhood pixel points; determining a target growth area according to the noise probability average value of the initial noise pixel points in each growth area; determining a noise adjustment factor according to the noise probability average value of the initial noise pixel points in the target growth area and the noise probability average value of all the initial noise pixel points except the initial noise pixel points in the target growth area;
the denoising module is used for determining a noise suppression factor according to the noise adjustment factor and the regional noise influence coefficient; and carrying out wiener filtering denoising on the ward gray level image of the previous frame according to the noise suppression factor to obtain a denoised image.
2. The intelligent collection system for wound patient care assessment of claim 1, wherein said determining initial noise pixels from said differential pixels based on gray values of pixels in a previous frame of ward gray image and gray values of differential pixels comprises:
calculating the gray value average value of all pixel points in the gray image of the ward of the previous frame as a first average value;
and taking the differential pixel point with the gray value larger than the first average value as an initial noise pixel point.
3. The intelligent collection system for wound patient care assessment according to claim 1, wherein the number of all pixels in the gray level image of the ward of the previous frame and the initial noise influence coefficient are in a negative correlation, the number of the initial noise pixels and the initial noise influence coefficient are in a positive correlation, and the value of the initial noise influence coefficient is a normalized value.
4. The intelligent wound patient care assessment acquisition system according to claim 2, wherein said determining the regional noise impact factor of the growing region based on the initial noise impact factor, the gray values of pixels in the gray image of the previous frame of ward, and the gray values of pixels in the growing region comprises:
respectively calculating the gray value average value of all pixel points in the growth area as a second average value of the corresponding growth area;
calculating an inverse proportion normalization value of the absolute value of the difference value between the second mean value and the first mean value as a mean value difference coefficient;
calculating the product of the mean difference coefficient and the initial noise influence coefficient as a noise correction weight of the growth area;
calculating gray value variances of all pixel points in the growing area, and obtaining an area noise influence coefficient of the growing area according to the gray value variances and the noise correction weight, wherein the noise correction weight and the area noise influence coefficient are in positive correlation, the gray value variances and the area noise influence coefficient are in positive correlation, and the value of the area noise influence coefficient is a normalized numerical value.
5. The intelligent wound patient care assessment acquisition system according to claim 4, wherein said determining the noise probability of said initial noise pixel based on the gray value of pixels in said growth area, the gray value difference between said initial noise pixel and surrounding neighborhood pixels, comprises:
taking the initial noise pixel point as a center, taking other pixel points in a neighborhood window with a preset size as neighborhood pixel points, and calculating the gray value difference absolute value of the initial noise pixel point and the neighborhood pixel points as gray value difference;
calculating a sum normalized value of gray value differences between the initial noise pixel point and each neighborhood pixel point respectively as a first probability factor;
calculating the absolute value of the difference between the gray value of the initial noise pixel point and the second average value as a second probability factor;
and obtaining noise probability according to the first probability factor and the second probability factor, wherein the first probability factor and the noise probability are in positive correlation, and the second probability factor and the noise probability are in positive correlation.
6. The intelligent wound patient care assessment acquisition system according to claim 1, wherein said determining a target growing region from a noise probability average of initial noise pixels in each of said growing regions comprises:
respectively calculating the noise probability average value of all initial noise pixel points in each growing area as the area noise probability of the growing area;
and taking the growing area with the largest area noise probability as a target growing area.
7. The intelligent wound patient care assessment acquisition system of claim 6, wherein the determining a noise adjustment factor based on the noise probability average of the initial noise pixels in the target growth area and the noise probability average of all but the initial noise pixels in the target growth area comprises:
taking the noise probability average value of all the initial noise pixel points except the initial noise pixel point in the target growth area as other probability average values;
calculating the absolute value of the difference between the regional noise probability of the target growth region and the average value of other probabilities to be used as regional probability difference;
and calculating an inverse proportion normalization value of the regional probability difference as a noise adjustment factor.
8. The intelligent wound patient care assessment acquisition system according to claim 1, wherein the noise adjustment factor and the noise suppression factor are in positive correlation, the maximum value of the noise influence coefficient of the corresponding region of the growth region and the noise suppression factor are in positive correlation, and the noise suppression factor is a normalized value.
9. The intelligent wound patient care assessment acquisition system according to claim 1, wherein said wiener filtering denoising of the gray scale image of the previous frame of ward according to said noise suppression factor to obtain a denoised image, comprising:
and taking the noise suppression factor as a minimum mean square error, and filtering and denoising the ward gray level image of the previous frame based on a wiener filtering algorithm to obtain a denoised image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310644224.5A CN116363021B (en) | 2023-06-02 | 2023-06-02 | Intelligent collection system for nursing and evaluating wound patients |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310644224.5A CN116363021B (en) | 2023-06-02 | 2023-06-02 | Intelligent collection system for nursing and evaluating wound patients |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116363021A true CN116363021A (en) | 2023-06-30 |
| CN116363021B CN116363021B (en) | 2023-07-28 |
Family
ID=86905504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310644224.5A Active CN116363021B (en) | 2023-06-02 | 2023-06-02 | Intelligent collection system for nursing and evaluating wound patients |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116363021B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117278692A (en) * | 2023-11-16 | 2023-12-22 | 邦盛医疗装备（天津）股份有限公司 | Desensitization protection method for monitoring data of medical detection vehicle patients |
| CN117523532A (en) * | 2023-11-29 | 2024-02-06 | 北京斯年智驾科技有限公司 | Weed point cloud filtering method, system and storage medium |
| CN117911273A (en) * | 2024-03-15 | 2024-04-19 | 深圳市桦隆科技有限公司 | Auxiliary positioning method for cutting protection leather sheath with keyboard by iPad |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008219296A (en) * | 2007-03-01 | 2008-09-18 | Fuji Xerox Co Ltd | Image inspection apparatus and image forming apparatus |
| CN102637404A (en) * | 2011-12-23 | 2012-08-15 | 友达光电股份有限公司 | Display and method for generating output image by display |
| CN105472204A (en) * | 2014-09-05 | 2016-04-06 | 南京理工大学 | Inter-frame noise reduction method based on motion detection |
| CN111951949A (en) * | 2020-01-21 | 2020-11-17 | 梅里医疗科技(洋浦)有限责任公司 | Intelligent nursing interaction system for intelligent ward |
| CN115311604A (en) * | 2022-09-29 | 2022-11-08 | 江苏海舟安防科技有限公司 | Fire fighting method based on Internet of things |
-
2023
- 2023-06-02 CN CN202310644224.5A patent/CN116363021B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008219296A (en) * | 2007-03-01 | 2008-09-18 | Fuji Xerox Co Ltd | Image inspection apparatus and image forming apparatus |
| CN102637404A (en) * | 2011-12-23 | 2012-08-15 | 友达光电股份有限公司 | Display and method for generating output image by display |
| CN105472204A (en) * | 2014-09-05 | 2016-04-06 | 南京理工大学 | Inter-frame noise reduction method based on motion detection |
| CN111951949A (en) * | 2020-01-21 | 2020-11-17 | 梅里医疗科技(洋浦)有限责任公司 | Intelligent nursing interaction system for intelligent ward |
| CN115311604A (en) * | 2022-09-29 | 2022-11-08 | 江苏海舟安防科技有限公司 | Fire fighting method based on Internet of things |
Non-Patent Citations (3)
| Title |
|---|
| 汪凯;张贵仓;: "基于改进蚁群算法的图像边缘检测研究", 计算机工程与应用, no. 23 * |
| 熊钢;平西建;张涛;孙兵;: "一种基于图像内容的最低有效位匹配隐写分析方法", 电子与信息学报, no. 06 * |
| 胡永生;杨玲玲;: "基于背景差值法的运动物体检测", 福建电脑, no. 12 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117278692A (en) * | 2023-11-16 | 2023-12-22 | 邦盛医疗装备（天津）股份有限公司 | Desensitization protection method for monitoring data of medical detection vehicle patients |
| CN117278692B (en) * | 2023-11-16 | 2024-02-13 | 邦盛医疗装备（天津）股份有限公司 | Desensitization protection method for monitoring data of medical detection vehicle patients |
| CN117523532A (en) * | 2023-11-29 | 2024-02-06 | 北京斯年智驾科技有限公司 | Weed point cloud filtering method, system and storage medium |
| CN117523532B (en) * | 2023-11-29 | 2024-06-04 | 北京斯年智驾科技有限公司 | Weed point cloud filtering method, system and storage medium |
| CN117911273A (en) * | 2024-03-15 | 2024-04-19 | 深圳市桦隆科技有限公司 | Auxiliary positioning method for cutting protection leather sheath with keyboard by iPad |
| CN117911273B (en) * | 2024-03-15 | 2024-05-28 | 深圳市桦隆科技有限公司 | Auxiliary positioning method for cutting protection leather sheath with keyboard by iPad |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116363021B (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116363021B (en) | Intelligent collection system for nursing and evaluating wound patients | |
| US9002131B2 (en) | Method and system for enhancing image quality | |
| Amiri et al. | A preprocessing approach for image analysis using gamma correction | |
| JP5721936B2 (en) | How to evaluate the quality of a distorted version of a frame sequence | |
| Liu et al. | A perceptually relevant no-reference blockiness metric based on local image characteristics | |
| US20110125030A1 (en) | Medical diagnostic device and method of improving image quality of medical diagnostic device | |
| CN107705260B (en) | The denoising system and calculation method of medical X-ray image | |
| CN117132510B (en) | Monitoring image enhancement method and system based on image processing | |
| CN117764864B (en) | Nuclear magnetic resonance tumor visual detection method based on image denoising | |
| CN111863232B (en) | Remote disease intelligent diagnosis system based on block chain and medical image | |
| CN106557729B (en) | Apparatus and method for processing face image | |
| CN117876402B (en) | Intelligent segmentation method for temporomandibular joint disorder image | |
| CN104915930B (en) | The method and device of grey level compensation and noise suppressed is carried out to image | |
| CN116109558A (en) | Method for screening fetal chromosomal abnormalities based on neck semitransparent thickness measurement | |
| CN116385316B (en) | Multi-target image dynamic capturing method and related device | |
| CN117036310A (en) | DICOM image peripheral outline identification and extraction method | |
| CN115797333B (en) | A personalized and customized intelligent vision training method | |
| CN118097160A (en) | Critical patient status monitoring system based on visual technology | |
| CN112507818A (en) | Illumination estimation method and system based on near-infrared image | |
| Radhika et al. | An adaptive optimum weighted mean filter and bilateral filter for noise removal in cardiac MRI images | |
| CN116596879A (en) | Grape downy mildew self-adaptive identification method based on quantiles of boundary samples | |
| CN114510976B (en) | Breathing signal denoising method and device based on bivariate threshold function | |
| Kerouh et al. | A perceptual blind blur image quality metric | |
| CN114693682A (en) | Spine feature identification method based on image processing | |
| WO2008056305A1 (en) | Noise reduction of an image signal |
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 |