CN117115126B - Method for determining multi-color overlapping intersection area of printed matter, storage medium and device - Google Patents
Method for determining multi-color overlapping intersection area of printed matter, storage medium and device Download PDFInfo
- Publication number
- CN117115126B CN117115126B CN202311139786.0A CN202311139786A CN117115126B CN 117115126 B CN117115126 B CN 117115126B CN 202311139786 A CN202311139786 A CN 202311139786A CN 117115126 B CN117115126 B CN 117115126B
- Authority
- CN
- China
- Prior art keywords
- image
- projection
- feature
- lab
- color
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000004364 calculation method Methods 0.000 claims description 29
- 239000003086 colorant Substances 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 abstract description 22
- 238000005259 measurement Methods 0.000 description 12
- 230000003287 optical effect Effects 0.000 description 5
- 238000002798 spectrophotometry method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30144—Printing quality
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Color Image Communication Systems (AREA)
- Facsimile Image Signal Circuits (AREA)
- Image Analysis (AREA)
Abstract
本发明公开了一种印刷品多色彩叠加交汇区域的确定方法、存储介质及装置，涉及图像处理领域，该方法包括获取包含多色彩叠加交汇区域的待检测RGB图像，并转换为HSI图像，计算得到饱和度特征图像；计算得到饱和度特征的掩膜图像，得到前景图像；对前景图像进行投影处理，将投影后的RGB图像转换为Lab图像，即获取得到投影特征Lab图像，拟合投影特征Lab图像中端点与非端点间距离得到投影特征曲线；基于投影特征曲线，得到待检测RGB图像中多色彩叠加交汇区域的起始位置以及交界点。本发明采用非接触式检测方式，在不破坏被测印刷体表面特征的同时获得准确的检测结果，且检测准确性高，鲁棒性更强，且不受墨色深浅的影响。
The present invention discloses a method, storage medium and device for determining a multi-color overlapping intersection area of a printed product, and relates to the field of image processing. The method comprises obtaining an RGB image to be detected containing a multi-color overlapping intersection area, converting the image into an HSI image, and calculating a saturation characteristic image; calculating a mask image of a saturation characteristic to obtain a foreground image; performing projection processing on the foreground image, converting the projected RGB image into a Lab image, that is, obtaining a projection characteristic Lab image, fitting the distance between the endpoint and the non-endpoint in the projection characteristic Lab image to obtain a projection characteristic curve; based on the projection characteristic curve, obtaining the starting position and the intersection point of the multi-color overlapping intersection area in the RGB image to be detected. The present invention adopts a non-contact detection method, obtains accurate detection results without destroying the surface characteristics of the printed body to be detected, and has high detection accuracy, stronger robustness, and is not affected by the depth of ink color.
Description
Technical Field
The invention relates to the field of image processing, in particular to a method for determining a multi-color overlapping intersection area of a printed matter, a storage medium and a device.
Background
The printed matter has color difference with the sample after printing due to various reasons in the printing process, so that the quality of the printed matter is reduced. The control and detection of chromatic aberration of the multi-color overlapping intersection area in the printed matter are important points, so that on one hand, the cost can be controlled to the greatest extent, and on the other hand, the quality of the printed matter can be effectively improved. The traditional multi-color overlapping intersection region color difference detection is characterized in that a color image is directly converted into a gray image, the gray value of the gray image is analyzed, and the starting point and the overlapping position of the multi-color overlapping intersection region are analyzed and judged.
Specifically, current multi-color overlapping intersection area color difference detection comprises spectrophotometry measurement and gray-scale intensity-based measurement. The spectrophotometry is used for measuring the same position of the same batch of products and comparing the same with a sample, so that the difference between the initial position of the multicolor superposition intersection area of the product to be detected and the initial position of the sample product is judged, the color image is converted into the gray image based on gray intensity measurement, and the conversion of gray image intensity is analyzed, so that the initial position and the overlapping position of the multicolor superposition intersection area are analyzed.
However, for spectrophotometry measurement, the spectrophotometry measurement is difficult to use for real-time on-line detection because the spectrophotometry measurement belongs to contact measurement, and the contact measurement can pollute the product to be detected, and for measurement based on gray scale intensity, although the measurement is simpler to realize, the measurement accuracy is not high, and the direct conversion of a color image to a gray scale image can cause information loss and is influenced by the ink color depth, so that the measurement is not accurate enough.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention aims to provide a method, a storage medium and a device for determining a multi-color overlapping intersection region of a printed matter, which adopt a non-contact detection mode, obtain an accurate detection result without damaging the surface characteristics of a detected printed matter, have high detection accuracy and stronger robustness, and are not influenced by the depth of ink.
In order to achieve the above purpose, the method for determining the multi-color overlapping intersection area of the printed matter provided by the invention specifically comprises the following steps:
acquiring an RGB image to be detected containing a multicolor superposition intersection area, converting the RGB image to be detected into an HSI image, and calculating to obtain a saturation characteristic image;
calculating a mask image with saturation characteristics based on the saturation characteristic image to obtain a foreground image of the RGB image to be detected;
Performing projection processing on the foreground image, converting the RGB image after projection into a Lab image, namely obtaining a projection characteristic Lab image, and fitting the distance between an endpoint and a non-endpoint in the projection characteristic Lab image to obtain a projection characteristic curve;
and obtaining the initial position and the boundary point of the multi-color superposition intersection area in the RGB image to be detected based on the projection characteristic curve obtained by calculation.
On the basis of the technical scheme, the RGB image to be detected is obtained by shooting the printed matter to be detected based on the CCD color camera, and the RGB image to be detected obtained by shooting is the RGB image.
On the basis of the technical scheme, the RGB image to be detected is converted into the HSI image, and the saturation characteristic image is obtained through calculation, wherein the calculation mode of the saturation characteristic image is as follows:
S(i.j)=M(i.j)-N(i.j)
M(i.j)=max(R(i.j),G(i.j),B(i.j))
N(i.j)=min(R(i.j),G(i.j),B(i.j))
wherein S (i.j) represents the saturation feature at the image coordinate (i.j), R (i.j) represents the gray value of the image at the R channel coordinate (i.j), G (i.j) represents the gray value of the image at the G channel coordinate (i.j), B (i.j) represents the gray value of the image at the B channel coordinate (i.j), R, G, B is three color channels of the RGB image to be detected, the size of the RGB image to be detected is m×n, M represents rows, and N represents columns.
Based on the technical scheme, the mask image with the saturation characteristic is obtained by calculating the saturation characteristic image, specifically:
carrying out Canny operation on the saturation characteristic image to obtain a saturation characteristic binary image;
and filling the seed points of the binary image of the saturation characteristic to obtain a mask image of the saturation characteristic.
On the basis of the technical scheme, the method for acquiring the foreground image of the RGB image to be detected comprises the following specific steps:
Performing an AND operation on the RGB image to be detected and the mask image with the saturation characteristic, wherein the obtained image is a foreground image, and performing an exclusive OR operation on the RGB image to be detected and the mask image with the saturation characteristic, wherein the obtained image is a background image, and the calculation mode is as follows:
FT＝TRGB&Smask
BT＝TRGB∧Smask
Wherein F T represents a foreground image, B T represents a background image, T RGB represents an RGB image to be detected, S mask represents a mask image of a saturation feature, & represents an and operation, & represents an exclusive or operation.
On the basis of the technical scheme, the projection processing is performed on the foreground image, the RGB image after projection is converted into the Lab image, namely, the projection characteristic Lab image is obtained, and the specific steps comprise:
performing vertical projection processing on the foreground image, converting the RGB image after projection into a Lab image to obtain a projection characteristic Lab image, wherein the vertical projection processing is to project a two-dimensional image in a horizontal direction according to a column, then calculate the mean value of each color channel as a projection value of the current column, and then convert the RGB image obtained after projection into the Lab image to obtain the projection characteristic Lab image;
And carrying out statistical average filtering treatment on the projection characteristic Lab image.
On the basis of the technical scheme, the fitting projection characteristic Lab image comprises the specific steps of:
converting the projection feature Lab image from the RGB color space to the CIE-Lab color space;
Calculating to obtain two endpoints of the projection characteristic Lab image, and calculating the distance between the non-endpoints in the projection characteristic Lab image;
Fitting the calculated distance so as to draw a projection characteristic curve, wherein the distance calculation mode is as follows:
Dl(i)＝(a(i)-a(l))2+(b(i)-b(l))2
Dr(i)＝(a(i)-a(r))2+(b(i)-b(r))2
Wherein l represents the left end point of the projection feature Lab image, r represents the right end point of the projection feature Lab image, i represents the i-th pixel point of the projection feature Lab image, D l (i) represents the distance between the i-th pixel point of the projection feature Lab image and the left end point of the projection feature Lab image, D r (i) represents the distance between the i-th pixel point of the projection feature Lab image and the right end point of the projection feature Lab image, a (i) represents the a-color component value of the i-th pixel point of the projection feature Lab image, a (l) represents the a-color component value of the left end point of the projection feature Lab image, a (r) represents the a-color component value of the i-th pixel point of the projection feature Lab image, b (i) represents the b-color component value of the left end point of the projection feature Lab image, a represents the redness of the color, a represents the range from-128 to +127, a (r) represents the b-color component value of the i-th pixel point of the projection feature Lab image, b (l) represents the b-color component value of the projection feature Lab image, b (l) represents the red-color component value of the red-color of the color-128-127, and a +127 represents the range from-128 to +127.
Based on the above technical solution, the obtaining, based on the projection characteristic curve obtained by calculation, a starting position and a boundary point of a multi-color overlapping intersection region in an RGB image to be detected specifically includes:
Based on the projection characteristic curve, the intersection point in the projection characteristic curve is the intersection point of the multi-color overlapping intersection region, and the starting position of the multi-color overlapping intersection region is determined according to the 3 sigma principle.
The present invention provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of determining a multi-color overlay intersection region of a printed matter described above.
The invention provides a device for determining a multi-color superposition intersection area of a printed matter, which comprises the following components:
The acquisition module is used for acquiring an RGB image to be detected containing a multicolor superposition intersection area, converting the RGB image to be detected into an HSI image and calculating to obtain a saturation characteristic image;
The computing module is used for computing a mask image with saturation characteristics based on the saturation characteristic image so as to obtain a foreground image of the RGB image to be detected;
The processing module is used for carrying out projection processing on the foreground image, converting the RGB image after projection into a Lab image, namely obtaining a projection characteristic Lab image, and fitting the distance between the end point and the non-end point in the projection characteristic Lab image to obtain a projection characteristic curve;
And the execution module is used for obtaining the starting position and the boundary point of the multi-color superposition intersection area in the RGB image to be detected based on the projection characteristic curve obtained by calculation.
Compared with the prior art, the method has the advantages that the method comprises the steps of converting a color image from an RGB color space to an HSI color space, calculating a saturation characteristic image, performing projection analysis on the saturation image, calculating a mask image with saturation characteristics based on the saturation characteristic image, obtaining a foreground image of the RGB image to be detected, performing projection processing on the foreground image, converting the projected RGB image into a Lab image, namely obtaining a projection characteristic Lab image, fitting the distance between an endpoint and a non-endpoint in the projection characteristic Lab image to obtain a projection characteristic curve, finally obtaining information of a multi-color superposition intersection area in the RGB image to be detected based on the projection characteristic curve, obtaining an accurate detection result without damaging the surface characteristics of a printed body to be detected by adopting a non-contact detection mode, and being high in detection accuracy, strong in robustness and free from the influence of ink color.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for determining a multi-color overlapping intersection area of a printed matter according to an embodiment of the present invention;
fig. 2 is an example of a projection characteristic curve.
Detailed Description
The embodiment of the invention provides a method for determining a multi-color overlapping and intersecting area of a printed matter, which comprises the steps of converting a color image from an RGB color space to an HSI color space, calculating a saturation characteristic image, then carrying out projection analysis on the saturation image, then calculating a mask image with saturation characteristics based on the saturation characteristic image, obtaining a foreground image of an RGB image to be detected, carrying out projection processing on the foreground image, converting the projected RGB image into a Lab image, namely obtaining a projection characteristic Lab image, fitting the distance between an endpoint and a non-endpoint in the projection characteristic Lab image to obtain a projection characteristic curve, finally obtaining information of the multi-color overlapping and intersecting area in the RGB image to be detected based on the projection characteristic curve, and adopting a non-contact detection mode to obtain an accurate detection result without damaging the surface characteristics of the printed matter to be detected. The embodiment of the invention correspondingly provides a non-transitory computer readable storage medium and a device for determining the multi-color superposition intersection area of the printed matter.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application.
Referring to fig. 1, the method for determining a multi-color overlapping intersection area of a printed matter provided by the embodiment of the invention specifically includes the following steps:
S1, acquiring an RGB image to be detected containing a multi-color superposition intersection area, converting the RGB image to be detected into an HSI image, and calculating to obtain a saturation characteristic image;
in the invention, the RGB image to be detected is obtained by shooting a printed matter to be detected based on a CCD (Charge Coupled Device ) color camera, and the RGB image to be detected obtained by shooting is an RGB image. The CCD color camera collects RGB data of the printed matter image, and the RGB color space belongs to the color space related to the equipment. In order to accurately describe colors, a color gamut space transformation of the CCD color camera is required, i.e. a device dependent color space of the CCD color camera is converted into a device independent color space.
For the RGB color space, RGB (red, green, blue) is a space defined according to colors recognized by human eyes, and can represent most colors. The RGB color space represents colors with a linear combination of three color components, to which any color is related, and which are highly correlated.
In the invention, an RGB image to be detected is converted into an HSI image, and a saturation characteristic image is obtained by calculation, wherein the calculation mode of the saturation characteristic image is as follows:
S(i.j)=M(i.j)-N(i.j)
M(i.j)=max(R(i.j),G(i.j),B(i.j))
N(i.j)=min(R(i.j),G(i.j),B(i.j))
wherein S (i.j) represents the saturation feature at the image coordinate (i.j), R (i.j) represents the gray value of the image at the R channel coordinate (i.j), G (i.j) represents the gray value of the image at the G channel coordinate (i.j), B (i.j) represents the gray value of the image at the B channel coordinate (i.j), R, G, B is three color channels of the RGB image to be detected, the size of the RGB image to be detected is m×n, M represents rows, and N represents columns.
For HSI, the HSI color space is proposed for better digitizing the colors. H represents hue, S represents saturation, and I represents intensity.
S2, calculating a mask image with saturation characteristics based on the saturation characteristic image to obtain a foreground image of the RGB image to be detected;
in the invention, a mask image with saturation characteristics is obtained based on saturation characteristic image calculation, specifically:
s201, carrying out Canny (an edge detection algorithm) operation on a saturation characteristic image to obtain a saturation characteristic binary image;
The Canny operation comprises the steps of Gaussian blur, gradient size and direction calculation, non-maximized suppression, double-threshold acquisition and weak edge connection. For non-maximized suppression, there should be only one response per edge, and for dual threshold acquisition, there is a separation of strong and weak edges.
S202, filling the seed points of the binary image of the saturation feature to obtain a mask image of the saturation feature.
The seed filling algorithm is generally implemented by using a stack data structure, namely, firstly stacking seed pixels, wherein the seed pixels are stack bottom pixels, if the stack is not empty, performing three steps of firstly popping the stack top pixels, secondly drawing the popped pixels according to filling colors, thirdly searching four (eight) pixels adjacent to the popped pixels according to left, right, lower, upper left, upper right, lower right and lower left in sequence, and if the color of the pixel is not boundary color and is not set into filling color, stacking the pixel, otherwise discarding the pixel.
The invention discloses a method for acquiring a foreground image of an RGB image to be detected, which comprises the specific steps of performing AND operation on the RGB image to be detected and a mask image with saturation characteristics, wherein the acquired image is the foreground image, performing exclusive OR operation on the RGB image to be detected and the mask image with saturation characteristics, and the acquired image is a background image, wherein the calculation mode is as follows:
FT＝TRGB&Smask
BT＝TRGB∧Smask
Wherein F T represents a foreground image, B T represents a background image, T RGB represents an RGB image to be detected, S mask represents a mask image of a saturation feature, & represents an and operation, & represents an exclusive or operation.
The method comprises the steps of performing AND operation on the RGB image to be detected and the mask image with the saturation characteristic to obtain a foreground image, wherein the coordinates of the RGB image to be detected are assumed to be (100 ), the pixel value is 192, the coordinates of the mask image with the saturation characteristic are assumed to be (100 ), the pixel value is 1, the coordinates of the image obtained by performing AND operation on the RGB image to be detected and the mask image with the saturation characteristic are assumed to be (100 ), the pixel value is 192, the coordinates of the RGB image to be detected are assumed to be (101 ), the pixel value is 85, the coordinates of the mask image with the saturation characteristic are assumed to be (101 ), the pixel value is 0, the coordinates of the image obtained by performing AND operation on the RGB image and the mask image with the saturation characteristic are assumed to be (101 ), and the pixel value is 0.
S3, performing projection processing on the foreground image, converting the RGB image after projection into a Lab image, namely obtaining a projection characteristic Lab image, and fitting the distance between an endpoint and a non-endpoint in the projection characteristic Lab image to obtain a projection characteristic curve;
in the invention, the foreground image is projected, the projected RGB image is converted into Lab image, namely, the projected characteristic Lab image is obtained, the specific steps include:
S301, performing vertical projection processing on a foreground image, converting a RGB image after projection into a Lab image to obtain a projection characteristic Lab image, wherein the vertical projection processing is to project a two-dimensional image in a horizontal direction according to a column, then calculate the mean value of each color channel as a projection value of a current column, and then convert the RGB image obtained after projection into the Lab image to obtain the projection characteristic Lab image;
S302, carrying out statistical mean filtering processing on the projection characteristic Lab image.
For step S301, the following is specifically described:
(1) Performing vertical projection processing on the foreground image, wherein for the vertical projection effect, the image is assumed to be M rows and N columns, and after the vertical projection is performed, the image is changed into 1 row and N columns;
(2) Calculating the average value of each color channel, wherein for the vertical projection calculation rule, specifically, the average value is calculated after accumulating the pixel values in the Y-axis (vertical) direction, for example, the color image has three pixels in the Y-axis direction, the pixel values of R channels are respectively 111, 120 and 129, the pixel value of R channels after projection is 120= (111+120+129)/3;G channels are respectively 135, 145 and 155, the pixel value of G channels after projection is 145= (135+145+155)/3;B channels are respectively 211, 220 and 199, and the pixel value of R channels after projection is 210= (211+220+199)/3;
(3) For calculating the mean value of each color channel, as the projection value of the current column, the foreground image is a color image, and the foreground image is still the color image after the processing is finished;
(4) The color image generally refers to an image formed by a plurality of color channels, and the number of the color channels is more than 1;
(5) For calculating the mean value of each color channel as the projection value of the current column, and then obtaining a projection characteristic Lab image through color space conversion, wherein the images processed in the invention are all digital images, and the digital images are images expressed in a two-dimensional digital group mode.
The projection characteristic Lab image is discontinuous in color, so that the color can jump in a large range to affect the segmentation effect, and therefore, the projection characteristic Lab image is required to be subjected to statistical mean filtering processing, and a smoother image is obtained. The statistical mean value filtering is equivalent to median value filtering and mean value filtering, and the specific implementation steps are that 8 pixels (or 24 pixels or 48 pixels) around the pixel point are used for removing the maximum value pixel point and the minimum value pixel point, the rest pixel points are subjected to average operation, and the average pixel value is used for replacing the pixel value of the point.
In the invention, a projection characteristic curve is obtained by fitting the distance between an endpoint and a non-endpoint in a projection characteristic Lab image, and the specific steps comprise:
S311, converting the projection characteristic Lab image from an RGB color space to a CIE-Lab color space;
For the CIE-Lab space, the CIE-Lab color model is a color model formulated by the CIE (International Commission on illumination).
S312, calculating two endpoints of the projection characteristic Lab image, and calculating the distance between the non-endpoints in the projection characteristic Lab image;
S313, fitting the calculated distance so as to draw a projection characteristic curve, wherein the distance calculation mode is as follows:
Dl(i)＝(a(i)-a(l))2+(b(i)-b(l))2
Dr(i)＝(a(i)-a(r))2+(b(i)-b(r))2
Wherein l represents the left end point of the projection feature Lab image, r represents the right end point of the projection feature Lab image, i represents the i-th pixel point of the projection feature Lab image, D l (i) represents the distance between the i-th pixel point of the projection feature Lab image and the left end point of the projection feature Lab image, D r (i) represents the distance between the i-th pixel point of the projection feature Lab image and the right end point of the projection feature Lab image, a (i) represents the a-color component value of the i-th pixel point of the projection feature Lab image, a (l) represents the a-color component value of the left end point of the projection feature Lab image, a (r) represents the a-color component value of the i-th pixel point of the projection feature Lab image, b (i) represents the b-color component value of the left end point of the projection feature Lab image, a represents the redness of the color, a represents the range from-128 to +127, a (r) represents the b-color component value of the i-th pixel point of the projection feature Lab image, b (l) represents the b-color component value of the projection feature Lab image, b (l) represents the red-color component value of the red-color of the color-128-127, and a +127 represents the range from-128 to +127.
After the projection characteristic Lab image is converted from RGB space to CIE-Lab space, each pixel point has a group of Lab values, when the projection characteristic Lab image is subjected to endpoint calculation, the left endpoint of the projection characteristic Lab image is firstly assumed to be the starting point, the right endpoint is the ending point, the distance between the endpoint and the non-endpoint is calculated, then the left endpoint of the projection characteristic Lab image is assumed to be the ending point, the right endpoint is the starting point, and the distance between the endpoint and the non-endpoint is calculated.
In the invention, the distance between the non-end point and the punctuation of the projection characteristic Lab image is calculated, and specifically, the distance between the non-end point and the end point in the projection characteristic Lab image is calculated.
In the invention, the least square method can be adopted to fit the calculated distance data, so that a corresponding curve, namely a projection characteristic curve, can be drawn.
And S4, obtaining the initial position and the boundary point of the multi-color superposition intersection area in the RGB image to be detected based on the projection characteristic curve obtained through calculation.
In the invention, based on the projection characteristic curve obtained by calculation, the initial position and the boundary point of the multi-color superposition intersection area in the RGB image to be detected are obtained, specifically:
Based on the projection characteristic curve, the intersection point in the projection characteristic curve is the intersection point of the multi-color overlapping intersection region, and the starting position of the multi-color overlapping intersection region is determined according to the 3 sigma principle.
The method specifically comprises the steps of 1, calculating the space distance between a starting point and other points by taking the left end point of a projection characteristic Lab image as a starting point, fitting the calculated space distance to obtain a curve, calculating the space distance between the starting point and other points by taking the right end point of the projection characteristic Lab image as the starting point, fitting the calculated space distance to obtain a curve, 2, wherein the interaction point of the two curves is the most important point of interaction of two colors, namely a boundary point, 3, when one color is mixed with the other color, the color component value of the color component is changed greatly (the method is reflected on the space distance), when the aliasing is finished, the color component value of the color component is changed into a stable value, the change is similar to normal distribution, the color component value of an aliasing area is changed suddenly, and the color value of a non-aliasing area is changed little.
In the projection characteristic curve example shown in fig. 2, the point a is the boundary point of the multi-color overlapping intersection region, and B, C is the multi-color overlapping intersection starting points of the two colors, respectively.
The multi-color overlapping intersection region refers to a region with only 2 kinds of color aliasing, so that 2 curves exist in the projection characteristic curve shown in fig. 2. In fig. 2, 2 curves each represent transition from one color to another, the intersection is the most severe point of color transition, and B, C points each represent a start intersection. The abscissa in fig. 2 represents the number of columns of the image, and the ordinate represents the spatial distance.
The invention converts RGB colors into HSI, separates foreground and background images by calculating saturation, projects the foreground images, converts the foreground images into LAB space, determines interaction points of multi-color overlapping intersection areas by calculating space distance, and determines starting points and end points of the multi-color overlapping intersection areas by 3 sigma principle. The method comprises the steps of adopting an AOI (Automated Optical Inspection, automatic optical detection) non-contact detection method, obtaining an accurate detection result while not damaging the surface characteristics of an object to be detected, converting RGB colors into HSI, distinguishing a foreground and a background by calculating saturation, and then converting a foreground image into LAB space to calculate the space distance between the two colors, so that the detection accuracy is high, the robustness is stronger, and the influence of ink color depth is avoided.
According to the method for determining the multi-color overlapping and intersecting region of the printed matter, the color image is transferred from the RGB color space to the HSI color space, the saturation characteristic image is calculated, then the saturation image is subjected to projection analysis, then the saturation characteristic mask image is obtained based on the saturation characteristic image, the foreground image of the RGB image to be detected is obtained, projection processing is carried out on the foreground image, the RGB image obtained after projection is converted into the Lab image, namely the projection characteristic Lab image is obtained, the distance between the end point and the non-end point in the projection characteristic Lab image is fitted to obtain the projection characteristic curve, finally the information of the multi-color overlapping and intersecting region in the RGB image to be detected can be obtained based on the projection characteristic curve, the accurate detection result is obtained without damaging the surface characteristics of the printed matter to be detected in a non-contact detection mode, the detection accuracy is high, the robustness is high, and the influence of ink color depth is avoided.
In a possible implementation manner, the embodiment of the invention further provides a non-transitory computer readable storage medium, wherein the readable storage medium is located in a PLC (Programmable Logic Controller ) controller, and a computer program is stored on the readable storage medium, and when the program is executed by a processor, the steps of the method for determining a multi-color superposition intersection area of a printed matter are implemented:
acquiring an RGB image to be detected containing a multicolor superposition intersection area, converting the RGB image to be detected into an HSI image, and calculating to obtain a saturation characteristic image;
calculating a mask image with saturation characteristics based on the saturation characteristic image to obtain a foreground image of the RGB image to be detected;
Performing projection processing on the foreground image, converting the RGB image obtained after projection into a Lab image, namely obtaining a projection characteristic Lab image, and fitting the distance between an endpoint and a non-endpoint in the projection characteristic Lab image to obtain a projection characteristic curve;
and obtaining the initial position and the boundary point of the multi-color superposition intersection area in the RGB image to be detected based on the projection characteristic curve obtained by calculation.
The storage media may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The device for determining the multi-color overlapping intersection area of the printed matter provided by the embodiment of the invention comprises an acquisition module, a calculation module, a processing module and an execution module.
The system comprises an acquisition module, a calculation module, a processing module and an execution module, wherein the acquisition module is used for acquiring an RGB image to be detected containing a multicolor superposition intersection area, converting the RGB image to be detected into an HSI image and calculating to obtain a saturation characteristic image, the calculation module is used for calculating to obtain a mask image with saturation characteristics based on the saturation characteristic image so as to acquire a foreground image of the RGB image to be detected, the processing module is used for carrying out projection processing on the foreground image, converting the RGB image obtained after projection into a Lab image, namely acquiring a projection characteristic Lab image, fitting the distance between an endpoint and a non-endpoint in the projection characteristic Lab image to obtain a projection characteristic curve, and the execution module is used for obtaining the initial position and a boundary point of the multicolor superposition intersection area in the RGB image to be detected based on the calculated projection characteristic curve.
In the invention, RGB images to be detected are obtained by shooting printed matters to be detected based on a CCD color camera, and the shot RGB images to be detected are RGB images.
In the invention, an RGB image to be detected is converted into an HSI image, and a saturation characteristic image is obtained by calculation, wherein the calculation mode of the saturation characteristic image is as follows:
S(i.j)=M(i.j)-N(i.j)
M(i.j)=max(R(i.j),G(i.j),B(i.j))
N(i.j)=min(R(i.j),G(i.j),B(i.j))
wherein S (i.j) represents the saturation feature at the image coordinate (i.j), R (i.j) represents the gray value of the image at the R channel coordinate (i.j), G (i.j) represents the gray value of the image at the G channel coordinate (i.j), B (i.j) represents the gray value of the image at the B channel coordinate (i.j), R, G, B is three color channels of the RGB image to be detected, the size of the RGB image to be detected is m×n, M represents rows, and N represents columns.
In the invention, a mask image with saturation characteristics is obtained based on saturation characteristic image calculation, specifically:
carrying out Canny operation on the saturation characteristic image to obtain a saturation characteristic binary image;
and filling the seed points of the binary image of the saturation characteristic to obtain a mask image of the saturation characteristic.
In the invention, the foreground image of the RGB image to be detected is obtained, and the specific steps include:
Performing an AND operation on the RGB image to be detected and the mask image with the saturation characteristic, wherein the obtained image is a foreground image, and performing an exclusive OR operation on the RGB image to be detected and the mask image with the saturation characteristic, wherein the obtained image is a background image, and the calculation mode is as follows:
FT＝TRGB&Smask
BT＝TRGB∧Smask
Wherein F T represents a foreground image, B T represents a background image, T RGB represents an RGB image to be detected, S mask represents a mask image of a saturation feature, & represents an and operation, & represents an exclusive or operation.
In the invention, the foreground image is projected, the RGB image obtained after projection is converted into Lab image, namely, the projection characteristic Lab image is obtained, the specific steps include:
Performing vertical projection processing on the foreground image, converting the RGB image obtained after projection into a Lab image to obtain a projection characteristic Lab image, wherein the vertical projection processing is to project a two-dimensional image in a horizontal direction according to a column, then calculate the mean value of each color channel as a projection value of the current column, and then convert the RGB image obtained after projection into the Lab image to obtain the projection characteristic Lab image;
And carrying out statistical average filtering treatment on the projection characteristic Lab image.
In the invention, a projection characteristic curve is obtained by fitting the distance between an endpoint and a non-endpoint in a projection characteristic Lab image, and the specific steps comprise:
converting the projection feature Lab image from the RGB color space to the CIE-Lab color space;
Calculating to obtain two endpoints of the projection characteristic Lab image, and calculating the distance between the non-endpoints in the projection characteristic Lab image;
Fitting the calculated distance so as to draw a projection characteristic curve, wherein the distance calculation mode is as follows:
Dl(i)＝(a(i)-a(l))2+(b(i)-b(l))2
Dr(i)＝(a(i)-a(r))2+(b(i)-b(r))2
Wherein l represents the left end point of the projection feature Lab image, r represents the right end point of the projection feature Lab image, i represents the i-th pixel point of the projection feature Lab image, D l (i) represents the distance between the i-th pixel point of the projection feature Lab image and the left end point of the projection feature Lab image, D r (i) represents the distance between the i-th pixel point of the projection feature Lab image and the right end point of the projection feature Lab image, a (i) represents the a-color component value of the i-th pixel point of the projection feature Lab image, a (l) represents the a-color component value of the left end point of the projection feature Lab image, a (r) represents the a-color component value of the i-th pixel point of the projection feature Lab image, b (i) represents the b-color component value of the left end point of the projection feature Lab image, a represents the redness of the color, a represents the range from-128 to +127, a (r) represents the b-color component value of the i-th pixel point of the projection feature Lab image, b (l) represents the b-color component value of the projection feature Lab image, b (l) represents the red-color component value of the red-color of the color-128-127, and a +127 represents the range from-128 to +127.
In the invention, based on the projection characteristic curve obtained by calculation, the initial position and the boundary point of the multi-color superposition intersection area in the RGB image to be detected are obtained, specifically:
Based on the projection characteristic curve, the intersection point in the projection characteristic curve is the intersection point of the multi-color overlapping intersection region, and the starting position of the multi-color overlapping intersection region is determined according to the 3 sigma principle.
The foregoing is only a specific embodiment of the application to enable those skilled in the art to understand or practice the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311139786.0A CN117115126B (en) | 2023-09-05 | 2023-09-05 | Method for determining multi-color overlapping intersection area of printed matter, storage medium and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311139786.0A CN117115126B (en) | 2023-09-05 | 2023-09-05 | Method for determining multi-color overlapping intersection area of printed matter, storage medium and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117115126A CN117115126A (en) | 2023-11-24 |
| CN117115126B true CN117115126B (en) | 2025-03-11 |
Family
ID=88805404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311139786.0A Active CN117115126B (en) | 2023-09-05 | 2023-09-05 | Method for determining multi-color overlapping intersection area of printed matter, storage medium and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117115126B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017092431A1 (en) * | 2015-12-01 | 2017-06-08 | 乐视控股（北京）有限公司 | Human hand detection method and device based on skin colour |
| CN114943719A (en) * | 2022-06-02 | 2022-08-26 | 卡奥斯工业智能研究院(青岛)有限公司 | Printing quality detection method and device, electronic equipment and storage medium |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009152868A (en) * | 2007-12-20 | 2009-07-09 | Sapporo Medical Univ | Image processing apparatus and image processing program |
| US8351707B2 (en) * | 2007-07-31 | 2013-01-08 | Sharp Kabushiki Kaisha | Image processing apparatus, image forming apparatus, image processing system, and image processing method |
| JP5699661B2 (en) * | 2011-02-14 | 2015-04-15 | 株式会社リコー | Image processing apparatus, image processing method, and image processing program |
| CN103971367B (en) * | 2014-04-28 | 2017-01-11 | 河海大学 | Hydrologic data image segmenting method |
| CN106952313A (en) * | 2017-03-21 | 2017-07-14 | 北京工商大学 | Skin color evaluation method based on HSI and Lab mixed color model |
| JP2019204428A (en) * | 2018-05-25 | 2019-11-28 | キヤノン株式会社 | Image processing device, display system, image processing method, and program |
| CN110728302A (en) * | 2019-09-10 | 2020-01-24 | 武汉纺织大学 | A method for texture identification of dyed fabrics based on HSV and Lab color space |
| CN111784703B (en) * | 2020-06-17 | 2023-07-14 | 泰康保险集团股份有限公司 | Image segmentation method and device, electronic equipment and storage medium |
| CN115358990A (en) * | 2022-08-18 | 2022-11-18 | 郑州轻工业大学 | A Fast Corner Detection Method Based on Center Distance Ratio of Symmetrical Contour |
-
2023
- 2023-09-05 CN CN202311139786.0A patent/CN117115126B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017092431A1 (en) * | 2015-12-01 | 2017-06-08 | 乐视控股（北京）有限公司 | Human hand detection method and device based on skin colour |
| CN114943719A (en) * | 2022-06-02 | 2022-08-26 | 卡奥斯工业智能研究院(青岛)有限公司 | Printing quality detection method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117115126A (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3477931B1 (en) | Image processing method and device, readable storage medium and electronic device | |
| CN108364010B (en) | License plate recognition method, device, equipment and computer readable storage medium | |
| CN105893925A (en) | Human hand detection method based on complexion and device | |
| US20100104175A1 (en) | Integrated image processor | |
| CN109520706B (en) | Screw hole coordinate extraction method of automobile fuse box | |
| JP7036477B1 (en) | Defect detection method, defect detection system, and defect detection program | |
| CN107767379A (en) | Pcb board marks print quality inspection method | |
| CN110866932A (en) | Multi-channel tongue edge detection device and method and storage medium | |
| CN107018407B (en) | Information processing device, evaluation chart, evaluation system, and performance evaluation method | |
| CN102074017A (en) | Method and device for detecting and tracking barbell central point | |
| CN113436220A (en) | Image background estimation method based on depth map segmentation | |
| CN110648336B (en) | Method and device for dividing tongue texture and tongue coating | |
| CN104156703A (en) | License plate location method and system based on color texture | |
| CN112699760A (en) | Face target area detection method, device and equipment | |
| CN117115126B (en) | Method for determining multi-color overlapping intersection area of printed matter, storage medium and device | |
| CN108205641B (en) | Gesture image processing method and device | |
| CN102855025B (en) | Optical multi-touch contact detection method based on visual attention model | |
| CN117115095A (en) | A method and system for detecting small defects in complex textured ceramic tiles | |
| Wang et al. | An efficient method of shadow elimination based on image region information in HSV color space | |
| CN111325209A (en) | License plate recognition method and system | |
| CN116485992A (en) | Composite three-dimensional scanning method and device and three-dimensional scanner | |
| KR101521269B1 (en) | Method for detecting snow or rain on video | |
| JP6180889B2 (en) | Printing inspection device | |
| JPH07146937A (en) | Pattern matching method | |
| CN114066837A (en) | A method and system for identifying dynamic water level in ship cabin |
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 |