CN120580237A - A method and system for detecting map print quality - Google Patents
A method and system for detecting map print qualityInfo
- Publication number
- CN120580237A CN120580237A CN202511086107.7A CN202511086107A CN120580237A CN 120580237 A CN120580237 A CN 120580237A CN 202511086107 A CN202511086107 A CN 202511086107A CN 120580237 A CN120580237 A CN 120580237A
- Authority
- CN
- China
- Prior art keywords
- map
- target
- region
- area
- gray
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Immunology (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Pathology (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
本发明属于图像处理技术领域，具体涉及一种地图印刷品质量检测方法及系统，其方法包括：对所有灰度图进行分区；根据目标灰度图中各区域与标准灰度图中对应区域的差分表现，获取目标灰度图中各区域的第一完整度；根据目标灰度图中各区域与邻域区域的关联地图结构的呈现，获取目标灰度图中各区域的第二完整度；得到目标灰度图中各区域的总体完整度；将目标灰度图的中心缺陷区域以及对应的辐射缺陷区域，记为一个缺陷区域；计算缺陷区域的缺陷指数，并用于评估地图印刷品的质量。本发明提高了地图印刷品质量检测的精确性以及速度。
The present invention belongs to the field of image processing technology, and specifically relates to a method and system for detecting the quality of map prints. The method comprises: partitioning all grayscale images; obtaining a first completeness of each region in the target grayscale image based on the differential representation of each region in the target grayscale image and the corresponding region in the standard grayscale image; obtaining a second completeness of each region in the target grayscale image based on the presentation of the associated map structure between each region in the target grayscale image and neighboring regions; obtaining the overall completeness of each region in the target grayscale image; recording the central defect region and the corresponding radial defect region in the target grayscale image as a defect region; and calculating a defect index for the defect region and using it to evaluate the quality of map prints. The present invention improves the accuracy and speed of map print quality detection.
Description
Technical Field
The invention relates to the technical field of image processing. More particularly, the invention relates to a map printing quality detection method and system.
Background
In the map printing production process, defects such as missing printing and spots of map printed matters may occur due to factors such as printing process, mechanical precision, detection environment and the like, so that the printed map products need to be detected. At present, a machine vision technology is commonly adopted, quality detection is carried out on a printed matter by a reference method, the process comprises the steps of selecting a standard printed matter template, collecting a printed matter image, preprocessing the printed matter image, carrying out image difference with the standard printed matter template, and determining the quality of the printed matter according to a difference result.
In the related art, for example, chinese patent document CN109840499B discloses a method for rapidly detecting print and binding quality of a printed matter, which discloses a feature matching algorithm based on dynamic time warping to measure similarity between an image to be detected and a reference image, and determine quality of the printed matter to be detected. The Chinese patent document with the authorized bulletin number of CN119130972B discloses a printed matter quality online detection method and a system, which detect defects of printed matters by setting different scanning frame sizes and multi-level scanning methods, and compare a subarea of an image to be detected with a subarea of a standard image so as to enable type division to be more detailed and accurate.
However, in the quality detection process of the printed matter, because the map product has higher information content than the general printed matter, taking a natural geographic diagram as an example, different administrative areas are distinguished by lines and color blocks, and natural geographic features such as mountains, rivers and the like and place names exist in each administrative area, the map printed matter needs higher detection precision, and defects can cause associated interference and the actual influence of amplification defects, so that the current quality detection effect on the map printed matter is poor.
Disclosure of Invention
In order to solve the above-described problem of poor detection effect when a map print is detected by using a reference method, the present invention provides the following aspects.
In a first aspect, the present invention provides a map print quality detection method, including:
The method comprises the steps of obtaining images of a plurality of maps to be tested of a map, preprocessing all the images of the map to be tested through manual screening of standard images, registering the images in the same coordinate system to obtain a plurality of grey maps to be tested and standard grey maps, recording any grey map to be tested as a target grey map, partitioning all the grey maps based on an edge detection algorithm and grey distribution to obtain a plurality of areas of any grey map, obtaining first integrity of each area in the target grey map according to differential expression of each area in the target grey map and a corresponding area in the standard grey map, obtaining second integrity of each area in the target grey map according to an associated map structure of each area in the target grey map and a neighborhood area, combining the first integrity with the second integrity to obtain overall integrity of each area in the target grey map, obtaining a central defect area and a corresponding radiation defect area of the target grey map according to change rules of the overall integrity of the areas in the target grey map, calculating the overall integrity of the areas and evaluating the map to be used for printing quality of the map.
According to the invention, the map printed matter is divided according to the regional shape according to the map characteristics, so that the defect area can be rapidly positioned during quality detection, and the efficiency of detecting the quality of the map printed matter is improved. According to the method and the device, the overall integrity of the region is obtained according to the shape of the region and the associated map structure, and the quality judgment is carried out on the subareas of the map from a more accurate angle, so that the quality detection of the map printed matter is more accurate and more effective.
Preferably, the acquiring several areas of any gray scale map includes:
Performing edge detection on all the gray images to obtain corresponding edge images of the gray images;
the ith edge pixel point of the edge image of the target gray scale image is marked as Acquisition ofPresetting a first threshold value in a left neighborhood A pixel point and a right neighborhood A pixel point in the normal direction of an edge, and recording the difference value between the gray average value of the left neighborhood A pixel point and the gray average value of the right neighborhood A pixel point asIf (if)Greater than the first threshold value, thenMarking as boundary pixel point ifLess than or equal to the first threshold value, thenMarking as characteristic pixel points;
any gray level map is divided into a plurality of closed subareas by boundary pixel points, and the any closed subareas are marked as one area to obtain a plurality of areas of the gray level map.
The invention effectively divides the areas according to the regional color block difference and the edge pixel points of the map, so that the integrity of the map region is ensured on the basis of reducing the quality detection range and improving the quality detection effect.
Preferably, the obtaining the first integrity of each region in the target gray scale image includes:
Marking any area of the target gray scale map as a target area, and making a difference between a gray scale matrix of the target area and a gray scale matrix of a corresponding area in the standard gray scale map to obtain a differential gray scale matrix of the target area;
the first integrity of the target region satisfies the expression:
;
In the formula, Representing a first integrity of the target region; The DTW distance between the chain code of the target area and the chain code of the corresponding area of the target area in the standard gray scale map is represented; an average value of the differential gray matrix representing the target area; The number of values greater than 0 in the differential gray matrix representing the target area.
The invention compares the target area with the corresponding area in the standard gray scale image based on the differential technology, and the differential technology shows that the larger the differential result value is, the larger the difference between the target area and the corresponding area is, so that the lower the first integrity of the target area is embodied.
Preferably, the obtaining the chain code of the target area includes:
and acquiring the eight-direction chain code of the boundary pixel point of the target area in the clockwise direction by taking the pixel point of the target area closest to the origin point of the coordinate system as a starting point.
Preferably, the obtaining the second integrity of each region in the target gray scale image includes:
Acquiring natural features of any gray level diagram, taking a pixel point with the nearest distance between the natural features and the origin of a coordinate system as a starting point, acquiring eight-direction chain codes of the natural features in a clockwise direction, and marking a v-th region of a u-th natural feature of a standard gray level diagram as a v-th region of the standard gray level diagram Acquiring the sum of the target gray level diagramCorresponding regions, noted as target gray-scale mapIs a control region of (2);
Calculating target gray scale map The second integrity of the target gray map with respect to the comparison area of the belonging area is marked as the second integrity of the target area if the comparison area of the target area is not the comparison area, and the second integrity of the target area is marked as 1 if the target area is not the comparison area.
According to the invention, natural features are used as key areas, and the second integrity of each area is calculated, so that the quality detection precision of the map printed matter is ensured and the accuracy of the quality detection of the map printed matter is improved from the aspect of being beneficial to practical use.
Preferably, the acquiring the natural characteristic of the arbitrary gray scale map includes:
And obtaining boundary pixel points adjacent to the characteristic pixel points, marking the boundary pixel points as equivalent characteristic pixel points, marking the arbitrary characteristic pixel points as growth seeds, carrying out regional growth, wherein the growth condition is that the adjacent pixel points have the characteristic pixel points or the equivalent characteristic pixel points, the growth stop condition is that the adjacent pixel points have no adjacent pixel points and have no equivalent characteristic pixel points, and after the growth is stopped, if the non-grown characteristic pixel points exist, selecting the growth seeds from the non-grown characteristic pixel points until all the characteristic pixel points have the growth regions, marking the arbitrary growth regions as a natural characteristic, and obtaining a plurality of natural characteristics of the gray map.
Preferably, the target gray scale map relates toThe second degree of integrity of the control region of (2) satisfies the expression:
;
In the formula, Representing target gray-scale image with respect toIs a second integrity of the control zone of (a); Representing target gray-scale image with respect to The number of pixels belonging to the natural feature in the comparison area; Representation of The number of pixels belonging to the natural feature; Representing target gray-scale image with respect to Is a natural feature quantity of the control region; Representing target gray-scale image with respect to Chain code of the r-th natural feature of the comparison region, andDTW distance of the chain code of the natural features.
Preferably, the obtaining the overall integrity of each region in the target gray scale image includes:
And adding the first integrity of the target area and the second integrity of the target area, and carrying out positive correlation normalization to obtain the overall integrity of the target area.
Preferably, the defect index of the arbitrary defect region satisfies the expression:
;
In the formula, A defect index indicating an h-th defect region; representing the number of areas of the h-th defective area; The number of pixels in the s-th region representing the h-th defective region; indicating the overall integrity of the s-th region of the h-th defective region.
The invention obtains the defect index of the defect area more comprehensively based on the area of the defect area and the total integrity of each area, so that the map quality can be judged from multiple dimensions, and the accuracy of the quality detection of the map printed matter is further improved.
In a second aspect, the present invention provides a map print quality detection system comprising a processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement a map print quality detection method as described above.
By adopting the technical scheme, the map printing quality detection method generates a computer program, stores the computer program in the memory and is loaded and executed by the processor, so that terminal equipment is manufactured according to the memory and the processor, and the map printing quality detection method is convenient to use.
The invention has the beneficial effects that:
(1) Based on the image characteristics of the map, the quality of the map is analyzed from the shape and natural geographic characteristics of the map printed matter, so that the quality detection accuracy of the map printed matter is improved;
(2) The invention also divides the map gray level map according to the regional distribution, so that the defect region can be rapidly positioned when the defect is found, the defect region is referred to, and the quality detection efficiency of the map printed matter is improved;
(3) The invention combines the areas of the defects, considers the associated interference and further improves the quality detection accuracy of the map printed matter.
Drawings
Fig. 1 is a flowchart schematically showing a map print quality detection method in the present invention;
fig. 2 is a schematic diagram schematically showing boundary pixel points and feature pixel points.
Detailed Description
The embodiment of the invention discloses a map printed matter quality detection method, which comprises the following steps of S1-S4 with reference to FIG. 1:
s1, acquiring images of a plurality of maps to be detected of a map, preprocessing the images of all the maps to be detected through manual screening of standard images, registering to obtain a plurality of gray level images to be detected and standard gray level images, which are commonly called gray level images, and recording any gray level image to be detected as a target gray level image.
It should be noted that, the map printing environment is complex, and the difference between the map printing environment and the map template in the computer environment is large, so in order to obtain the quality of the map printed matter more accurately, the invention screens the images of all the maps to be detected manually, thereby obtaining the map detection result more in line with the real environment.
Specifically, an industrial camera is used for collecting images of all printed matters after map printing, the images are respectively recorded as images of a map to be detected, and standard images are screened manually. The standard image can present the details in the map to the maximum extent, and there is no region such as a defect or shadow that affects the viewing of the map.
The method comprises the steps of preprocessing images of all the maps to be detected, including graying and geometric correction, wherein the graying can keep colors to the greatest extent through a weighted average method, for example, the weights of RGB three spaces can be set to be 0.3, 0.6 and 0.1, the geometric correction method can adopt SIFT algorithm-based feature matching of the images of the maps to be detected and standard images, all matching points are placed in the same coordinate system, image registration of the maps to be detected is completed, and a plurality of gray maps to be detected and standard gray maps are obtained and are commonly called as gray maps. The origin of the coordinate system is the first pixel point of the lower left corner of the standard image, and the positive direction of the horizontal axis and the positive direction of the vertical axis of the coordinate system are the right side and the upper side of the first pixel point of the sitting corner of the standard image respectively.
Thus, a gray scale image set consisting of a plurality of gray scale images to be measured and a standard gray scale image is obtained.
S2, partitioning all gray level images based on an edge detection algorithm and gray level distribution to obtain a plurality of areas of any gray level image, and obtaining first integrity of each area in the target gray level image according to differential expression of each area in the target gray level image and a corresponding area in the standard gray level image.
It should be noted that, the map printed matter has a greater influence on the defect of the text printed matter, for example, when ink marks appear at the boundary of the area, all adjacent areas are affected to view, so that the map printed matter is divided according to the areas in consideration of the uniqueness of the map printed matter, thereby establishing a map printed matter quality detection model from a more accurate dimension, rapidly positioning the defect and determining the influence caused.
It should be further noted that, comparing the region of the target gray scale map with the corresponding region in the standard gray scale map can obtain the relative difference of the region of the target gray scale map, the map print is used for accurately showing the region shape and the natural geographic features, so that the difference of the non-feature pixels does not affect the quality of the map print, and therefore, the invention firstly determines the feature expression of the pixels with larger relative difference between the region of the target gray scale map and the corresponding region in the standard gray scale map, and further calculates the first integrity of each region in the target gray scale map.
Specifically, based on an edge detection algorithm and gray distribution, all gray maps are partitioned, and a plurality of areas of any gray map are obtained, including:
And carrying out edge detection on all the gray level images to obtain corresponding edge images of the gray level images.
It should be noted that, in the corresponding edge image of the gray scale image, the edges are divided into boundary type edges and feature type edges, the boundary type edges are used for distinguishing different regions, the feature type edges are used for representing natural features such as rivers, the rivers flow through multiple places, so that the feature type edges can intersect with the boundary type edges, each partition cannot be guaranteed to be a complete region only according to the edge detection result, and map color blocks of adjacent regions are different, so that the regions can be divided by combining gray scale distribution.
The ith edge pixel point of the edge image of the target gray scale image is marked asAcquisition ofPresetting a first threshold value in a left neighborhood A pixel point and a right neighborhood A pixel point in the normal direction of an edge, and recording the difference value between the gray average value of the left neighborhood A pixel point and the gray average value of the right neighborhood A pixel point asIf (if)Greater than the first threshold value, thenMarking as boundary pixel point ifLess than or equal to the first threshold value, thenAnd is marked as a characteristic pixel point. The value of A is a preset value, which can be set to 5, and the first threshold value is set to 10. It should be noted that, the boundary pixel points are pixel points for distinguishing different areas of the map, and the feature pixel points are used for representing natural features. Fig. 2 is a schematic diagram of boundary pixels and feature pixels.
Any gray level map is divided into a plurality of closed subareas by boundary pixel points, and the any closed subareas are marked as one area to obtain a plurality of areas of the gray level map.
Thus, several areas of each gray scale map are acquired.
What is needed is that the gray matrix of the corresponding area in the standard gray map is differentiated from the area of the target gray map, when the shape of the area of the target gray map is complete and has no defect, the differential result is zero matrix, and the more serious the defect of the area of the target gray map is, the more the matrix of the differential result is, and when the area of the target gray map has interference defect, the data in the matrix of the differential result is regularly distributed, so the first integrity of each area in the target gray map is obtained according to the differential expression and the data distribution of each area in the target gray map and the corresponding area in the standard gray map.
Preferably, the obtaining the first integrity of each region in the target gray scale image according to the differential expression of each region in the target gray scale image and the corresponding region in the standard gray scale image includes:
and marking any region of the target gray scale map as a target region, and obtaining a differential gray scale matrix of the target region by making a difference between the gray scale matrix of the target region and the gray scale matrix of the corresponding region in the standard gray scale map.
And acquiring the chain code of any region, namely taking the target region as an example, taking the pixel point with the closest distance between the target region and the origin of the coordinate system as a starting point, and acquiring the eight-direction chain code of the boundary pixel point of the target region in the clockwise direction. The chain codes are numerical sequences describing the shapes, and the shapes are similar when the chain codes are similar.
The first integrity of the target region satisfies the expression:
;
In the formula, Representing a first integrity of the target region; The DTW distance between the chain code of the target area and the chain code of the corresponding area of the target area in the standard gray scale map is represented; an average value of the differential gray matrix representing the target area; The number of values greater than 0 in the differential gray matrix representing the target area. The DTW distance is an index for evaluating the similarity between two sequences in the dynamic time warping algorithm.
In the formula,The ratio of each value larger than 0 in the average value of the differential gray matrix representing the target area is larger, and the larger the value is, the smaller the value larger than 0 is at the same time of the larger average value, so that the defects of the target area are more concentrated and can be focused by human eyes, thereby influencing map viewing, and further representing that the first integrity of the target area is lower; The larger the value representing the difference between the shape of the target region and the shape of the corresponding region of the target region in the standard gray scale map, the larger the shape difference, thereby representing that the target region has difficulty in satisfying the description of the shape of the relevant region by the map, and the lower the first integrity of the target region.
Thus, the first integrity of each region is obtained.
S3, according to the association map structure of each region and the neighborhood region in the target gray scale image, the second integrity of each region in the target gray scale image is obtained through presentation in the standard gray scale image, and the first integrity and the second integrity are combined to obtain the overall integrity of each region in the target gray scale image.
It should be noted that, since the pixel points of the natural feature such as the river pass through multiple regions, if a defect exists in one region, the overall knowledge of the natural feature may be wrong, so that the integrity of the natural feature in other regions is affected. Therefore, the invention analyzes the defect condition of all pixel points of each characteristic and obtains the second integrity of all the passed areas. And finally, combining the first integrity of the region with the second integrity of the region to obtain the overall integrity of each region, wherein the first integrity is used for describing the integrity of the shape and the gray level of the region, and the second integrity is used for describing the integrity of the critical natural features in the region.
Specifically, according to the association map structure of each region and the neighborhood region in the target gray scale map, the second integrity of each region in the target gray scale map is obtained by presenting in the standard gray scale map, which comprises the following steps:
And obtaining boundary pixel points adjacent to the characteristic pixel points, marking the boundary pixel points as equivalent characteristic pixel points, marking the arbitrary characteristic pixel points as growth seeds, carrying out regional growth, wherein the growth condition is that the adjacent pixel points have the characteristic pixel points or the equivalent characteristic pixel points, the growth stop condition is that the adjacent pixel points have no adjacent pixel points and have no equivalent characteristic pixel points, and after the growth is stopped, if the non-grown characteristic pixel points exist, selecting the growth seeds from the non-grown characteristic pixel points until all the characteristic pixel points have the growth regions, marking the arbitrary growth regions as a natural characteristic, and obtaining a plurality of natural characteristics of the gray map.
The v-th region of the standard gray scale image to which the u-th natural feature belongs is recorded asAcquiring the sum of the target gray level diagramCorresponding regions, noted as target gray-scale mapIs related to the acquisition of the target gray-scale imageIs a natural feature of the control region of (c).
It should be noted that, the u-th natural feature of the standard gray scale map completely records the trend of the natural feature, and if the natural feature of the comparison area is defective, the situation of disconnection and redundancy of the pixel points exists, so that the integrity of the natural feature of the comparison area can be obtained according to the difference of the pixel point trend and the number of the u-th natural feature of the standard gray scale map and the natural feature of the comparison area.
And acquiring chain codes of all the natural features, namely taking a pixel point with the nearest distance between any natural feature and the origin of the coordinate system as a starting point, and acquiring eight-direction chain codes of the natural features in a clockwise direction.
Target gray scale mapThe second degree of integrity of the control region of (2) satisfies the expression:
;
In the formula, Representing target gray-scale image with respect toIs a second integrity of the control zone of (a); Representing target gray-scale image with respect to The number of pixels belonging to the natural feature in the comparison area; Representation of The number of pixels belonging to the natural feature; Representing target gray-scale image with respect to Is a natural feature quantity of the control region; Representing target gray-scale image with respect to Chain code of the r-th natural feature of the comparison region, andDTW distance of the chain code of the natural features.
In the formula,Representing target gray-scale image with respect toThe larger the difference between the number of pixels belonging to the natural feature and the number of pixels belonging to the natural feature in the region under the standard condition, the more the value is, the more the target gray-scale image is aboutThe worse and less complete the natural characteristic behavior of the control region of (c), and thus the target gray scale map is relative toThe lower the second integrity of the control zone of (c); expressed in relation to the target gray scale In the case where natural features are split or superfluous in the control region of (a), each natural feature is associated withThe larger the value, the more the trend difference of the natural features in the middle, the target gray map is represented with respect toThe less the trend of the natural features in the control region is in line with the standard case, the more the target gray scale map is related toThe lower the second integrity of the control zone of (c).
If the target region is a comparison region, the second integrity of the target gray map relative to the comparison region of the region is marked as the second integrity of the target region; if the target area is not the control area, the second integrity of the target area is noted as 1.
Thus, the second integrity of each region is obtained.
Preferably, the first integrity and the second integrity are combined to obtain the overall integrity of each region in the target gray scale image, and the method comprises the steps of adding the first integrity of the target region and the second integrity of the target region, and performing positive correlation normalization to obtain the overall integrity of the target region.
So far, the overall integrity of each region is obtained.
S4, acquiring a central defect area and a corresponding radiation defect area of the target gray level image according to the change rule of the overall integrity among the areas in the target gray level image, and recording the central defect area and the corresponding radiation defect area as a defect area, calculating the defect index of any defect area according to the overall integrity of the area contained in the defect area, and evaluating the quality of a map print.
It should be noted that, due to irregular distribution of defects, one defect may be distributed in a plurality of adjacent regions, and the regions include a central defect region with the lowest overall integrity of the defect source and a plurality of defect regions with gradually reduced overall integrity of outward radiation.
Specifically, according to the change rule of the overall integrity between the regions in the target gray level image, a center defect region and a corresponding radiation defect region of the target gray level image are obtained, and the defect region is recorded as a defect region, which comprises:
And acquiring minimum values of the overall integrity of all the areas, respectively marking the minimum values as a central defect area, performing breadth-first traversal on the central defect area until the neighborhood has no defect area, marking all the traversed areas as radiation defect areas corresponding to the central defect area, and combining the central defect area and all the radiation defect areas into one defect area. The second threshold value may be set by an operator according to actual implementation, and for example, the second threshold value may be set to 0.8.
The larger the defective area is, the lower the overall integrity of the defective area is, and the higher the defect index of the defective area is, and thus the defect index of any defective area is calculated.
Preferably, the defect index of any defective region satisfies the expression:
;
In the formula, A defect index indicating an h-th defect region; representing the number of areas of the h-th defective area; The number of pixels in the s-th region representing the h-th defective region; indicating the overall integrity of the s-th region of the h-th defective region.
In the formula,The number of pixel points of the h defect area is represented, the larger the value is, the larger the area of the h defect area is, and the larger the influence of the area of the h defect area on the quality of the map printed matter is, so that the defect index of the h defect area is represented to be higher; the larger the value is, the more serious the defect of the h-th defective area is, and thus the higher the defect index of the h-th defective area is.
Thus, the defect index of each defective area is obtained.
Preferably, evaluating the quality of the map print comprises:
And (3) obtaining defect indexes of all defect areas of all the gray maps to be detected by the method in the step (S1-S3), setting a third threshold value, and if the defect areas with the defect indexes larger than the third threshold value exist in the gray maps to be detected, marking the quality of the map printed matter corresponding to the gray maps to be detected as unqualified. The third threshold value may be set by an operator according to the accuracy requirement of the actual map print, and may be set to 0.3, for example.
Thus, the quality detection of the map printed matter is completed.
The embodiment of the invention also discloses a map print quality detection system, which comprises a processor and a memory, wherein the memory stores computer program instructions, and the computer program instructions realize the map print quality detection method according to the invention when being executed by the processor.
The above system further comprises other components well known to those skilled in the art, such as a communication bus and a communication interface, the arrangement and function of which are known in the art and therefore are not described in detail herein.
While various embodiments of the present invention have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Many modifications, changes, and substitutions will now occur to those skilled in the art without departing from the spirit and scope of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in practicing the invention.
Claims (10)
1. A map print quality detection method, comprising:
Acquiring images of a plurality of maps to be detected of a map, preprocessing the images of all the maps to be detected by manually screening standard images, registering the images in the same coordinate system to obtain a plurality of gray-scale images to be detected and standard gray-scale images, which are commonly called gray-scale images;
Dividing all gray level images based on an edge detection algorithm and gray level distribution to obtain a plurality of areas of any gray level image;
According to the association map structure of each region and the neighborhood region in the target gray scale image, the second integrity of each region in the target gray scale image is obtained through presentation in the standard gray scale image;
Acquiring a central defect area and a corresponding radiation defect area of the target gray level image according to the change rule of the overall integrity among the areas in the target gray level image, and marking the central defect area and the corresponding radiation defect area as a defect area; and calculating the defect index of any defective area according to the total integrity of the areas contained in the defective area, and evaluating the quality of the map printed matter.
2. The method for detecting quality of map printing according to claim 1, wherein the acquiring the plurality of areas of the arbitrary gray scale map includes:
Performing edge detection on all the gray images to obtain corresponding edge images of the gray images;
the ith edge pixel point of the edge image of the target gray scale image is marked as Acquisition ofPresetting a first threshold value in a left neighborhood A pixel point and a right neighborhood A pixel point in the normal direction of an edge, and recording the difference value between the gray average value of the left neighborhood A pixel point and the gray average value of the right neighborhood A pixel point asIf (if)Greater than the first threshold value, thenMarking as boundary pixel point ifLess than or equal to the first threshold value, thenMarking as characteristic pixel points;
any gray level map is divided into a plurality of closed subareas by boundary pixel points, and the any closed subareas are marked as one area to obtain a plurality of areas of the gray level map.
3. The method for detecting quality of map printing according to claim 1, wherein the obtaining the first integrity of each region in the target gray scale image comprises:
Marking any area of the target gray scale map as a target area, and making a difference between a gray scale matrix of the target area and a gray scale matrix of a corresponding area in the standard gray scale map to obtain a differential gray scale matrix of the target area;
the first integrity of the target region satisfies the expression:
;
In the formula, Representing a first integrity of the target region; The DTW distance between the chain code of the target area and the chain code of the corresponding area of the target area in the standard gray scale map is represented; an average value of the differential gray matrix representing the target area; The number of values greater than 0 in the differential gray matrix representing the target area.
4. A method of detecting quality of a map printing according to claim 3, wherein the acquisition of the chain code of the target area comprises:
and acquiring the eight-direction chain code of the boundary pixel point of the target area in the clockwise direction by taking the pixel point of the target area closest to the origin point of the coordinate system as a starting point.
5. The method for detecting quality of map printing according to claim 1, wherein the obtaining the second integrity of each region in the target gray scale image comprises:
Acquiring natural features of any gray level diagram, taking a pixel point with the nearest distance between the natural features and the origin of a coordinate system as a starting point, acquiring eight-direction chain codes of the natural features in a clockwise direction, and marking a v-th region of a u-th natural feature of a standard gray level diagram as a v-th region of the standard gray level diagram Acquiring the sum of the target gray level diagramCorresponding regions, noted as target gray-scale mapIs a control region of (2);
Calculating target gray scale map The second integrity of the target gray map with respect to the comparison area of the belonging area is marked as the second integrity of the target area if the comparison area of the target area is not the comparison area, and the second integrity of the target area is marked as 1 if the target area is not the comparison area.
6. The method for detecting quality of map printing according to claim 5, wherein the acquiring natural features of an arbitrary gray scale image comprises:
And obtaining boundary pixel points adjacent to the characteristic pixel points, marking the boundary pixel points as equivalent characteristic pixel points, marking the arbitrary characteristic pixel points as growth seeds, carrying out regional growth, wherein the growth condition is that the adjacent pixel points have the characteristic pixel points or the equivalent characteristic pixel points, the growth stop condition is that the adjacent pixel points have no adjacent pixel points and have no equivalent characteristic pixel points, and after the growth is stopped, if the non-grown characteristic pixel points exist, selecting the growth seeds from the non-grown characteristic pixel points until all the characteristic pixel points have the growth regions, marking the arbitrary growth regions as a natural characteristic, and obtaining a plurality of natural characteristics of the gray map.
7. The method according to claim 5, wherein the target gray scale map is related toThe second degree of integrity of the control region of (2) satisfies the expression:
;
In the formula, Representing target gray-scale image with respect toIs a second integrity of the control zone of (a); Representing target gray-scale image with respect to The number of pixels belonging to the natural feature in the comparison area; Representation of The number of pixels belonging to the natural feature; Representing target gray-scale image with respect to Is a natural feature quantity of the control region; Representing target gray-scale image with respect to Chain code of the r-th natural feature of the comparison region, andDTW distance of the chain code of the natural features.
8. The method for detecting quality of map printing according to claim 1, wherein the step of obtaining the overall integrity of each region in the target gray scale image comprises:
And adding the first integrity of the target area and the second integrity of the target area, and carrying out positive correlation normalization to obtain the overall integrity of the target area.
9. The map print quality detection method according to claim 1, wherein the defect index of the arbitrary defect area satisfies the expression:
;
In the formula, A defect index indicating an h-th defect region; representing the number of areas of the h-th defective area; The number of pixels in the s-th region representing the h-th defective region; indicating the overall integrity of the s-th region of the h-th defective region.
10. A map print quality detection system comprising a processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement a map print quality detection method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511086107.7A CN120580237B (en) | 2025-08-05 | 2025-08-05 | Map printed matter quality detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511086107.7A CN120580237B (en) | 2025-08-05 | 2025-08-05 | Map printed matter quality detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120580237A true CN120580237A (en) | 2025-09-02 |
| CN120580237B CN120580237B (en) | 2025-10-03 |
Family
ID=96863187
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202511086107.7A Active CN120580237B (en) | 2025-08-05 | 2025-08-05 | Map printed matter quality detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120580237B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002366929A (en) * | 2001-06-11 | 2002-12-20 | Printing Bureau Ministry Of Finance | Method and apparatus for extracting defective defects in printed matter |
| JP2004177215A (en) * | 2002-11-26 | 2004-06-24 | Dainippon Printing Co Ltd | Printed matter inspection apparatus, printed matter inspection method, printed matter inspection processing program, and recording medium on which the program is recorded |
| CN117237265A (en) * | 2022-06-08 | 2023-12-15 | 腾讯科技（深圳）有限公司 | Method, device, equipment and storage medium for detecting frozen image frames |
| CN117541588A (en) * | 2024-01-10 | 2024-02-09 | 大连建峰印业有限公司 | Printing defect detection method for paper product |
| CN118134886A (en) * | 2024-03-19 | 2024-06-04 | 北京大恒图像视觉有限公司 | A method for detecting imaging defects of laser printed products |
| CN118247259A (en) * | 2024-04-16 | 2024-06-25 | 山东润声印务有限公司 | High-speed printed matter quality online detection method |
| CN119130972A (en) * | 2024-09-04 | 2024-12-13 | 成都中永印务有限责任公司 | A method and system for online detection of printed product quality |
-
2025
- 2025-08-05 CN CN202511086107.7A patent/CN120580237B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002366929A (en) * | 2001-06-11 | 2002-12-20 | Printing Bureau Ministry Of Finance | Method and apparatus for extracting defective defects in printed matter |
| JP2004177215A (en) * | 2002-11-26 | 2004-06-24 | Dainippon Printing Co Ltd | Printed matter inspection apparatus, printed matter inspection method, printed matter inspection processing program, and recording medium on which the program is recorded |
| CN117237265A (en) * | 2022-06-08 | 2023-12-15 | 腾讯科技（深圳）有限公司 | Method, device, equipment and storage medium for detecting frozen image frames |
| CN117541588A (en) * | 2024-01-10 | 2024-02-09 | 大连建峰印业有限公司 | Printing defect detection method for paper product |
| CN118134886A (en) * | 2024-03-19 | 2024-06-04 | 北京大恒图像视觉有限公司 | A method for detecting imaging defects of laser printed products |
| CN118247259A (en) * | 2024-04-16 | 2024-06-25 | 山东润声印务有限公司 | High-speed printed matter quality online detection method |
| CN119130972A (en) * | 2024-09-04 | 2024-12-13 | 成都中永印务有限责任公司 | A method and system for online detection of printed product quality |
Non-Patent Citations (1)
| Title |
|---|
| 杨欧;胡涛;郭轩;郭宝平;: "灰度形态学在印刷品缺陷检测中的应用", 微计算机信息, no. 07, 5 March 2008 (2008-03-05), pages 226 - 227 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120580237B (en) | 2025-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113379680B (en) | Defect detection method, defect detection device, electronic device and computer readable storage medium | |
| US6778703B1 (en) | Form recognition using reference areas | |
| CN111028213A (en) | Image defect detection method, device, electronic device and storage medium | |
| CN114972173B (en) | Defect detection method, defect detection device and system | |
| CN114418899B (en) | Self-adaptive repairing method and system for self-color printing and readable storage medium | |
| CN116559183B (en) | Method and system for improving defect judging efficiency | |
| CN109472271B (en) | Printed circuit board image contour extraction method and device | |
| CN114937037B (en) | Product defect detection method, device and equipment and readable storage medium | |
| CN118501177B (en) | Appearance defect detection method and system for formed foil | |
| CN115546141B (en) | A method and system for detecting defects in small-sample Mini LEDs based on multi-dimensional metrics | |
| CN113469171A (en) | Method, device and medium for identifying interest area in SFR test card image | |
| CN114187363A (en) | A method, device and mobile terminal for obtaining radial distortion parameter value | |
| WO2007139836A2 (en) | Optical mark reader | |
| CN117830318A (en) | Ink printing defect detection method based on image processing | |
| CN119492522A (en) | Bad pixel detection method, system, device and storage medium for liquid crystal display screen | |
| CN113989482B (en) | Automatic reading identification method of optical imaging level based on image processing | |
| CN114254605B (en) | Answer sheet template generation method, answer sheet recognition method, device and electronic device | |
| CN118967798B (en) | Positioning method and device for display screen sub-pixel bright clusters and storage medium | |
| CN120672748A (en) | Display screen detection method and system based on image processing | |
| CN120580237A (en) | A method and system for detecting map print quality | |
| CN116228601B (en) | A visual monitoring method for flat coal effect of train two-way flat coal | |
| CN114638805B (en) | Track slab crack detection method, system and storage medium | |
| CN119477924B (en) | Method, device, electronic equipment and storage medium for repeated X-ray weld film detection | |
| CN112287856A (en) | Logo detection method | |
| CN119274197B (en) | Wireless form detection method and system |
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 |