CN112837303A - Defect detection method, device, equipment and medium for mold monitoring - Google Patents
Defect detection method, device, equipment and medium for mold monitoring Download PDFInfo
- Publication number
- CN112837303A CN112837303A CN202110181174.2A CN202110181174A CN112837303A CN 112837303 A CN112837303 A CN 112837303A CN 202110181174 A CN202110181174 A CN 202110181174A CN 112837303 A CN112837303 A CN 112837303A
- Authority
- CN
- China
- Prior art keywords
- pixel point
- point set
- image
- region
- points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 108
- 238000001514 detection method Methods 0.000 title claims abstract description 83
- 238000012544 monitoring process Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 70
- 230000009466 transformation Effects 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims description 29
- 239000011159 matrix material Substances 0.000 claims description 26
- 230000009467 reduction Effects 0.000 claims description 22
- 238000006243 chemical reaction Methods 0.000 claims description 19
- 238000003860 storage Methods 0.000 claims description 19
- 230000035945 sensitivity Effects 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 8
- 238000005316 response function Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 11
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 230000003044 adaptive effect Effects 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 6
- 238000013209 evaluation strategy Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000001746 injection moulding Methods 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 235000002566 Capsicum Nutrition 0.000 description 2
- 239000006002 Pepper Substances 0.000 description 2
- 241000722363 Piper Species 0.000 description 2
- 235000016761 Piper aduncum Nutrition 0.000 description 2
- 235000017804 Piper guineense Nutrition 0.000 description 2
- 235000008184 Piper nigrum Nutrition 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
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
- G06T7/001—Industrial image inspection using an image reference approach
-
- G06T5/70—
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The embodiment of the invention discloses a defect detection method, a defect detection device, defect detection equipment and a defect detection medium for mold monitoring. Wherein, the method comprises the following steps: acquiring a first pixel point set corresponding to a template image and a second pixel point set corresponding to an image to be detected; determining a first characteristic point set and a second characteristic point set according to the similarity between the first target pixel point and the corresponding second target pixel point; determining an image transformation rule according to the position information of a preset number of first feature points in the first feature point set and the position information of corresponding second feature points in the second feature point set, and correcting the position information of all pixel points in the second region of interest according to the image transformation rule to obtain corrected pixel points; and determining a difference image according to the corrected pixel points and the corresponding pixel points in the first region of interest, and performing defect detection on the difference image. The technical scheme of the embodiment of the invention can realize efficient and accurate defect detection and is beneficial to improving the production quality of the die.
Description
Technical Field
The embodiment of the invention relates to the technical field of digital image processing, in particular to a defect detection method, device, equipment and medium for mold monitoring.
Background
In the manufacturing industry, due to the particularity and irregularity of different products and dies, time and labor are wasted when the production state of the products is detected, the die opening state of the dies cannot be accurately and quickly detected, and the problems of die damage, reduction of production efficiency and the like are caused. Taking the injection molding industry as an example, the quality of the mold is directly related to the quality of the product, so how to effectively monitor the states of the mold and the product in the injection molding process, thereby ensuring the production quality of the mold is the key point of the injection molding industry.
The existing defect detection methods for mold monitoring can be roughly divided into three categories: a matching-based method, an image understanding search-based method, and a feature location search-based method. There are two main matching-based methods, grayscale and shape. The matching method based on the gray scale measures the similarity of the pixel points of the target image to be detected and the original image, the matching method based on the shape measures the similarity of the target image to be detected and the template, and then the defect detection is carried out; the image understanding-based searching method is characterized in that target characteristics are summarized by means of Artificial Intelligence (AI) and the like, and then defect detection is carried out; the method based on feature positioning search firstly converts the analysis of the whole image into the analysis of the image features, and then carries out defect detection.
However, the matching speed of the matching method based on the gray scale in the scheme is low, and the method is not suitable for the situation that the target rotates and deforms before and after the mould is opened; the shape-based matching method has higher requirements on the field working conditions, and the field environment of the mold monitoring application is complex and is not suitable for the mold monitoring application; the image understanding and searching based method is low in matching precision, and a large amount of data needs to be trained in each scene, so that generalization is difficult to realize; the method based on feature positioning search has high requirement on feature selection and consumes long time. There is no efficient defect detection method for mold monitoring.
Disclosure of Invention
The embodiment of the invention provides a defect detection method, device, equipment and medium for monitoring a mold, which can realize efficient and accurate defect detection and are beneficial to improving the production quality of the mold.
In a first aspect, an embodiment of the present invention provides a defect detection method for mold monitoring, where the method includes:
acquiring a first pixel point set corresponding to a first interested area of a template image and a second pixel point set corresponding to a second interested area of an image to be detected, wherein the template image is obtained by shooting a mold, and the image to be detected is obtained by shooting a product produced by using the mold;
determining a first characteristic point set and a second characteristic point set according to the similarity between a first target pixel point in the first pixel point set and a corresponding second target pixel point in the second pixel point set;
determining an image transformation rule according to the position information of a preset number of first feature points in the first feature point set and the position information of a corresponding same number of second feature points in the second feature point set, and correcting the position information of all pixel points in the second region of interest according to the image transformation rule to obtain corrected pixel points;
and determining a difference image according to the corrected pixel points and the corresponding pixel points in the first region of interest, and performing defect detection on the difference image according to a preset defect judgment method.
In a second aspect, an embodiment of the present invention provides a defect detecting apparatus for mold monitoring, the apparatus including:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a first pixel point set corresponding to a first interested area of a template image and a second pixel point set corresponding to a second interested area of an image to be detected, the template image is obtained by shooting a mold, and the image to be detected is obtained by shooting a product produced by using the mold;
the determining module is used for determining a first characteristic point set and a second characteristic point set according to the similarity between a first target pixel point in the first pixel point set and a corresponding second target pixel point in the second pixel point set;
the correction module is used for determining an image transformation rule according to the position information of a preset number of first feature points in the first feature point set and the position information of a corresponding same number of second feature points in the second feature point set, and correcting the position information of all pixel points in the second region of interest according to the image transformation rule to obtain corrected pixel points;
and the detection module is used for determining a difference image according to the corrected pixel points and the corresponding pixel points in the first region of interest and detecting the defects of the difference image according to a preset defect judgment method.
In a third aspect, an embodiment of the present invention provides a computer device, where the computer device includes:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method for defect detection for mold monitoring as described in any embodiment of the invention.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements a defect detection method for mold monitoring according to any embodiment of the present invention.
The embodiment of the invention provides a defect detection method, a device, equipment and a medium for monitoring a mold, which comprises the steps of firstly obtaining a first pixel point set corresponding to a first interested area of a template image and a second pixel point set corresponding to a second interested area of an image to be detected, then determining a first characteristic point set and a second characteristic point set according to the similarity between a first target pixel point in the first pixel point set and a corresponding second target pixel point in the second pixel point set, then determining an image transformation rule according to the position information of a preset number of first characteristic points in the first characteristic point set and the position information of a corresponding same number of second characteristic points in the second characteristic point set, correcting the position information of all pixel points in the second interested area according to the image transformation rule to obtain corrected pixel points, and finally determining an image according to the corrected pixel points and the corresponding pixel points in the first interested area, and the difference image is subjected to defect detection according to a preset defect judgment method, so that efficient and accurate defect detection can be realized, and the production quality of the die is improved.
Drawings
FIG. 1 is a flowchart of a defect detection method for mold monitoring according to an embodiment of the present invention;
FIG. 2 is a flowchart of a defect detection method for mold monitoring according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a defect detection apparatus for mold monitoring according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a defect detection method for mold monitoring according to an embodiment of the present invention, which is applicable to a situation of defect detection of an image to be detected, which is obtained by shooting a product produced by using a mold in a mold monitoring process. The defect detection method for mold monitoring provided by the embodiment can be executed by the defect detection device for mold monitoring provided by the embodiment of the invention, and the device can be realized by software and/or hardware and is integrated in computer equipment for executing the method.
Referring to fig. 1, the method of the present embodiment includes, but is not limited to, the following steps:
s110, a first pixel point set corresponding to a first interested area of the template image and a second pixel point set corresponding to a second interested area of the image to be detected are obtained.
The template image is obtained by shooting a mold, the image to be detected is obtained by shooting a product produced by using the mold, and the template image and the image to be detected can be obtained by carrying out corresponding shooting operation after receiving a shooting signal. A first pixel point set corresponding to a first Region of Interest (ROI) can be understood as two meanings, one is a first pixel point set in the first ROI, and the other is a first pixel point set in the first ROI obtained by performing boundary expansion on the first ROI. Similarly, the second pixel point set corresponding to the second ROI may also be understood as two meanings, one is the second pixel point set in the second ROI, and the other is the second pixel point set in the second region obtained by performing boundary expansion on the second ROI. The pixels in the first pixel set and the second pixel set are in one-to-one correspondence.
In order to detect the defect condition of the image to be detected, after the template image and the image to be detected are obtained, because the two images both contain a plurality of pixel points, if all the pixel points are processed, time is consumed, and unnecessary resource waste is caused. By acquiring a first pixel point set corresponding to a first ROI of a template image and a second pixel point set corresponding to a second ROI of an image to be detected, corresponding operations are performed on pixels in the first pixel point set and corresponding pixels in the second pixel point set, time can be saved, and detection speed is accelerated.
S120, determining a first characteristic point set and a second characteristic point set according to the similarity between a first target pixel point in the first pixel point set and a corresponding second target pixel point in the second pixel point set.
The first target pixel point and the second target pixel point are both points meeting target point screening conditions, and the target point screening conditions can be preset and can also be determined according to specific conditions.
After the first pixel point set and the second pixel point set are obtained, according to preset target point screening conditions, a first target pixel point in the first pixel point set and a corresponding second target pixel point in the second pixel point set can be determined, then, according to any one of Euclidean distance, Hamming distance or other similarity detection methods, the similarity between the first target pixel point and the corresponding second target pixel point is determined, according to the similarity, whether the first target pixel point and the corresponding second target pixel point are feature points can be determined, and accordingly, the first feature point set and the second feature point set can be determined.
S130, determining an image transformation rule according to the position information of the preset number of first feature points in the first feature point set and the position information of the corresponding same number of second feature points in the second feature point set, and correcting the position information of all pixel points in the second region of interest according to the image transformation rule to obtain corrected pixel points.
The preset number may be determined according to specific situations, or may be set in advance, and this embodiment is not particularly limited.
After the first feature point set and the second feature point set are determined, an image transformation rule, namely an image transformation matrix, can be determined according to the position information of a preset number of first feature points in the first feature point set and the position information of a corresponding same number of second feature points in the second feature point set. And correcting the position information of all pixel points in the second ROI according to the image conversion matrix to obtain corrected pixel points, so that all the pixel points in the second ROI and the corresponding pixel points in the first ROI are positioned at the same position, a differential image is conveniently determined according to the corrected pixel points and the corresponding pixel points in the first ROI in the follow-up process, and defect detection is carried out on the differential image according to a preset defect judgment method.
And S140, determining a difference image according to the corrected pixel points and the corresponding pixel points in the first region of interest, and performing defect detection on the difference image according to a preset defect judgment method.
The differential image can be understood as the difference between the corrected pixel point and the corresponding pixel point in the first region of interest.
After all pixel point sets in the second ROI of the image to be detected are corrected, in order to acquire the difference between the template image and the image to be detected, a difference image obtained by comparing the two images needs to be determined, and the difference image can display different information of ROI areas of the two images. The difference image of the template image and the image to be detected can be obtained according to the corrected pixel points and the corresponding pixel points in the first ROI, after the difference image is determined, the defect detection is carried out on the difference image according to a preset defect judgment method, for example, the size of a gray value difference value corresponding to the difference image is judged so as to carry out defect detection on the difference image, or the difference image is judged through a preset sensitivity threshold value so as to determine a region to be detected of the difference image, the area of the region to be detected is judged so as to carry out defect detection on the difference image, and the like, so that the defect detection result of the image to be detected can be obtained.
The technical solution provided in this embodiment is to first obtain a first pixel point set corresponding to a first region of interest of a template image and a second pixel point set corresponding to a second region of interest of an image to be detected, then determine a first feature point set and a second feature point set according to similarity between a first target pixel point in the first pixel point set and a corresponding second target pixel point in the second pixel point set, then determine an image transformation rule according to position information of a preset number of first feature points in the first feature point set and position information of a corresponding same number of second feature points in the second feature point set, correct position information of all pixel points in the second region of interest according to the image transformation rule to obtain corrected pixel points, and finally determine a difference image according to the corrected pixel points and the corresponding pixel points in the first region of interest, and the defect detection is carried out on the difference image according to a preset defect judgment method, the workload can be effectively reduced and the time can be saved through the selection of the region of interest, the efficient and accurate defect detection is finally realized, and the production quality of the die is favorably improved.
In some embodiments, obtaining a first pixel point set corresponding to a first region of interest of the template image and a second pixel point set corresponding to a second region of interest of the image to be detected may specifically include: determining a first interested area of the template image and a second interested area of the image to be detected; and carrying out noise reduction processing on the pixel points corresponding to the first region of interest to obtain a first pixel point set, and carrying out noise reduction processing on the pixel points corresponding to the second region of interest to obtain a second pixel point set.
Specifically, the first ROI of the template image and the second ROI of the image to be detected are determined, for example, a plurality of shaped regions such as a circular region, a rectangular region, and a polygonal region may be selected as the first ROI in the entire image of the template image, and a plurality of shaped regions such as a circular region, a rectangular region, and a polygonal region may be selected as the second ROI in the entire image of the image to be detected. It should be noted that: the shapes of the first ROI and the second ROI should be kept consistent to ensure the accuracy of the acquired first pixel point set and the corresponding second pixel point set. After the first ROI and the second ROI are obtained, denoising processing is carried out on pixel points corresponding to the first ROI through denoising methods such as an average filter, a self-adaptive median filter and a morphological noise filter, so that a first pixel point set is obtained, denoising processing is carried out on pixel points corresponding to the second ROI through denoising methods such as the average filter, the self-adaptive median filter and the morphological noise filter, so that a second pixel point set is obtained.
In the embodiment of the invention, the first ROI and the second ROI are determined firstly, and then the noise reduction processing is respectively carried out on the pixel points corresponding to the first ROI and the pixel points corresponding to the second ROI, so that the interference of noise to the image can be reduced, and the accuracy of the subsequent defect detection result can be improved.
In some embodiments, the denoising processing is performed on the pixel point corresponding to the first region of interest to obtain a first pixel point set, and the denoising processing is performed on the pixel point corresponding to the second region of interest to obtain a second pixel point set, which may specifically include: performing boundary expansion on the first region of interest to obtain an expanded first region, and performing boundary expansion on the second region of interest to obtain an expanded second region; and carrying out noise reduction processing on the pixel points in the first region through the self-adaptive median filter to obtain a first pixel point set, and carrying out noise reduction processing on the pixel points in the second region through the self-adaptive median filter to obtain a second pixel point set.
The self-adaptive median filter is an image noise reduction method, can filter salt and pepper noise with high probability, and can better protect image details. The pepper noise is a small gray value, and the presented effect is small black dots; salt noise refers to a large gray value and the effect presented is a small white dot.
Specifically, in order to better acquire the edge features of the template image and the image to be detected, the boundary of the first ROI is extended, for example, the boundary of the first ROI may be filled by using a set fixed value, so that the extended first region can be obtained. Similarly, the boundary extension is performed on the second ROI by the same method, and the extended second region can be obtained. After the first region and the second region are obtained, noise reduction processing is performed on all pixel points in the first region through a self-adaptive median filter, and a first pixel point set can be obtained. Similarly, noise reduction processing is performed on all pixel points in the second region through the adaptive median filter, so that a second pixel point set can be obtained, and the first feature point set and the second feature point set are determined according to the similarity between the first target pixel point in the first pixel point set and the corresponding second target pixel point in the second pixel point set.
When the probability of noise occurrence is high, the window size of the median filter is dynamically changed through the adaptive median filter according to a preset condition, and the effects of removing noise and protecting image details can be achieved. The output result of the adaptive median filter is a gray value, which is used to replace the gray value at the point (x, y) at the center position of the filtering window, and the value range of the gray value is 0-255. The adaptive median filter can be divided into two steps, step a and step B:
step A: let A1＝Zmed-Zmin，A2＝Zmed-ZmaxIf A is1>0 and A2<0, jumping to the step B; otherwise, increasing the size of the window; if the size of the increased window is less than or equal to SmaxRepeating the step A, otherwise, outputting Zmed。
This step is intended to determine the median value Z obtained in the current windowmedWhether it is noise.
And B: let B1＝Zxy-Zmin，B2＝Zxy-ZmaxIf B is1>0 and B2<0, then output ZxyOtherwise, output Zmed。
Wherein S isxyThe method is characterized by comprising the following steps of representing an action area of the self-adaptive median filter and also representing an area covered by a filter window, wherein the central point of the area is the xth row and the xth column of pixel points in an image. ZminDenotes SxyMiddle minimum gray value, ZmaxDenotes SxyMiddle maximum gray value, ZmedDenotes SxyMedian of all gray values in, ZxyExpressing the gray value of the pixel point of the y row and the x column in the image, SmaxDenotes SxyThe maximum window size allowed.
From the above two steps: the self-adaptive median filter can quickly process noise with low occurrence probability; the same can be handled by increasing the window size in the adaptive median filter when the noise point probability is high.
In some embodiments, after performing noise reduction processing on the pixel points corresponding to the first ROI to obtain a first pixel point set and performing noise reduction processing on the pixel points corresponding to the second ROI to obtain a second pixel point set, image sharpness evaluation may be performed on the image subjected to noise reduction processing, and specifically, evaluation may be performed through a multi-factor image sharpness evaluation policy.
Since image sharpness directly affects image quality, high-definition images are more conducive to subsequent defect detection in mold monitoring applications. The multi-factor image definition evaluation strategy can be a two-way gradient evaluation strategy and an image variance evaluation strategy. In both cases, processing is performed in a spatial domain, and the main idea is to perform image sharpness evaluation by using the gradient difference of the gray features between adjacent pixels.
For the bi-directional gradient evaluation strategy, if the original image is represented by A, GxRepresenting convolution by detection of transverse edges, i.e. gradient values in the horizontal direction, GyRepresenting convolutions with longitudinal edge detection, i.e. gradient values in the vertical direction, e.g. a 3 x3 matrix, corresponding to GxAnd GyThe formula of (a) is as follows:
order to
Wherein f (x, y) represents the gray value of the pixel point at the middle position in the image a, x represents the number of rows, and y represents the number of columns, and the matrix a is respectively substituted into the two formulas to obtain:
in obtaining GxAnd GyThen go toOver-evaluation function
The image definition can be evaluated, and the larger the value of G, the higher the definition of the corresponding image.
Variance is a metric used in probability theory to examine the degree of dispersion between a set of discrete data and its expectations. The variance is large, which means that the deviation between the group of data is large, and the data distribution in the group is not balanced; the variance is small, indicating an average distribution among the data within the group. For the image variance evaluation strategy, the image definition is high, the gray difference between image data is increased, namely the variance is large, so that the image definition can be measured through the variance of the image gray data, the larger the variance is, the better the definition is represented, the difference between image pixels is evaluated through calculating the variance of the image, and then whether the image definition is qualified is evaluated. The image variance formula is as follows:
wherein M × N represents the resolution of the image, M represents the width of the image, N represents the height of the image, p (i, j) represents the gray value of the pixel point of the ith row and the jth column, and μ represents the mean value.
In some embodiments, determining the first feature point set and the second feature point set according to the similarity between the first target pixel point in the first pixel point set and the corresponding second target pixel point in the second pixel point set may specifically include: determining a first to-be-confirmed corner set according to the gradient of each pixel point in the first pixel point set, and determining a first target pixel point set according to a first corner response function of each to-be-confirmed corner in the first to-be-confirmed corner set; determining a second to-be-confirmed corner set according to the gradient of each pixel point in the second pixel point set, and determining a second target pixel point set according to a second corner response function of each to-be-confirmed corner in the second to-be-confirmed corner set; aiming at each first target pixel point in the first target pixel point set, calculating the Hamming distance between the current first target pixel point and a second target pixel point corresponding to the position of the current first target pixel point in the second target pixel point set, determining whether the current first target pixel point and the second target pixel point are feature points or not according to the Hamming distance, if so, storing the current first target pixel point to the first feature point set, and storing the second target pixel point to the second feature point set.
Specifically, the determination method of the first target pixel point set is as follows:
1) assuming that the template image is I, the gradient value I of each pixel point in the first pixel point set corresponding to the template image I in the horizontal direction can be calculated through a gradient calculation formulaXAnd a gradient value I in the vertical directionYIf I isXGreater than or equal to a set gradient threshold in the horizontal direction, and IYIf the gradient threshold value is larger than or equal to the set gradient threshold value in the vertical direction, determining the pixel point as a first corner point to be confirmed, and storing the pixel point to a first corner point set to be confirmed;
2) for calculating each first to-be-confirmed corner in the first set of to-be-confirmed corners
And IXIY；
3) For calculated
And IXIYCarrying out Gaussian filtering to eliminate Gaussian noise;
4) for each first corner point to be confirmed, a correlation matrix is respectively constructed
And a first angular response function
Where | M | represents the determinant of M, tr(M) represents the trace of M, i.e., the sum of the elements on the diagonal of matrix M;
5) and performing non-maximum suppression on the R, if the R is greater than a threshold value T, determining a corresponding first corner to be confirmed as a first target pixel point, and storing the first target pixel point into a first target pixel point set.
Similarly, the same calculation is performed on all the pixel points in the second pixel point set corresponding to the image to be detected through the determining mode, so that a second target pixel point set can be determined. And the pixels in the first target pixel point set and the second target pixel point set are in one-to-one correspondence. After the first target pixel point set and the second target pixel point set are obtained, aiming at each first target pixel point in the first target pixel point set, calculating the Hamming distance between the current first target pixel point and a second target pixel point corresponding to the current first target pixel point in the second target pixel point set, if the value corresponding to the Hamming distance is greater than a preset distance threshold value, determining that the current first target pixel point and the second target pixel point are feature points, storing the current first target pixel point to the first feature point set, and storing the second target pixel point to the second feature point set.
Wherein, the hamming distance represents the number of bits with different corresponding bit values in two binary sequences (with the same length), i.e. the description sequence x ═ x1,x2，…,xk,…,xn) And the sequence y ═ y (y)1,y2，…，yk,…，yn) The calculation formula of the hamming distance is as follows:
wherein the content of the first and second substances,
denotes a modulo-2 operation (XOR operation), xk∈{0,1}，ykE {0,1}, k being the sequence index.
Exemplarily, taking calculation of the hamming distance between the current first target pixel point and the second target pixel point corresponding to the current position of the first target pixel point in the second target pixel point set as an example, the gray value of the first target pixel point is first converted into a binary sequence x, the second target pixel point corresponding to the current position of the first target pixel point in the second target pixel point set is converted into a binary sequence y, and then the hamming distance between the current first target pixel point and the corresponding second target pixel point can be obtained according to a calculation formula of d (x, y). For example, suppose
x is: 00000000000000000100000011101111
y is: 00000000100000001100000001101111
Then d (x, y) is 3.
It should be noted that the gradient threshold in the horizontal direction, the gradient threshold in the vertical direction, and the threshold T may be determined according to specific situations, and may also be set in advance, and this embodiment is not particularly limited.
In the embodiment of the invention, in the complex working condition monitored by the mold, the similarity between the first target pixel point and the corresponding second target pixel point is judged according to the size relation of the Hamming distance, so that whether the two pixel points are the feature points or not is determined, and the Euclidean distance between the obtained first feature point set and the second feature point set is more accurate. The smaller the Hamming distance is, the higher the similarity of the two pixel points is, the higher the similarity is, the two points are both characteristic points, the better the uniqueness of the two points is, and one-to-one information can be formed.
Example two
Fig. 2 is a flowchart of a defect detection method for mold monitoring according to a second embodiment of the present invention. The embodiment of the invention is optimized on the basis of the embodiment. Optionally, this embodiment explains in detail a process of performing defect detection on the difference image according to a preset defect judgment method.
Referring to fig. 2, the method of the present embodiment includes, but is not limited to, the following steps:
s210, a first pixel point set corresponding to a first interested area of the template image and a second pixel point set corresponding to a second interested area of the image to be detected are obtained.
S220, determining a first characteristic point set and a second characteristic point set according to the similarity between a first target pixel point in the first pixel point set and a corresponding second target pixel point in the second pixel point set.
And S230, determining an image transformation rule according to the position information of the preset number of first feature points in the first feature point set and the position information of the corresponding same number of second feature points in the second feature point set, and correcting the position information of all pixel points in the second region of interest according to the image transformation rule to obtain corrected pixel points.
Optionally, determining an image transformation rule according to the position information of a preset number of first feature points in the first feature point set and the position information of a corresponding same number of second feature points in the second feature point set, and performing position information correction on all pixel points in the second region of interest according to the image transformation rule to obtain corrected pixel points, which may specifically include: extracting a preset number of first feature points from the first feature point set, and extracting the same number of second feature points corresponding to the first feature points from the second feature point set to form a preset number of groups of feature points, wherein the preset number is equal to the preset number of groups; determining an image conversion matrix according to the position information of each group of feature points in the feature points with the preset group number; and correcting the position information of all pixel points in the second region of interest according to the image conversion matrix to obtain corrected pixel points.
The preset number can be designed in advance, and can also be determined according to specific conditions, so that the requirement for determining the image conversion matrix can be met.
Specifically, for the working condition monitored by the mold, at least four groups of feature point position information are needed for calculation, but considering that the feature points with inaccurate position information influence the transformation precision in the feature point screening process, multiple groups of feature points are needed for calculation. Theoretically, the more the feature points are, the more accurate the result of the transformation matrix is, and in practical application, the more the feature points are, the more the calculation amount is increased. Therefore, a preset number of first feature points are extracted from the first feature point set, and the same number of second feature points corresponding to the first feature points are extracted from the second feature point set to form a preset number of groups of feature points. According to the position information of each group of feature points in the preset number of groups of feature points, an image conversion matrix can be determined, and the specific conversion process is as follows: assuming that [ u, v, w ] is the position information of a certain feature point in the second feature point set in the image to be detected (equivalent to the position information before the transformation of a certain feature point), [ x ', y ', w ' ] is the position information of the corresponding feature point in the first feature point set in the template image (equivalent to the position information after the transformation of a certain feature point), the corresponding image transformation rule is as follows:
wherein the content of the first and second substances,
a is the corresponding image transformation matrix, a11，a12，…，a33Are the corresponding elements in matrix a.
After the image conversion matrix is obtained, matrix conversion is carried out on all pixel points in the second ROI through the image conversion matrix, namely position information correction is carried out, and the corrected pixel points can be obtained after correction.
In the embodiment of the invention, the image conversion matrix is more accurate by acquiring the preset group number of feature points, determining the image conversion matrix according to the position information of the preset group number of feature points and correcting the position information of all pixel points in the second ROI according to the image conversion matrix, so that the corrected pixel points are more accurate, the error is reduced, and the precision and the speed are considered.
For example, the following describes the calculation process of the image transformation matrix by taking four sets of feature points as an example:
one two-dimensional image is transformed into another planar image through perspective by the following process:
wherein x represents the horizontal position information of the feature points in the second feature point set, y represents the vertical position information of the feature points in the second feature point set, u represents the horizontal position information of the corresponding feature points in the first feature point set, v represents the vertical position information of the corresponding feature points in the first feature point set, and a, b, c, d, e, f, k, l, m, and n are all coefficients to be calculated.
Converting equations (8) and (9) to obtain the following equations:
wherein, g and h are coefficients to be solved, n-m-g, and l-k-h.
Assuming that (x1, y1), (x2, y2), (x3, y3), (x4, y4) are four sets of feature points in the second feature point set (i.e., four feature points before conversion), (u1, v1), (u2, v2), (u3, v3), and (u4, v4) are four sets of feature points in the first feature point set corresponding to four sets of feature points in the second feature point set (i.e., four feature points after conversion), the four sets of feature points are combined to form a total of four sets of feature points, and the four sets of feature points are substituted into equation (10), so that an image conversion matrix can be obtained:
s240, subtracting the gray value corresponding to each pixel point in the corrected pixel points from the gray value corresponding to the pixel point in the first interested region to obtain a difference image.
After the corrected pixel points are obtained, because the corrected pixel points are consistent with the position information of the corresponding pixel points in the first ROI, the gray value corresponding to each pixel point in the corrected pixel points is subtracted from the gray value corresponding to the corresponding pixel point in the first ROI, so that a difference image can be obtained, and the difference image is expressed by a matrix.
And S250, judging the differential image through a preset sensitivity threshold value, and determining the to-be-detected region of the differential image.
The preset sensitivity threshold may be preset, or may be determined according to specific situations, and the embodiment is not particularly limited.
After obtaining the difference image, judging the size of each gray value difference value in the difference image and a preset sensitivity threshold, wherein the judgment rule may be: if a certain gray value difference value is smaller than or equal to a preset sensitivity threshold, filtering a region corresponding to the gray value difference value in the second ROI of the image to be detected (namely, the region is not determined as the region to be detected of the differential image); if the difference value of a certain gray value is larger than the preset sensitivity threshold value, the region corresponding to the gray value in the second ROI of the image to be detected is determined as the region to be detected of the difference image. The judgment rule can be expressed by the following formula:
wherein, M (x, y) represents the gray value of a certain pixel in the corrected pixels, N (x, y) represents the gray value of the pixel corresponding to M (x, y) in the first ROI, T represents a preset sensitivity threshold, D (x, y) represents the determination result of the region to be detected, if D (x, y) is equal to 1, it represents that the region corresponding to the pixel is determined as the region to be detected of the differential image, and if D (x, y) is equal to 0, it represents that the region corresponding to the pixel is filtered.
And S260, detecting the defects of the to-be-detected area according to a preset defect judgment method.
After the to-be-detected region of the differential image is determined, defect detection can be performed on the to-be-detected region through a preset defect judgment method, and a defect detection result of the to-be-detected image is obtained.
Optionally, the defect detection of the to-be-detected region according to the preset defect judgment method may specifically include: for each to-be-detected area in the to-be-detected area, if the area of the current to-be-detected area is larger than or equal to a first area threshold value, determining that the defect detection result of the current to-be-detected area does not pass; and when the areas of all the regions to be detected are smaller than the first area threshold value, acquiring the total area of all the regions to be detected, and if the total area is larger than or equal to the second area threshold value, determining that the defect detection result of the regions to be detected does not pass.
The first area threshold and the second area threshold may be preset, or may be determined according to specific situations, and this embodiment is not particularly limited.
In the embodiment of the invention, by judging the area of each region to be detected and judging the total area of all the regions to be detected when the area of all the regions to be detected is smaller than the first area threshold value, the judgment process is more reliable, and the finally obtained defect detection result is more accurate.
Illustratively, as shown in table 1 below, the evaluation results of the two filtering methods are shown, and as can be seen from table 1, the results in the multi-factor image sharpness evaluation strategy show that the adaptive median filter can better preserve image details.
TABLE 1
Illustratively, the comparison results of the feature point time determined by the two methods are shown in table 2 below, and it can be seen from table 2 that: the time for determining the characteristic points by the method is about 100ms faster than the time for determining the characteristic points by an Oriented Fast and Rotated Brief (ORB) method.
TABLE 2
Exemplarily, the defect detection results are shown in the following table 3, and it can be seen from table 3 that: under the condition that the mold opening position is unstable, the method for detecting the defects can accurately judge the working condition, and is favorable for improving the production quality and precision of the mold.
TABLE 3
According to the technical scheme provided by the embodiment, after the corrected pixel points are obtained, the gray value corresponding to each pixel point in the corrected pixel points is subtracted from the gray value corresponding to the pixel point in the first region of interest to obtain the difference image, the difference image is judged through the preset sensitivity threshold value, the region to be detected of the difference image is determined, and the defect detection is performed on the region to be detected according to the preset defect judgment method, so that the defect detection result is more accurate and closer to the actual condition, the efficient and accurate defect detection is realized, and the mold production quality is favorably improved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a defect detecting apparatus for mold monitoring according to a third embodiment of the present invention, as shown in fig. 3, the apparatus may include:
the acquiring module 310 is configured to acquire a first pixel point set corresponding to a first region of interest of a template image and a second pixel point set corresponding to a second region of interest of an image to be detected, where the template image is obtained by shooting a mold, and the image to be detected is obtained by shooting a product produced by using the mold;
a determining module 320, configured to determine a first feature point set and a second feature point set according to similarity between a first target pixel point in the first pixel point set and a corresponding second target pixel point in the second pixel point set;
the correcting module 330 is configured to determine an image transformation rule according to the position information of a preset number of first feature points in the first feature point set and the position information of a corresponding same number of second feature points in the second feature point set, and correct the position information of all pixel points in the second region of interest according to the image transformation rule to obtain corrected pixel points;
the detection module 340 is configured to determine a difference image according to the corrected pixel points and the corresponding pixel points in the first region of interest, and perform defect detection on the difference image according to a preset defect judgment method.
The technical solution provided in this embodiment is to first obtain a first pixel point set corresponding to a first region of interest of a template image and a second pixel point set corresponding to a second region of interest of an image to be detected, then determine a first feature point set and a second feature point set according to similarity between a first target pixel point in the first pixel point set and a corresponding second target pixel point in the second pixel point set, then determine an image transformation rule according to position information of a preset number of first feature points in the first feature point set and position information of a corresponding same number of second feature points in the second feature point set, correct position information of all pixel points in the second region of interest according to the image transformation rule to obtain corrected pixel points, and finally determine a difference image according to the corrected pixel points and the corresponding pixel points in the first region of interest, and the difference image is subjected to defect detection according to a preset defect judgment method, so that efficient and accurate defect detection can be realized, and the production quality of the die is improved.
Further, the obtaining module 320 may include: the region determining unit is used for determining a first region of interest of the template image and a second region of interest of the image to be detected; and the set determining unit is used for performing noise reduction processing on the pixel points corresponding to the first region of interest to obtain a first pixel point set, and performing noise reduction processing on the pixel points corresponding to the second region of interest to obtain a second pixel point set.
Further, the set determining unit may be specifically configured to: performing boundary expansion on the first region of interest to obtain an expanded first region, and performing boundary expansion on the second region of interest to obtain an expanded second region; and carrying out noise reduction processing on the pixel points in the first region through the self-adaptive median filter to obtain a first pixel point set, and carrying out noise reduction processing on the pixel points in the second region through the self-adaptive median filter to obtain a second pixel point set.
Further, the determining module 320 may be specifically configured to: determining a first to-be-confirmed corner set according to the gradient of each pixel point in the first pixel point set, and determining a first target pixel point set according to a first corner response function of each to-be-confirmed corner in the first to-be-confirmed corner set; determining a second to-be-confirmed corner set according to the gradient of each pixel point in the second pixel point set, and determining a second target pixel point set according to a second corner response function of each to-be-confirmed corner in the second to-be-confirmed corner set; aiming at each first target pixel point in the first target pixel point set, calculating the Hamming distance between the current first target pixel point and a second target pixel point corresponding to the position of the current first target pixel point in the second target pixel point set, determining whether the current first target pixel point and the second target pixel point are feature points or not according to the Hamming distance, if so, storing the current first target pixel point to the first feature point set, and storing the second target pixel point to the second feature point set.
Further, the correction module 330 may be specifically configured to: extracting a preset number of first feature points from the first feature point set, and extracting the same number of second feature points corresponding to the first feature points from the second feature point set to form a preset number of groups of feature points, wherein the preset number is equal to the preset number of groups; determining an image conversion matrix according to the position information of each group of feature points in the feature points with the preset group number; and correcting the position information of all pixel points in the second region of interest according to the image conversion matrix to obtain corrected pixel points.
Further, the detecting module 340 may include: the differential image determining unit is used for subtracting the gray value corresponding to each pixel point in the corrected pixel points from the gray value corresponding to the pixel point in the first interested region to obtain a differential image; the to-be-detected region determining unit is used for judging the differential image through a preset sensitivity threshold value and determining the to-be-detected region of the differential image; and the defect detection unit is used for detecting the defects of the to-be-detected area according to a preset defect judgment method.
Further, the defect detecting unit may be specifically configured to: for each to-be-detected area in the to-be-detected area, if the area of the current to-be-detected area is larger than or equal to a first area threshold value, determining that the defect detection result of the current to-be-detected area does not pass; and when the areas of all the regions to be detected are smaller than the first area threshold value, acquiring the total area of all the regions to be detected, and if the total area is larger than or equal to the second area threshold value, determining that the defect detection result of the regions to be detected does not pass.
The defect detection device for mold monitoring provided by the embodiment can be applied to the defect detection method for mold monitoring provided by any embodiment, and has corresponding functions and beneficial effects.
Example four
Fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention, as shown in fig. 4, the computer device includes a processor 410, a storage device 420, and a communication device 430; the number of the processors 410 in the computer device may be one or more, and one processor 410 is taken as an example in fig. 4; the processor 410, the storage 420 and the communication means 430 in the computer device may be connected by a bus or other means, and fig. 4 illustrates the connection by a bus as an example.
The storage device 420, as a computer-readable storage medium, may be used to store software programs, computer-executable programs, and modules, such as the modules corresponding to the defect detection method for mold monitoring in the embodiment of the present invention (e.g., the acquisition module 310, the determination module 320, the correction module 330, and the detection module 340 in the defect detection device for mold monitoring). The processor 410 executes various functional applications of the computer device and data processing by executing software programs, instructions and modules stored in the storage device 420, that is, implements the defect detection method for mold monitoring described above.
The storage device 420 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the storage 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the storage 420 may further include memory located remotely from the processor 410, which may be connected to a computer device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
And a communication device 430 for implementing a network connection or a mobile data connection between the servers.
The computer device provided by the embodiment can be used for executing the defect detection method for mold monitoring provided by any embodiment, and has corresponding functions and beneficial effects.
EXAMPLE five
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a defect detection method for mold monitoring in any embodiment of the present invention, where the method specifically includes:
acquiring a first pixel point set corresponding to a first interested area of a template image and a second pixel point set corresponding to a second interested area of an image to be detected, wherein the template image is obtained by shooting a mold, and the image to be detected is obtained by shooting a product produced by using the mold;
determining a first characteristic point set and a second characteristic point set according to the similarity between a first target pixel point in the first pixel point set and a corresponding second target pixel point in the second pixel point set;
determining an image transformation rule according to the position information of a preset number of first feature points in the first feature point set and the position information of a corresponding same number of second feature points in the second feature point set, and correcting the position information of all pixel points in the second region of interest according to the image transformation rule to obtain corrected pixel points;
and determining a difference image according to the corrected pixel points and the corresponding pixel points in the first region of interest, and performing defect detection on the difference image according to a preset defect judgment method.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the defect detection method for mold monitoring provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the defect detecting apparatus for mold monitoring, the included units and modules are only divided according to the functional logic, but are not limited to the above division as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method of defect detection for mold monitoring, comprising:
acquiring a first pixel point set corresponding to a first interested area of a template image and a second pixel point set corresponding to a second interested area of an image to be detected, wherein the template image is obtained by shooting a mold, and the image to be detected is obtained by shooting a product produced by using the mold;
determining a first characteristic point set and a second characteristic point set according to the similarity between a first target pixel point in the first pixel point set and a corresponding second target pixel point in the second pixel point set;
determining an image transformation rule according to the position information of a preset number of first feature points in the first feature point set and the position information of a corresponding same number of second feature points in the second feature point set, and correcting the position information of all pixel points in the second region of interest according to the image transformation rule to obtain corrected pixel points;
and determining a difference image according to the corrected pixel points and the corresponding pixel points in the first region of interest, and performing defect detection on the difference image according to a preset defect judgment method.
2. The method of claim 1, wherein the obtaining a first set of pixel points corresponding to a first region of interest of the template image and a second set of pixel points corresponding to a second region of interest of the image to be detected comprises:
determining a first region of interest of the template image and a second region of interest of the image to be detected;
and performing noise reduction processing on the pixel points corresponding to the first region of interest to obtain a first pixel point set, and performing noise reduction processing on the pixel points corresponding to the second region of interest to obtain a second pixel point set.
3. The method according to claim 2, wherein the performing noise reduction processing on the pixel point corresponding to the first region of interest to obtain a first pixel point set, and performing noise reduction processing on the pixel point corresponding to the second region of interest to obtain a second pixel point set comprises:
performing boundary expansion on the first region of interest to obtain an expanded first region, and performing boundary expansion on the second region of interest to obtain an expanded second region;
and carrying out noise reduction processing on the pixel points in the first region through a self-adaptive median filter to obtain a first pixel point set, and carrying out noise reduction processing on the pixel points in the second region through the self-adaptive median filter to obtain a second pixel point set.
4. The method of claim 1, wherein determining a first feature point set and a second feature point set according to a similarity between a first target pixel point in the first pixel point set and a corresponding second target pixel point in the second pixel point set comprises:
determining a first to-be-confirmed corner set according to the gradient of each pixel point in the first pixel point set, and determining a first target pixel point set according to a first corner response function of each to-be-confirmed corner in the first to-be-confirmed corner set;
determining a second to-be-confirmed corner set according to the gradient of each pixel point in the second pixel point set, and determining a second target pixel point set according to a second corner response function of each to-be-confirmed corner in the second to-be-confirmed corner set;
and aiming at each first target pixel point in the first target pixel point set, calculating the Hamming distance between the current first target pixel point and a second target pixel point corresponding to the position of the current first target pixel point in the second target pixel point set, determining whether the current first target pixel point and the second target pixel point are feature points or not according to the Hamming distance, if so, storing the current first target pixel point to the first feature point set, and storing the second target pixel point to the second feature point set.
5. The method according to claim 1, wherein the determining an image transformation rule according to the position information of a preset number of first feature points in the first feature point set and the position information of a corresponding same number of second feature points in the second feature point set, and performing position information correction on all pixel points in the second region of interest according to the image transformation rule to obtain corrected pixel points comprises:
extracting a preset number of first feature points from the first feature point set, and extracting the same number of second feature points corresponding to the first feature points from the second feature point set to form a preset number of groups of feature points, wherein the preset number is equal to the preset number of groups;
determining an image conversion matrix according to the position information of each group of feature points in the feature points with the preset group number;
and correcting the position information of all pixel points in the second interested region according to the image conversion matrix to obtain corrected pixel points.
6. The method according to claim 1, wherein the determining a difference image according to the corrected pixel point and the corresponding pixel point in the first region of interest, and performing defect detection on the difference image according to a preset defect judgment method comprises:
subtracting the gray value corresponding to each pixel point in the corrected pixel points from the gray value corresponding to the pixel point in the first interested region to obtain a difference image;
judging the differential image through a preset sensitivity threshold value, and determining a to-be-detected region of the differential image;
and detecting the defects of the area to be detected according to a preset defect judgment method.
7. The method according to claim 6, wherein the performing defect detection on the region to be detected according to a preset defect judgment method comprises:
for each to-be-detected area in the to-be-detected areas, if the area of the current to-be-detected area is larger than or equal to a first area threshold value, determining that the defect detection result of the current to-be-detected area does not pass;
and when the areas of all the regions to be detected are smaller than the first area threshold value, acquiring the total area of all the regions to be detected, and if the total area is larger than or equal to a second area threshold value, determining that the defect detection result of the regions to be detected does not pass.
8. A defect detection apparatus for mold monitoring, comprising:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a first pixel point set corresponding to a first interested area of a template image and a second pixel point set corresponding to a second interested area of an image to be detected, the template image is obtained by shooting a mold, and the image to be detected is obtained by shooting a product produced by using the mold;
the determining module is used for determining a first characteristic point set and a second characteristic point set according to the similarity between a first target pixel point in the first pixel point set and a corresponding second target pixel point in the second pixel point set;
the correction module is used for determining an image transformation rule according to the position information of a preset number of first feature points in the first feature point set and the position information of a corresponding same number of second feature points in the second feature point set, and correcting the position information of all pixel points in the second region of interest according to the image transformation rule to obtain corrected pixel points;
and the detection module is used for determining a difference image according to the corrected pixel points and the corresponding pixel points in the first region of interest and detecting the defects of the difference image according to a preset defect judgment method.
9. A computer device, characterized in that the computer device comprises:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the defect detection method for mold monitoring of any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method for defect detection for mold monitoring according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110181174.2A CN112837303A (en) | 2021-02-09 | 2021-02-09 | Defect detection method, device, equipment and medium for mold monitoring |
| PCT/CN2021/098423 WO2022170706A1 (en) | 2021-02-09 | 2021-06-04 | Defect detection method and apparatus for mold monitoring, and device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110181174.2A CN112837303A (en) | 2021-02-09 | 2021-02-09 | Defect detection method, device, equipment and medium for mold monitoring |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112837303A true CN112837303A (en) | 2021-05-25 |
Family
ID=75933294
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110181174.2A Pending CN112837303A (en) | 2021-02-09 | 2021-02-09 | Defect detection method, device, equipment and medium for mold monitoring |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112837303A (en) |
| WO (1) | WO2022170706A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114155367A (en) * | 2022-02-09 | 2022-03-08 | 北京阿丘科技有限公司 | Method, device and equipment for detecting defects of printed circuit board and storage medium |
| WO2022170706A1 (en) * | 2021-02-09 | 2022-08-18 | 广东拓斯达科技股份有限公司 | Defect detection method and apparatus for mold monitoring, and device and medium |
| CN115063613A (en) * | 2022-08-09 | 2022-09-16 | 海纳云物联科技有限公司 | Method and device for verifying commodity label |
| CN116453029A (en) * | 2023-06-16 | 2023-07-18 | 济南东庆软件技术有限公司 | Building fire environment detection method based on image data |
| CN117058141A (en) * | 2023-10-11 | 2023-11-14 | 福建钜鸿百纳科技有限公司 | Glass edging defect detection method and terminal |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115294410B (en) * | 2022-10-08 | 2023-10-17 | 加乐新材料(南通)有限公司 | Plastic product molding control method based on pattern recognition |
| CN115496762B (en) * | 2022-11-21 | 2023-01-24 | 深圳市富安娜家居用品股份有限公司 | Textile technology-based dyeing defect identification method |
| CN115690102B (en) * | 2022-12-29 | 2023-04-18 | 摩尔线程智能科技(北京)有限责任公司 | Defect detection method, defect detection apparatus, electronic device, storage medium, and program product |
| CN115880302B (en) * | 2023-03-08 | 2023-05-23 | 杭州智源电子有限公司 | Method for detecting welding quality of instrument panel based on image analysis |
| CN116363136B (en) * | 2023-06-01 | 2023-08-11 | 山东创元智能设备制造有限责任公司 | On-line screening method and system for automatic production of motor vehicle parts |
| CN116402815B (en) * | 2023-06-08 | 2023-08-22 | 岑科科技(深圳)集团有限公司 | Artificial intelligence-based induction coil packaging abnormality detection method |
| CN116682107B (en) * | 2023-08-03 | 2023-10-10 | 山东国宏生物科技有限公司 | Soybean visual detection method based on image processing |
| CN117095003B (en) * | 2023-10-20 | 2024-01-26 | 山东亿盟源新材料科技有限公司 | Method and device for detecting cleanliness of carbon steel raw materials of bimetal composite plate |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106803244A (en) * | 2016-11-24 | 2017-06-06 | 深圳市华汉伟业科技有限公司 | Defect identification method and system |
| CN110503633A (en) * | 2019-07-29 | 2019-11-26 | 西安理工大学 | A kind of applique ceramic disk detection method of surface flaw based on image difference |
| CN111028213A (en) * | 2019-12-04 | 2020-04-17 | 北大方正集团有限公司 | Image defect detection method and device, electronic equipment and storage medium |
| CN111583211A (en) * | 2020-04-29 | 2020-08-25 | 广东利元亨智能装备股份有限公司 | Defect detection method and device and electronic equipment |
| CN111986190A (en) * | 2020-08-28 | 2020-11-24 | 哈尔滨工业大学（深圳） | Printed matter defect detection method and device based on artifact elimination |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108288274B (en) * | 2018-02-24 | 2021-01-12 | 北京理工大学 | Mold detection method and device and electronic equipment |
| CN112837303A (en) * | 2021-02-09 | 2021-05-25 | 广东拓斯达科技股份有限公司 | Defect detection method, device, equipment and medium for mold monitoring |
-
2021
- 2021-02-09 CN CN202110181174.2A patent/CN112837303A/en active Pending
- 2021-06-04 WO PCT/CN2021/098423 patent/WO2022170706A1/en unknown
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106803244A (en) * | 2016-11-24 | 2017-06-06 | 深圳市华汉伟业科技有限公司 | Defect identification method and system |
| CN110503633A (en) * | 2019-07-29 | 2019-11-26 | 西安理工大学 | A kind of applique ceramic disk detection method of surface flaw based on image difference |
| CN111028213A (en) * | 2019-12-04 | 2020-04-17 | 北大方正集团有限公司 | Image defect detection method and device, electronic equipment and storage medium |
| CN111583211A (en) * | 2020-04-29 | 2020-08-25 | 广东利元亨智能装备股份有限公司 | Defect detection method and device and electronic equipment |
| CN111986190A (en) * | 2020-08-28 | 2020-11-24 | 哈尔滨工业大学（深圳） | Printed matter defect detection method and device based on artifact elimination |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022170706A1 (en) * | 2021-02-09 | 2022-08-18 | 广东拓斯达科技股份有限公司 | Defect detection method and apparatus for mold monitoring, and device and medium |
| CN114155367A (en) * | 2022-02-09 | 2022-03-08 | 北京阿丘科技有限公司 | Method, device and equipment for detecting defects of printed circuit board and storage medium |
| CN114155367B (en) * | 2022-02-09 | 2022-05-13 | 北京阿丘科技有限公司 | Method, device and equipment for detecting defects of printed circuit board and storage medium |
| CN115063613A (en) * | 2022-08-09 | 2022-09-16 | 海纳云物联科技有限公司 | Method and device for verifying commodity label |
| CN116453029A (en) * | 2023-06-16 | 2023-07-18 | 济南东庆软件技术有限公司 | Building fire environment detection method based on image data |
| CN116453029B (en) * | 2023-06-16 | 2023-08-29 | 济南东庆软件技术有限公司 | Building fire environment detection method based on image data |
| CN117058141A (en) * | 2023-10-11 | 2023-11-14 | 福建钜鸿百纳科技有限公司 | Glass edging defect detection method and terminal |
| CN117058141B (en) * | 2023-10-11 | 2024-03-01 | 福建钜鸿百纳科技有限公司 | Glass edging defect detection method and terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022170706A1 (en) | 2022-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112837303A (en) | Defect detection method, device, equipment and medium for mold monitoring | |
| CN107688829A (en) | A kind of identifying system and recognition methods based on SVMs | |
| CN112419297A (en) | Bolt looseness detection method, device, equipment and storage medium | |
| CN110909712B (en) | Moving object detection method and device, electronic equipment and storage medium | |
| CN109934262B (en) | Picture variability judging method, device, computer equipment and storage medium | |
| CN111739020B (en) | Automatic labeling method, device, equipment and medium for periodic texture background defect label | |
| CN112734654B (en) | Image processing method, device, equipment and storage medium | |
| CN111178193A (en) | Lane line detection method, lane line detection device and computer-readable storage medium | |
| CN113888461A (en) | Method, system and equipment for detecting defects of hardware parts based on deep learning | |
| WO2017113692A1 (en) | Method and device for image matching | |
| Pok et al. | Efficient block matching for removing impulse noise | |
| CN114972339B (en) | Data enhancement system for bulldozer structural member production abnormity detection | |
| CN113192059A (en) | On-orbit ship detection method based on infrared remote sensing image | |
| CN110365404B (en) | Wavefront-free sensing self-adaptive system and method for improving convergence speed by using same | |
| CN113362238A (en) | Test image processing method and device, electronic equipment and storage medium | |
| US9286217B2 (en) | Systems and methods for memory utilization for object detection | |
| CN111445487A (en) | Image segmentation method and device, computer equipment and storage medium | |
| CN114359665A (en) | Training method and device of full-task face recognition model and face recognition method | |
| CN117372487A (en) | Image registration method, device, computer equipment and storage medium | |
| CN111242051A (en) | Vehicle identification optimization method and device and storage medium | |
| CN113643290B (en) | Straw counting method and device based on image processing and storage medium | |
| CN110264488B (en) | Binary image edge extraction device | |
| CN112861874B (en) | Expert field denoising method and system based on multi-filter denoising result | |
| CN114339395A (en) | Video jitter detection method, detection device, electronic equipment and readable storage medium | |
| Okarma et al. | A fast image analysis technique for the line tracking robots |
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 |