CN113554582B - Defect detection method, device and system for functional hole in electronic equipment cover plate - Google Patents
Defect detection method, device and system for functional hole in electronic equipment cover plate Download PDFInfo
- Publication number
- CN113554582B CN113554582B CN202010322419.4A CN202010322419A CN113554582B CN 113554582 B CN113554582 B CN 113554582B CN 202010322419 A CN202010322419 A CN 202010322419A CN 113554582 B CN113554582 B CN 113554582B
- Authority
- CN
- China
- Prior art keywords
- line
- functional hole
- contour
- cover plate
- fitting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06T7/0006—Industrial image inspection using a design-rule based approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06T2207/20004—Adaptive image processing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a defect detection method of a functional hole on a cover plate of electronic equipment, which comprises the steps of scanning and collecting a cover plate image to obtain a binary image; extracting pixel points of the functional hole outline in the binary image; and fitting the pixel points on the functional hole outline according to a preset line segment to obtain an outline fit line, judging whether the difference value of the pixel coordinates of the non-coincident part of the functional hole outline and the outline fit line is greater than a preset difference value, and if so, taking the non-coincident part of the functional hole outline and the outline fit line as the position of the functional hole of the cover plate with the defect. The contour pixel points of the functional holes in the binary image of the cover plate are fitted, whether the functional holes have defects or not is determined according to the coincidence condition of the contour lines of the cover plate and the pixel points of the contour fitting line, the precision of detecting the defects of the functional holes is improved, and the quality of electronic equipment is further improved. The application also provides a defect detection device and system for the functional hole in the cover plate of the electronic equipment, and the defect detection device and system have the beneficial effects.
Description
Technical Field
The invention relates to the technical field of electronic product quality detection, in particular to a method, a device and a system for detecting defects of functional holes in a cover plate of electronic equipment.
Background
With the rapid development of electronic technology, electronic products such as smart phones, tablet computers, watch phones and the like become portable mobile devices essential for people to live and work. Generally, a voice function, a camera function, and the like need to be configured on most electronic products, and accordingly, various functional holes such as a sound hole, a camera hole, and even a key hole are configured on a cover plate of the electronic device in a matching manner to accommodate corresponding functional components.
In the actual production process, the functional holes on the cover plate are inevitably defective in the actual application due to the process limitation. For example, for a glass cover plate of a mobile phone, the edge breakage of a sound hole is one of the longest defects. At present, the edge breakage detection of sound holes or similar functional holes is mainly based on artificial naked eye detection, and because the degree of edge breakage is not obvious, illumination angles need to be changed continuously by workers, observation is carried out from different directions, and meanwhile, black bottom materials are used as auxiliary detection tools. The manual detection method is long in time consumption, and due to long-time work, the vision can generate fatigue, so that the defect omission phenomenon is caused. Meanwhile, manual detection consumes a large amount of human resources.
Disclosure of Invention
The invention aims to provide a method, a device and a system for detecting defects of functional holes in a cover plate of electronic equipment, which improve the accuracy of detecting the defects of the functional holes in the cover plate of the electronic equipment.
In order to solve the above technical problem, the present invention provides a method for detecting a defect of a functional hole on a cover plate of an electronic device, comprising:
scanning and collecting a cover plate image, and carrying out binarization processing on the cover plate image to obtain a binarization image;
positioning a functional hole image area in the binary image;
extracting pixel points of the functional hole outline in the functional hole image area to obtain a functional hole outline;
fitting pixel points on the functional hole outline according to a preset line segment to obtain an outline fitting line, wherein the preset line segment is a line segment which is set according to the shape of the functional hole of the cover plate and can be spliced to form the outline shape of the functional hole;
and judging whether the difference value of the pixel coordinates of the non-coincident part of the functional hole outline and the outline fit line is larger than a preset difference value, if so, determining that the non-coincident part of the functional hole outline and the outline fit line is the position of the functional hole of the cover plate with defects.
Optionally, locating a functional pore image region in the binarized image comprises:
and positioning a functional hole image area in the binary image according to the model of the cover plate.
Optionally, the binarizing processing on the cover plate image includes:
and carrying out binarization processing on the cover plate image by using a self-adaptive binarization algorithm.
Optionally, fitting the pixel points on the functional hole contour line according to a predetermined line segment to obtain a contour fit line, including:
obtaining a symmetry axis linear equation of the functional hole outline according to the coordinate value of each pixel point on the functional hole outline and a symmetry axis formula;
determining intersection point pixel points of the functional hole contour line and the main symmetry axis linear equation according to the symmetry axis linear equation;
and selecting coordinate values of a plurality of pixel points on the functional hole contour line by taking the intersection point pixel points as a reference, and fitting according to the preset line segment to obtain a contour fitting line.
Optionally, the preset line segment includes at least two line segments;
and selecting coordinate values of a plurality of pixel points on the functional hole contour line by taking the intersection point pixel points as a reference, and fitting according to the preset line segment to obtain a contour fitting line, wherein the contour fitting line comprises:
selecting coordinate values of a plurality of pixel points within a preset distance range of the reference point on the functional hole contour line by taking the intersection point pixel points as the reference points, and fitting according to a line segment formula which is satisfied by the preset line segment at the reference point position to obtain a curve formula which is satisfied by a sub-contour fitting line;
judging whether the difference value of the pixel coordinates of the non-coincident part of the functional hole contour line and the contour fitting line is larger than a preset difference value or not comprises the following steps:
detecting the distance between pixel points on the functional hole contour line and the sub-contour fitting line one by taking the reference point as a starting point;
when the distance from a continuous preset number of pixel points to the pixel coordinate of the sub-contour fitting line on the functional hole contour line is larger than a preset difference value, taking the first pixel point with the distance from the sub-contour fitting line to the sub-contour fitting line larger than the preset distance threshold value as the endpoint of the sub-contour fitting line;
taking the end point of the sub-contour fit line as a new reference point, and repeatedly executing the operation of selecting the coordinate values of a plurality of pixel points in the preset distance range of the reference point on the functional hole contour line to obtain a new sub-contour fit line;
and if the end point of the sub-contour fitting line is taken as a new reference point and cannot be fitted according to the preset line segment, the end point position of the sub-contour fitting line is the position of the functional hole of the cover plate with defects.
Optionally, after the pixel point whose first distance from the sub-contour fitting line is greater than the preset distance threshold is taken as the endpoint of the sub-contour fitting line, the method further includes:
judging whether the length of a line segment between the reference point and the end point of the sub-contour fit line is within a preset length range, if not, the end point position of the sub-contour fit line is the position of the functional hole of the cover plate with defects; if so, the operation of taking the end point of the sub-contour fitting line as a new reference point is carried out.
Optionally, fitting the pixel points on the functional hole contour line according to a predetermined line segment to obtain a contour fit line, including:
fitting the pixel points on the inner contour line of the functional hole and the pixel points on the outer contour line of the functional hole according to preset line segments respectively to obtain an inner contour fitting line and an outer contour fitting line;
judging whether the difference value of the pixel coordinates of the non-coincident part of the functional hole contour line and the contour fitting line is larger than a preset difference value or not, wherein the judging step comprises the following steps:
and judging whether the pixel coordinate difference of the non-coincident part of the functional hole inner contour line and the inner contour fit line and/or the pixel coordinate difference of the non-coincident part of the functional hole outer contour line and the outer contour fit line is larger than the preset difference or not.
The application also provides a defect detection device of functional hole on electronic equipment apron, includes:
the image acquisition module is used for scanning and acquiring a cover plate image and carrying out binarization processing on the cover plate image to obtain a binarization image;
the area positioning module is used for positioning a functional hole image area in the binary image;
the contour line extraction module is used for extracting pixel points of the functional hole contour in the functional hole image area to obtain a functional hole contour line;
the contour fitting module is used for fitting the pixel points on the contour line of the functional hole according to a preset line segment to obtain a contour fitting line, wherein the preset line segment is a line segment set according to the shape of the functional hole of the cover plate;
and the defect judging module is used for judging whether the difference value of the pixel coordinates of the non-coincident part of the functional hole contour line and the contour fit line is greater than a preset difference value, if so, the non-coincident part of the functional hole contour line and the contour fit line is the position of the functional hole of the cover plate with defects.
The application also provides a defect detection system of the functional hole on the cover plate of the electronic equipment, which comprises a camera, a processor and a memory;
wherein the memory is for storing a computer program;
the camera is used for shooting and collecting the cover plate image;
the processor is configured to execute the computer program according to the cover plate image to implement the operation steps of the method for detecting defects of functional holes on a cover plate of an electronic device as described in any one of the above.
Optionally, the light source is used for providing illumination for the cover plate; the camera is a line array camera.
The invention provides a defect detection method of a functional hole on a cover plate of electronic equipment, which comprises the steps of scanning and collecting a cover plate image, and carrying out binarization processing on the cover plate image to obtain a binarization image; positioning a functional hole image area in the binary image; extracting pixel points of the functional hole outline in the functional hole image area to obtain a functional hole outline; fitting the pixel points on the functional hole outline according to a preset line segment to obtain an outline fitting line, wherein the preset line segment is a line segment which is set according to the shape of the functional hole of the cover plate and can be spliced to form the outline shape of the functional hole; and judging whether the difference value of the pixel coordinates of the non-coincident part of the functional hole outline and the outline fit line is larger than a preset difference value, if so, taking the non-coincident part of the functional hole outline and the outline fit line as the position of the functional hole of the cover plate with the defect.
When the defects of the functional holes in the cover plate are detected, the preset line segments capable of being spliced to form the outline shape of the functional holes are preset, the outline pixel points of the functional holes in the binary image of the cover plate are fitted according to the preset line segments, an outline fit line is obtained, under normal conditions, the outline of the cover plate and the outline fit line are approximately coincided, and if the misaligned line segments exist and the distance of the misaligned part is too large, the cover plate is indicated to have the defects. Therefore, when the defect of the functional hole in the cover plate is judged, the pixel point level is carefully reached, even if the functional hole has a tiny defect, the functional hole can be identified, the defect detection precision of the functional hole is improved, and the quality of the electronic equipment is improved.
The application also provides a defect detection device and system of the functional hole on the cover plate of the electronic equipment, and the defect detection device and system have the beneficial effects.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the embodiments or technical solutions of the present invention will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a method for detecting defects of a functional hole in a cover plate of an electronic device according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart illustrating a method for detecting defects of a functional hole on a cover plate of an electronic device according to another embodiment of the present disclosure;
FIG. 3 is a schematic view of a functional hole provided by an embodiment of the present application;
FIG. 4 is a schematic view of a defective functional hole provided in an embodiment of the present application;
fig. 5 is a schematic flowchart illustrating a method for detecting defects of a functional hole on a cover plate of an electronic device according to another embodiment of the present disclosure;
fig. 6 is a block diagram of a defect detection apparatus for a functional hole on a cover plate of an electronic device according to an embodiment of the present invention.
Detailed Description
In the conventional technology for detecting defects such as crack gaps of components by using an image recognition mode, repeated feature learning is performed on a large number of samples with defects and samples without defects based on neural network training, and finally a recognition defect feature model is formed and used for detecting the defects in the images of the components. However, the detection method is more suitable for parts with larger defect gaps, and if the gaps of the gaps are smaller, the gaps can be easily ignored as noise in the actual identification process.
Therefore, the technical scheme for detecting the defects of the functional holes in the cover plate of the electronic equipment is provided, the defects of the functional holes in the cover plate can be detected accurately to the pixel point level, the detection of the small gap defects is facilitated, and the detection accuracy is improved.
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, fig. 1 is a schematic flowchart of a method for detecting defects of a functional hole on a cover plate of an electronic device according to an embodiment of the present application, where the method may include:
s11: and scanning and collecting a cover plate image, and performing binarization processing on the cover plate image to obtain a binarization image.
Specifically, the cover in the present application may be, but is not limited to, a mobile phone cover, a Pad cover, a notebook cover, and the like.
The functional holes on the cover plate may be various through holes, such as a sound hole configured for a microphone of the electronic device, a key hole reserved for a key of the electronic device, a camera hole reserved for a camera, and an earphone hole reserved for an earphone, which are not listed herein.
The cover plate image is subjected to binarization processing, namely, the photographed cover plate image is subjected to gray processing firstly, and a binarized image is finally obtained according to the comparison between the gray value size and the gray threshold value of each pixel point.
It should be noted that, in the process of cover plate imaging, the light brightness is difficult to ensure complete uniformity and consistency, so that the uniform threshold value cannot be used to binarize the cover plate image. Therefore, in an optional embodiment of the present application, an adaptive binarization algorithm may be adopted to analyze the acquired cover plate image. Specifically, firstly, the pixel value of each pixel point of the cover plate image is traversed, the difference value between the pixel value of the current pixel point and the pixel mean value of the neighborhood pixel point is calculated, and if the difference value is larger than a preset pixel difference value threshold value, the pixel point is regarded as a foreground point but not a background point.
S12: and positioning a functional hole image area in the binary image.
For the cover plate with the determined model, the position of the functional hole in the image is determined, so that the approximate region position of the functional hole in the binary image can be determined based on the position in practical application, and therefore the region image can be divided and independently used for defect judgment, and the interference of irrelevant factors is reduced.
S13: and extracting pixel points of the functional hole outline in the functional hole image area to obtain a functional hole outline.
S14: and fitting the pixel points on the functional hole contour line according to a preset line segment to obtain a contour fit line.
The preset line segment is a line segment which is set according to the shape of the functional hole of the cover plate and can be spliced to form the outline shape of the functional hole.
Specifically, the functional holes in the cover plate are generally designed according to a specific shape, and the contour lines of the functional holes can generally satisfy a certain curve. For example, for a circular functional hole, according to coordinate values of a plurality of contour pixel points, fitting a circular curve function of a contour fitting line representing a contour line of the functional hole; for the square functional hole, the functional hole can be formed by splicing four straight line segments, and four straight line segment functions representing a fitting contour line can be obtained through fitting.
S15: and judging whether the difference value of the pixel coordinates of the non-coincident part of the functional hole outline and the outline fitting line is larger than a preset difference value, if so, determining that the functional hole has defects, and if not, determining that the functional hole does not have defects.
Under normal conditions, if the functional hole has no defects, the outline fitting line coincidence is obtained by approximating and fitting each pixel point on the outline of the functional hole, namely the distance from each pixel point to the outline fitting line is small. For the functional hole with defects, it is obvious that the distance from the pixel point of the defect position to the contour fitting line is relatively large. Therefore, the functional hole can be determined whether to have defects or not based on the judgment of the pixel point coordinate values on the functional hole contour line by taking the position as the basis.
When carrying out the defect detection to the functional hole on the apron in this application, be based on in the apron image, the profile pixel point coordinate of functional hole is judged, that is to say that can be accurate to the pixel rank to the defect detection of functional hole in this application, this has promoted the degree of accuracy to functional hole defect detection at to a great extent, also can accurate discernment to tiny crack defect, improves the reliability that the apron functional hole detected at to a great extent, guarantees the product quality of apron.
In another optional embodiment of the present application, as shown in fig. 2, fig. 2 is a schematic flowchart of a defect detection method for a functional hole on an electronic device cover plate according to another embodiment of the present application. The method can comprise the following steps:
s21: and acquiring a cover plate image, carrying out binarization processing on the cover plate image to obtain a binarized image, positioning a functional hole image area in the binarized image, and extracting pixel points of the functional hole outline in the functional hole image area to obtain a functional hole outline.
S22: and obtaining a main symmetry axis linear equation of the functional hole outline according to the coordinate value of each pixel point on the functional hole outline and a main symmetry axis formula.
Specifically, the barycentric coordinates of each pixel point on the functional hole contour line are set as follows: o (x) c ,y c ) And the coordinates of each pixel point are as follows: i (x, y), then, the barycentric coordinates are obtained according to the barycentric formula:
based on the formula satisfied by the barycentric coordinates and the symmetry axis direction angle θ:
from this, it can be further determined that the satisfied linear equation of the main symmetry axis is:
(y-y c )=tan(θ)(x-x c )。
the equation for the symmetry axis perpendicular to the main symmetry axis is: (x-x) c )=-tan(θ)(y-y c )。
S23: and determining intersection point pixel points of the functional hole contour line and the symmetry axis linear equation according to the symmetry axis linear equation, and taking the intersection point pixel points as reference points.
And determining a linear equation which is satisfied by the symmetry axis of the functional hole contour line and the functional hole contour line, namely determining an intersection point pixel point between the functional contour line and the symmetry axis.
S24: and selecting coordinate values of a plurality of pixel points within a preset distance range of the datum point on the functional hole contour line, and fitting according to a line segment formula which is satisfied by a preset line segment at the datum point.
It should be noted that, in the present application, a pixel point at an intersection of the functional contour line and the symmetry axis is to be obtained, that is, a reference point is provided for line segment fitting of the functional hole contour.
Since the position of the symmetry point is determined for a certain functional hole, the curve equation that the symmetry point and its peripheral position point satisfy is also determined.
Specifically, as shown in fig. 3, fig. 3 is a schematic diagram of a functional hole provided in this application according to an embodiment, and for the functional hole shown in fig. 3, an intersection point symmetry point includes a pixel point a and a pixel point B.
When contour line fitting is carried out, one of the pixel points A or the pixel points B can be selected as a reference point for fitting, if the pixel points A are used as the reference points, a plurality of pixel points around the pixel points A can be selected for straight line fitting, and the pixel points B are selected as the reference points, a plurality of pixel points around the pixel points B can be selected for circular curve fitting.
Of course, in practical applications, it is not excluded to use other ways of determining the reference point, as long as it is ensured that when the line segment fitting is performed, a correct preset line segment can be found for fitting.
S25: and when the plurality of selected pixel points cannot be fitted according to the preset line segment, determining that the functional hole has defects.
S26: and when a curve formula which is satisfied by the sub-contour fitting line can be obtained through fitting based on the selected multiple pixel points, the distance between the pixel points on the functional hole contour line and the sub-contour fitting line is detected one by taking the reference point as a starting point.
S27: and when the pixel coordinate distance from a continuous preset number of pixel points to the sub-contour fitting line on the functional hole contour line is larger than a preset difference value, taking the pixel point with the first distance from the sub-contour fitting line and the distance larger than a preset distance threshold value as the end point of the sub-contour fitting line.
As shown in fig. 3, for a functional via similar to that shown in fig. 3, the entire via profile is stitched from a variety of different line segments. For example, for line segment CD being a straight line segment, curve segment EF being a circular curve segment, and curve segment EC being a curve segment with varying curvature.
Therefore, for the functional hole shown in fig. 3, when contour line fitting is performed, if the pixel point a is used as a starting point, a linear equation of the fitting straight line MN can be obtained first, and then the distance from each pixel point to the fitting straight line MN is calculated one by one in the AD direction and the AC direction by using the pixel point a as the starting pixel point. Obviously, the distance between the pixel point C and the pixel point E and the fitting straight line MN is gradually increased, that is, the pixel point behind the pixel point C is not positioned on the fitting straight line MN, so that the pixel point C can be determined as an end point of a fitting contour line CD, the pixel point D can be determined as another end point of the contour fitting line CD in the same way, and the fitting contour line CD meets the straight line equation of the fitting straight line MN.
S28: and judging whether the obtained sub-contour fit lines are connected end to form a closed contour fit line, if so, determining that the functional hole has no defect, and if not, entering S29.
S29: and taking the end point of the newly obtained sub-contour fitting line as a new reference point, and entering S24.
As shown in fig. 4, fig. 4 is a schematic diagram of a defective functional hole provided in an embodiment of the present application. In fig. 4, a defect exists between the pixel point G and the pixel point H, and then a plurality of pixel points are inevitably larger than the fitting straight line MN between the pixel point G and the pixel point H, and at this time, the pixel point G may be considered as an end point of a fitting contour line.
Then, the pixel point G can be corrected as a new reference point, and a pixel point between the pixel point G and the pixel point H can be selected for fitting, under a normal condition, fitting should be performed according to a curve segment that is satisfied by the curve CE at this time, and it is obvious that the pixel point between the pixel point G and the pixel point H does not meet the fitting requirement, so when the above step S24 is executed again after the pixel point G is used as a new reference point, the condition that fitting is impossible in S25 exists, and thus it can be judged that the pixel point after the pixel point G is a defective pixel point.
Similarly, when a defect exists near the pixel point a at the intersection point of the symmetry axis and the functional hole contour line, the defect can not be immediately judged by fitting the pixel point a into a straight line MN.
Of course, the length of each contour line in the binarized image should be within a certain range, and after determining the end point by the distance between each pixel point and the fitted contour line, for example, when the pixel point G in fig. 4 is determined as one end point, it can be determined whether the length of the line segment AG is within the preset length range, obviously, as shown in fig. 4, it can be determined that the length of the AG is smaller, and therefore, it can be rapidly determined that a defect exists near the pixel point G.
In addition, the defect is also possibly caused to be positioned near the point C of the pixel point, at the moment, whether the defect point is a defect point is difficult to distinguish by judging the length from the end point to the reference point, at the moment, curve fitting is carried out on the pixel point passing through the end point, and whether the defect exists can also be judged.
Based on the steps, the functional hole contour line can be fitted section by section, and if the whole functional hole has no defects, a closed contour fitting line can be obtained inevitably.
In another optional embodiment of the present application, as shown in fig. 5, fig. 5 is a schematic flowchart of a defect detection method for a functional hole on an electronic device cover plate according to another embodiment of the present application. The method can comprise the following steps:
s31: and obtaining a cover plate image, carrying out binarization processing on the cover plate image to obtain a binarized image, positioning a functional hole image area in the binarized image, and extracting pixel points of the functional hole outline in the functional hole image area to obtain a functional hole outline.
S32: and obtaining a symmetry axis linear equation of the functional hole outline according to the coordinate value of each pixel point on the functional hole outline and a symmetry axis formula.
S33: and determining intersection point pixel points of the functional hole contour line and the main symmetry axis linear equation according to the symmetry axis linear equation.
S34: and selecting coordinate values of a plurality of pixel points on the functional hole contour line by taking the intersection point pixel points as a reference, and fitting according to a preset line segment to obtain a contour fitting line.
S35: and calculating to obtain the distance from each pixel point on the functional contour line to the contour fitting line.
S36: and judging whether the distance from the continuous preset number of pixel points to the contour fitting line is greater than the preset distance on the functional contour line, if so, determining that the functional hole has defects, and if not, determining that the functional hole does not have defects.
When the contour fitting is carried out on the pixel points on the contour line of the functional hole, the contour line of the whole functional hole can be directly fitted firstly.
For example, for a contour line, such as a circle, which can be represented by only one function, the center of gravity of the functional hole is determined, i.e., the center of the circle of the contour fit line is determined. And determining a curve equation of a circular contour fit line through four intersection point pixel points generated by two symmetrical axis straight lines and the functional hole contour line, and judging defects of all the pixel points on the functional hole contour line.
Of course, for a functional hole of the shape shown in fig. 3, a contour fit line can also be obtained in a similar manner. After determining the center of gravity, the symmetry line, and the intersection point pixel points of the functional hole contour line shown in fig. 3, it is equivalent to determining the orientation of the functional hole contour line. For example, for a straight-line equation satisfied by the line segment CD, it is obvious that the straight-line equation can be determined by fitting coordinate values of a plurality of pixel points centered on the point a; for the curve equation satisfied by the curve segment EF, obviously, the coordinate value of a plurality of pixel points taking the point B as the center can be fitted and determined; although there is no intersection point between the curve segment CE and the symmetry axis, the length of the line segment CD and the central angle of the curve segment EF can be roughly determined based on the shape of the designed functional hole, so that the general positions of the end points C and E can be roughly determined, and the coordinate values of a plurality of pixel points between the end points C and E can be selected to perform fitting of the curve segment CE, and then the end points between the end line segments can be determined according to the intersection points of the fitted curve, the curve segment EF and the fitted curve of the line segment CD. Similarly, the contour fitting line of the whole functional hole can be realized according to a similar mode.
It should be noted that, for the conventional electronic device at present, the shape and the circle of the functional hole on the cover plate are mainly the shape and the circle of the functional hole shown in fig. 3, but it is not excluded that functional holes with other shapes may exist. Aiming at functional holes with different shapes, the positions of the functional holes in the binary image can be positioned in a targeted manner according to the specific shapes of the functional holes, reference points are selected, and then a plurality of pixel points are fitted according to preset line segments, so that the contour line of the whole functional hole can be fitted. The way of fitting pixel points on the contour of functional holes of other shapes is not further listed here.
Based on any of the above embodiments, the cover plate of the electronic device has a certain thickness, so that when the image of the functional hole is actually shot, the contour lines at the upper end and the lower end of the functional hole also present an inner contour line and an outer contour line in the image. Therefore, in order to further ensure the accuracy of the detection of the functional hole defect. In the present application, fitting the pixel points on the functional hole contour line according to the predetermined line segment, and obtaining the contour fitting line may specifically include:
and fitting the pixel points on the inner contour line of the functional hole and the pixel points on the outer contour line of the functional hole according to preset line segments respectively to obtain an inner contour fitting line and an outer contour fitting line.
The sizes of the aperture edges of the functional holes on the inner surface and the outer surface of the cover plate are the same, but the contour line aperture of the end, far away from the camera lens, of the functional hole is smaller than the contour line aperture of the end, close to the camera lens, of the functional hole due to the shooting angle, and then the inner contour line and the outer contour line of the functional hole in the binary image are formed; although the apertures of the inner and outer contours are different in size, the shapes should be similar, with a scaling, so that the fit can be made to the same predetermined line segment.
Because there are two circles of contour lines inside and outside, after fitting respectively to obtain two circles of contour fit lines, it is also necessary to judge whether the functional hole has a defect or not, and judge whether the difference value of the pixel coordinates of the non-overlapped part of the functional hole contour line and the contour fit line is greater than a preset difference value or not, and this process may specifically include:
and judging whether the pixel coordinate difference of the non-coincident part of the functional hole inner contour line and the functional hole inner contour fit line and/or the pixel coordinate difference of the non-coincident part of the functional hole outer contour line and the functional hole outer contour fit line is larger than a preset difference.
That is to say, if any one of the outer contour fit line and the inner contour fit line has a defect, the functional hole is considered to have a defect, so that the problem that the crack defect of one of the contour lines is shielded and cannot be displayed in an image due to the shooting angle problem is avoided, and the precision of detecting the defect of the functional hole is improved.
The following describes a defect detection apparatus for a functional hole on an electronic device cover plate according to an embodiment of the present invention, and the following description describes the defect detection apparatus for a functional hole on an electronic device cover plate and the above-described defect detection method for a functional hole on an electronic device cover plate with reference to each other.
Fig. 6 is a block diagram of a structure of a defect detection apparatus for a functional hole on an electronic device cover plate according to an embodiment of the present invention, where the defect detection apparatus for a functional hole on an electronic device cover plate shown in fig. 6 may include:
the image acquisition module 100 is used for scanning and acquiring a cover plate image, and performing binarization processing on the cover plate image to obtain a binarized image;
the region positioning module 200 is configured to position a functional hole image region in the binarized image;
a contour line extraction module 300, configured to extract pixel points of a functional hole contour in the functional hole image area to obtain a functional hole contour line;
the contour fitting module 400 is configured to fit pixel points on the contour line of the functional hole according to a predetermined line segment, so as to obtain a contour fitting line, where the predetermined line segment is a line segment set according to the shape of the functional hole of the cover plate;
and the defect judging module 500 is configured to judge whether a difference between pixel coordinates of the non-overlapping portion of the functional hole outline and the outline fit line is greater than a preset difference, and if so, the non-overlapping portion of the functional hole outline and the outline fit line is a position where the functional hole of the cover plate has a defect.
Optionally, in another specific embodiment of the present application, the area positioning module 200 is specifically configured to position the functional hole image area in the binarized image according to the model of the cover plate.
Optionally, in another specific embodiment of the present application, the image capturing module 100 is specifically configured to perform binarization processing on the cover plate image by using an adaptive binarization algorithm.
Optionally, in another specific embodiment of the present application, the profile fitting module 400 is specifically configured to obtain a symmetry axis linear equation of the functional hole contour line according to the coordinate values of the pixels on the functional hole contour line and a symmetry axis formula; determining intersection point pixel points of the functional hole contour line and the main symmetry axis linear equation according to the symmetry axis linear equation; and selecting coordinate values of a plurality of pixel points on the functional hole contour line by taking the intersection point pixel points as a reference, and fitting according to the preset line segment to obtain a contour fitting line.
Optionally, in another specific embodiment of the present application, the contour fitting module 400 is specifically configured to select, with the intersection point pixel point as a reference point, coordinate values of a plurality of pixel points within a preset distance range of the reference point on the functional hole contour line, and perform fitting according to a line segment formula that is satisfied by the preset line segment at the reference point position, so as to obtain a curve formula that is satisfied by a sub-contour fitting line; wherein the preset line segment comprises at least two line segments.
The defect determining module 500 is specifically configured to detect the distance between the pixel points on the functional hole contour line and the sub-contour fitting line one by one with the reference point as a starting point; when the distance from a continuous preset number of pixel points to the pixel coordinate of the sub-contour fitting line on the functional hole contour line is larger than a preset difference value, taking the first pixel point with the distance from the sub-contour fitting line to the sub-contour fitting line larger than the preset distance threshold value as the endpoint of the sub-contour fitting line; taking the end point of the sub-contour fit line as a new reference point, and repeatedly executing the operation of selecting the coordinate values of a plurality of pixel points in the preset distance range of the reference point on the functional hole contour line so as to obtain a new sub-contour fit line; and if the end point of the sub-contour fitting line is taken as a new reference point and cannot be fitted according to the preset line segment, the end point position of the sub-contour fitting line is the position of the defect of the functional hole of the cover plate.
Optionally, in another specific embodiment of the present application, the defect determining module 500 is further specifically configured to determine whether a length of a line segment between the reference point and an end point of the sub-contour fit line is within a preset length range, and if not, a position of the end point of the sub-contour fit line is a position where a defect exists in the functional hole of the cover plate; and if so, performing the operation of taking the end point of the sub-contour fitting line as a new reference point.
Optionally, in another specific embodiment of the present application, the contour fitting module 400 is specifically configured to fit the pixel points on the inner contour line of the functional hole and the pixel points on the outer contour line of the functional hole according to predetermined line segments, respectively, to obtain an inner contour fitting line and an outer contour fitting line.
The defect determining module 500 is further specifically configured to determine whether a pixel coordinate difference of a non-coinciding portion of the inner contour line and the inner contour fit line of the functional hole and/or a pixel coordinate difference of a non-coinciding portion of the outer contour line and the outer contour fit line of the functional hole are greater than the preset difference.
The defect detection apparatus for a functional hole on an electronic device cover plate of this embodiment is used to implement the aforementioned defect detection method for a functional hole on an electronic device cover plate, and therefore, a specific implementation manner of the defect detection apparatus for a functional hole on an electronic device cover plate can be found in the foregoing embodiment section of the defect detection method for a functional hole on an electronic device cover plate, and is not described herein again.
The present application further provides an embodiment of a system for detecting defects in functional holes on a cover plate of an electronic device, where the system for detecting defects in functional holes can include:
a camera, a processor, and a memory;
wherein the memory is used for storing a computer program;
the camera is used for shooting and collecting the cover plate image;
the processor is used for executing a computer program according to the cover plate image to realize the operation steps of the defect detection method of the functional hole on the cover plate of the electronic equipment as described in any embodiment above.
The memory may be Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Optionally, the camera for collecting the cover plate image can adopt a linear camera, the cover plate is provided with a light source, the light source irradiates the cover plate at a certain angle, the linear camera is opposite to the cover plate, the cover plate is driven to sequentially pass through the linear camera through belt type transmission, the linear camera continuously scans, a complete cover plate image is obtained after scanning is finished, and compared with an ordinary camera, the image pixel shot by the linear camera is higher, the image is more detailed, and the defect judgment accuracy is favorably improved.
After the camera scans and shoots the cover plate image, the processor judges the pixel-level defect of the image, so that the tiny defect gap which is not easy to detect is accurately judged, the fineness of the cover plate defect detection is improved, and the product quality of the cover plate of the electronic equipment is improved.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include elements inherent in the list. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element. In addition, parts of the above technical solutions provided in the embodiments of the present application, which are consistent with the implementation principles of corresponding technical solutions in the prior art, are not described in detail so as to avoid redundant description.
In the present specification, the embodiments are described in a progressive manner, and each embodiment focuses on differences from other embodiments, and the same or similar parts between the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Claims (9)
1. A defect detection method for a functional hole on an electronic equipment cover plate is characterized by comprising the following steps:
scanning and collecting a cover plate image, and carrying out binarization processing on the cover plate image to obtain a binarization image;
positioning a functional hole image area in the binary image;
extracting pixel points of the functional hole outline in the functional hole image area to obtain a functional hole outline;
fitting the pixel points on the functional hole outline according to a preset line segment to obtain an outline fitting line, wherein the preset line segment is a line segment which is set according to the shape of the functional hole of the cover plate and can be spliced to form the outline shape of the functional hole;
judging whether the difference value of the pixel coordinates of the non-coincident part of the functional hole outline and the outline fit line is larger than a preset difference value, if so, determining that the non-coincident part of the functional hole outline and the outline fit line is the position of the functional hole of the cover plate with defects;
the method is characterized in that pixel points on the functional hole contour line are fitted according to a preset line segment to obtain a contour fitting line, and the method comprises the following steps:
obtaining a symmetry axis linear equation of the functional hole outline according to the coordinate value of each pixel point on the functional hole outline and a symmetry axis formula;
determining intersection point pixel points of the functional hole contour line and the main symmetry axis linear equation according to the symmetry axis linear equation;
and selecting coordinate values of a plurality of pixel points on the functional hole contour line by taking the intersection point pixel points as a reference, and fitting according to the preset line segment to obtain a contour fit line.
2. The method for detecting defects of functional holes in a cover plate of an electronic device as claimed in claim 1, wherein locating a functional hole image area in the binarized image comprises:
and positioning the functional hole image area in the binary image according to the model of the cover plate.
3. The method for detecting defects of functional holes on a cover plate of an electronic device as claimed in claim 1, wherein the binarization processing of the cover plate image comprises:
and carrying out binarization processing on the cover plate image by using a self-adaptive binarization algorithm.
4. The method of claim 1, wherein the predetermined line segment comprises at least two line segments;
and selecting coordinate values of a plurality of pixel points on the functional hole contour line by taking the intersection point pixel points as a reference, and fitting according to the preset line segment to obtain a contour fitting line, wherein the contour fitting line comprises:
selecting coordinate values of a plurality of pixel points in a preset distance range of the reference point on the functional hole contour line by taking the intersection point pixel point as the reference point, and fitting according to a line segment formula which is met by the preset line segment at the reference point position to obtain a curve formula which is met by a sub-contour fitting line;
judging whether the difference value of the pixel coordinates of the non-coincident part of the functional hole contour line and the contour fitting line is larger than a preset difference value or not comprises the following steps:
detecting the distance between pixel points on the functional hole contour line and the sub-contour fitting line one by taking the reference point as a starting point;
when the distance from a continuous preset number of pixel points to the pixel coordinate of the sub-contour fitting line on the functional hole contour line is larger than a preset difference value, taking the first pixel point with the distance from the sub-contour fitting line to the sub-contour fitting line larger than the preset distance threshold value as the endpoint of the sub-contour fitting line;
taking the end point of the sub-contour fit line as a new reference point, and repeatedly executing the operation of selecting the coordinate values of a plurality of pixel points in the preset distance range of the reference point on the functional hole contour line so as to obtain a new sub-contour fit line;
and if the end point of the sub-contour fitting line is taken as a new reference point and cannot be fitted according to the preset line segment, the end point position of the sub-contour fitting line is the position of the functional hole of the cover plate with defects.
5. The method of claim 4, wherein after the pixel point having a first distance from the sub-contour fit line greater than the predetermined distance threshold is the end point of the sub-contour fit line, the method further comprises:
judging whether the length of a line segment between the reference point and the end point of the sub-outline fitting line is within a preset length range, if not, the end point position of the sub-outline fitting line is the position of the functional hole of the cover plate with defects; if so, the operation of taking the end point of the sub-contour fitting line as a new reference point is carried out.
6. The method for detecting defects of functional holes in a cover plate of an electronic device as claimed in any one of claims 1 to 5, wherein fitting pixel points on the outline of the functional holes according to a predetermined line segment to obtain an outline fitting line comprises:
fitting the pixel points on the inner contour line of the functional hole and the pixel points on the outer contour line of the functional hole according to preset line segments respectively to obtain an inner contour fitting line and an outer contour fitting line;
judging whether the difference value of the pixel coordinates of the non-coincident part of the functional hole contour line and the contour fitting line is larger than a preset difference value or not, comprising the following steps:
and judging whether the pixel coordinate difference of the non-coincident part of the inner contour line and the inner contour fit line of the functional hole and/or the pixel coordinate difference of the non-coincident part of the outer contour line and the outer contour fit line of the functional hole are larger than the preset difference or not.
7. A defect detecting device for a functional hole in an electronic device cover plate, comprising:
the image acquisition module is used for scanning and acquiring a cover plate image and carrying out binarization processing on the cover plate image to obtain a binarization image;
the area positioning module is used for positioning a functional hole image area in the binary image;
the contour line extraction module is used for extracting pixel points of the functional hole contour in the functional hole image area to obtain a functional hole contour line;
the contour fitting module is used for fitting pixel points on the contour line of the functional hole according to a preset line segment to obtain a contour fitting line, wherein the preset line segment is a line segment set according to the shape of the functional hole of the cover plate;
the defect judging module is used for judging whether the difference value of the pixel coordinates of the non-coincident part of the functional hole outline and the outline fit line is larger than a preset difference value or not, and if so, the non-coincident part of the functional hole outline and the outline fit line is the position of the functional hole of the cover plate with defects;
the method for fitting the pixel points on the functional hole contour line according to the preset line segment to obtain the contour fitting line comprises the following steps:
obtaining a symmetry axis linear equation of the functional hole outline according to the coordinate value of each pixel point on the functional hole outline and a symmetry axis formula;
determining intersection point pixel points of the functional hole contour line and the main symmetry axis linear equation according to the symmetry axis linear equation;
and selecting coordinate values of a plurality of pixel points on the functional hole contour line by taking the intersection point pixel points as a reference, and fitting according to the preset line segment to obtain a contour fit line.
8. A defect detection system of a functional hole on a cover plate of an electronic device is characterized by comprising a camera, a processor and a memory;
wherein the memory is for storing a computer program;
the camera is used for shooting and acquiring the cover plate image;
the processor is configured to execute the computer program according to the cover plate image to implement the operation steps of the method for detecting defects of functional holes on a cover plate of an electronic device according to any one of claims 1 to 6.
9. The system for detecting defects in functional holes in a cover sheet for electronic devices of claim 8, further comprising a light source for providing light to the cover sheet; the camera is a line-scan camera.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010322419.4A CN113554582B (en) | 2020-04-22 | 2020-04-22 | Defect detection method, device and system for functional hole in electronic equipment cover plate |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010322419.4A CN113554582B (en) | 2020-04-22 | 2020-04-22 | Defect detection method, device and system for functional hole in electronic equipment cover plate |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113554582A CN113554582A (en) | 2021-10-26 |
CN113554582B true CN113554582B (en) | 2022-11-08 |
Family
ID=78101024
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010322419.4A Active CN113554582B (en) | 2020-04-22 | 2020-04-22 | Defect detection method, device and system for functional hole in electronic equipment cover plate |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113554582B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114764804B (en) * | 2022-06-16 | 2022-09-20 | 深圳新视智科技术有限公司 | Lithium battery pole piece defect detection method, device, equipment and storage medium |
CN115018846B (en) * | 2022-08-09 | 2022-12-27 | 东声(苏州)智能科技有限公司 | AI intelligent camera-based multi-target crack defect detection method and device |
CN115049657A (en) * | 2022-08-15 | 2022-09-13 | 启东晶尧光电科技有限公司 | Glass defect detection method |
CN115937114B (en) * | 2022-11-25 | 2024-06-04 | 无锡海纳智能科技有限公司 | Preprocessing method and device for fan pictures |
CN115932864B (en) * | 2023-02-24 | 2023-08-01 | 深圳市博铭维技术股份有限公司 | Pipeline defect detection method and pipeline defect detection device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1401107A (en) * | 2000-01-18 | 2003-03-05 | 索威森公司 | Method and system for detecting defects on a printed circuit board |
WO2013069389A1 (en) * | 2011-11-07 | 2013-05-16 | 株式会社神戸製鋼所 | Tire shape inspection method and tire shape inspection device |
CN107064170A (en) * | 2017-04-11 | 2017-08-18 | 深圳市深视智能科技有限公司 | One kind detection phone housing profile tolerance defect method |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101110101A (en) * | 2006-07-17 | 2008-01-23 | 松下电器产业株式会社 | Method for recognizing picture pattern and equipment thereof |
US8355562B2 (en) * | 2007-08-23 | 2013-01-15 | Hitachi High-Technologies Corporation | Pattern shape evaluation method |
US10330608B2 (en) * | 2012-05-11 | 2019-06-25 | Kla-Tencor Corporation | Systems and methods for wafer surface feature detection, classification and quantification with wafer geometry metrology tools |
CN104299261B (en) * | 2014-09-10 | 2017-01-25 | 深圳大学 | Three-dimensional imaging method and system for human body |
CN105321182B (en) * | 2015-11-12 | 2019-06-07 | 彭涛 | A kind of the sound hole defect inspection method and system of mobile phone glass panel |
CN107301636A (en) * | 2017-05-17 | 2017-10-27 | 华南理工大学 | A kind of high density circuit board circular hole sub-pixel detection method based on Gauss curve fitting |
CN109001224B (en) * | 2017-06-07 | 2022-02-18 | 宁德时代新能源科技股份有限公司 | Welding seam detection method and detection device |
CN107578438A (en) * | 2017-07-13 | 2018-01-12 | 南京协辰电子科技有限公司 | Circle recognition methods, device and electronic equipment |
CN108389179B (en) * | 2018-01-15 | 2020-10-13 | 湖南大学 | Machine vision-based can cover surface defect detection method |
CN109658402B (en) * | 2018-12-17 | 2023-04-18 | 中山大学 | Automatic detection method for geometric dimension of industrial profile based on computer vision imaging |
CN109727231A (en) * | 2018-12-17 | 2019-05-07 | 江苏鸿祺生物科技有限公司 | A kind of appearance random defect detecting spheroid shape soft capsule for identification from Determination method |
CN110163853B (en) * | 2019-05-14 | 2021-05-25 | 广东奥普特科技股份有限公司 | Edge defect detection method |
-
2020
- 2020-04-22 CN CN202010322419.4A patent/CN113554582B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1401107A (en) * | 2000-01-18 | 2003-03-05 | 索威森公司 | Method and system for detecting defects on a printed circuit board |
WO2013069389A1 (en) * | 2011-11-07 | 2013-05-16 | 株式会社神戸製鋼所 | Tire shape inspection method and tire shape inspection device |
CN107064170A (en) * | 2017-04-11 | 2017-08-18 | 深圳市深视智能科技有限公司 | One kind detection phone housing profile tolerance defect method |
Also Published As
Publication number | Publication date |
---|---|
CN113554582A (en) | 2021-10-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113554582B (en) | Defect detection method, device and system for functional hole in electronic equipment cover plate | |
CN108460757B (en) | Mobile phone TFT-LCD screen Mura defect online automatic detection method | |
CN110672617B (en) | Method for detecting defects of silk-screen area of glass cover plate of smart phone based on machine vision | |
CN115908269B (en) | Visual defect detection method, visual defect detection device, storage medium and computer equipment | |
WO2022110804A1 (en) | Image noise measurement method and device based on local statistical information | |
KR100556856B1 (en) | Screen control method and apparatus in mobile telecommunication terminal equipment | |
CN116758083B (en) | Quick detection method for metal wash basin defects based on computer vision | |
WO2020253827A1 (en) | Method and apparatus for evaluating image acquisition accuracy, and electronic device and storage medium | |
US20040146187A1 (en) | Iris extraction method | |
CN110059702B (en) | Object contour recognition method and device | |
CN110210448B (en) | Intelligent face skin aging degree identification and evaluation method | |
CN110827244A (en) | Method and equipment for detecting appearance flaws of electronic equipment | |
US11010884B2 (en) | System and method for evaluating displays of electronic devices | |
CN113781406B (en) | Scratch detection method and device for electronic component and computer equipment | |
CN106651837B (en) | White glass plate surface chipping defect inspection method | |
CN110648330B (en) | Defect detection method for camera glass | |
CN113012098B (en) | Iron tower angle steel punching defect detection method based on BP neural network | |
CN106815830B (en) | Image defect detection method | |
CN117011291B (en) | Watch shell quality visual detection method | |
CN109975307A (en) | Bearing surface defect detection system and detection method based on statistics projection training | |
CN113378663A (en) | Inspection pointer type circular instrument identification method and device | |
CN116908185A (en) | Method and device for detecting appearance defects of article, electronic equipment and storage medium | |
CN108805883B (en) | Image segmentation method, image segmentation device and electronic equipment | |
CN116258703A (en) | Defect detection method, defect detection device, electronic equipment and computer readable storage medium | |
CN114723728A (en) | Method and system for detecting CD line defects of silk screen of glass cover plate of mobile phone camera |
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 |