CN115187585A - Defect detection method and device, electronic equipment and storage medium - Google Patents

Abstract

The embodiment of the invention discloses a defect detection method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a silk-screen image generated after image acquisition is carried out on a silk-screen product with a silk-screen edge detection requirement, and extracting a silk-screen edge from the silk-screen image; filtering the silk-screen edge to obtain a filtering edge, wherein filtering points respectively corresponding to the silk-screen points on the silk-screen edge exist on the filtering edge; for each silk-screen point, determining the distance between a filtering point corresponding to the silk-screen point and the silk-screen point, and determining whether the silk-screen point is a defect point according to the distance; and detecting whether the silk-screen edge has defects or not according to whether each silk-screen point is a defect point or not. The technical scheme of the embodiment of the invention can automatically detect whether the silk-screen edge has defects.

Description

Defect detection method and device, electronic equipment and storage medium

Technical Field

The embodiment of the invention relates to the technical field of image processing, in particular to a defect detection method and device, electronic equipment and a storage medium.

Background

With the rapid development of the silk-screen technology, silk-screen products with various styles and exquisite styles are increasingly popular with people. It should be noted that, since the ink applied in the screen printing process is viscous, there may be some defects on the edge of the screen printing, which may affect the screen printing effect.

In order to guarantee the silk-screen effect, whether defects exist on the edge of the silk-screen is mainly detected through manual visual inspection at present, but the defect detection scheme has the problems of low detection speed and low accuracy.

Disclosure of Invention

The embodiment of the invention provides a defect detection method, a defect detection device, electronic equipment and a storage medium, which are used for automatically detecting whether a defect exists on a silk-screen edge.

According to an aspect of the present invention, there is provided a defect detection method, which may include:

acquiring a silk-screen image generated after image acquisition is carried out on a silk-screen product aiming at the silk-screen product with the silk-screen edge detection requirement, and extracting a silk-screen edge from the silk-screen image;

filtering the silk-screen edge to obtain a filtering edge, wherein the filtering edge is provided with filtering points respectively corresponding to all the silk-screen points on the silk-screen edge;

determining the distance between a filtering point corresponding to each silk-screen point and the silk-screen point for each silk-screen point, and determining whether the silk-screen points are defective points according to the distance;

and detecting whether the silk-screen edge has defects or not according to whether each silk-screen point is a defective point or not.

According to another aspect of the present invention, there is provided a defect detecting apparatus, which may include:

the silk-screen edge extraction module is used for acquiring a silk-screen image generated after image acquisition is carried out on the silk-screen product aiming at the silk-screen product with the silk-screen edge detection requirement, and extracting a silk-screen edge from the silk-screen image;

the filtering edge obtaining module is used for filtering the silk-screen edge to obtain a filtering edge, wherein the filtering edge is provided with filtering points respectively corresponding to the silk-screen points on the silk-screen edge;

the defect point determining module is used for determining the distance between the filtering point corresponding to the silk-screen point and the silk-screen point for each silk-screen point and determining whether the silk-screen point is a defect point according to the distance;

and the defect detection module is used for detecting whether the silk-screen edge has defects or not according to whether each silk-screen point is a defective point or not.

According to another aspect of the present invention, there is provided an electronic device, which may include:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor, when executed, to implement a defect detection method as provided by any of the embodiments of the invention.

According to another aspect of the present invention, there is provided a computer-readable storage medium having stored thereon computer instructions for causing a processor to execute a method for defect detection provided by any of the embodiments of the present invention.

According to the technical scheme of the embodiment of the invention, a silk-screen image generated after image acquisition is carried out on a silk-screen product is obtained by aiming at the silk-screen product with the silk-screen edge detection requirement, and the silk-screen edge is extracted from the silk-screen image; filtering the silk-screen edge to obtain a filtering edge, wherein the filtering edge is provided with filtering points respectively corresponding to all the silk-screen points on the silk-screen edge; then, for each silk-screen point, determining the distance between a filtering point corresponding to the silk-screen point and the silk-screen point, and determining whether the silk-screen point is a defect point according to the distance; and detecting whether the silk-screen edge has defects or not according to whether each silk-screen point is a defective point or not. According to the technical scheme of the embodiment of the invention, the defect points are determined according to the silk-screen points on the silk-screen edge and the filter points on the filter edge, and the defects of the silk-screen edge are detected according to the defect points, so that whether the defects exist on the silk-screen edge can be automatically detected according to the silk-screen edge of a silk-screen product, and the effect of quickly and accurately detecting the silk-screen defects is achieved.

It should be understood that the statements in this section do not necessarily identify key or critical features of any embodiment of the present invention, nor do they necessarily limit the scope of the present invention. Other features of the present invention will become apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and 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 to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of a defect detection method according to an embodiment of the present invention;

FIG. 2 is a flowchart of a defect detection method according to a second embodiment of the present invention;

FIG. 3 is a schematic diagram of a burr defect in a defect detection method according to a second embodiment of the present invention;

FIG. 4 is a diagram illustrating a defect of a notch in a defect detection method according to a second embodiment of the present invention;

FIG. 5 is a flowchart of a defect detection method according to a third embodiment of the present invention;

fig. 6 is a schematic diagram illustrating a process of determining a silk-screen dot in a defect detection method according to a third embodiment of the present invention;

FIG. 7 is a flowchart of an alternative example of a defect detection method according to a third embodiment of the present invention;

FIG. 8 is a flowchart of another alternative example of a defect detection method according to a third embodiment of the present invention;

fig. 9 is a block diagram illustrating a defect detecting apparatus according to a fourth embodiment of the present invention;

fig. 10 is a schematic structural diagram of an electronic device implementing the defect detection method according to the embodiment of the invention.

Detailed Description

In order to make those skilled in the art better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. The cases of "target", "original", etc. are similar and will not be described in detail herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example one

Fig. 1 is a flowchart of a defect detection method according to an embodiment of the present invention. The embodiment can be suitable for detecting the silk-screen defects. The method may be executed by a defect detection apparatus provided in an embodiment of the present invention, where the apparatus may be implemented by software and/or hardware, and the apparatus may be integrated on an electronic device, and the electronic device may be various user terminals or servers.

Referring to fig. 1, the method of the embodiment of the present invention specifically includes the following steps:

s110, acquiring a silk-screen image generated after image acquisition is carried out on the silk-screen product aiming at the silk-screen product with the silk-screen edge detection requirement, and extracting the silk-screen edge from the silk-screen image.

Wherein, the silk-screen edge can be understood as the edge profile of the silk-screen product. The silk-screen product can be understood as a product which needs to detect the defects of the silk-screen edge on the product.

It can be understood that, because the surface of the silk-screen product may have a light-reflecting characteristic, a silk-screen image generated after the image of the silk-screen product is acquired may have light-reflecting points. Considering that the reflection point is a mutation point in the image, distortion of a silk-screen edge curve can be caused, and misjudgment on silk-screen edge defects is caused, after the silk-screen image is obtained, relevant processing for removing the reflection point can be performed on the obtained silk-screen image. In the embodiment of the present invention, the related processing may be preprocessing such as filtering, denoising, and morphological operation, and may also be implemented according to a pre-trained neural network model, and the like, which is not specifically limited herein.

It should be noted that the extracted silkscreen edge may be considered to be formed by connecting lines of silkscreen dots extracted from the silkscreen image. The silk-screen dots can be understood as dots that can form the edges of the silk-screen.

And S120, filtering the silk-screen edge to obtain a filtering edge, wherein filtering points respectively corresponding to all the silk-screen points on the silk-screen edge exist on the filtering edge.

In practical applications, the filtering scheme adopted herein may be, optionally, mean filtering, median filtering, moving average filtering, kalman filtering, and the like, and is not specifically limited herein.

It should be noted that the extracted filtering edge can be considered as being formed by connecting filtering points. In addition, each filtering point on the filtering edge corresponds to each screen printing point on the screen printing edge one to one, that is, any screen printing point on the filtered screen printing edge can be understood as a filtering point corresponding to the screen printing point. Wherein a filter point is understood to be a point that can constitute a filter edge.

For example, a planar rectangular coordinate system may be established on the silk-screen image (or an image coordinate system of the silk-screen image itself is directly applied), a serial number is set for each silk-screen dot, a coordinate point of each silk-screen dot on the planar rectangular coordinate system is obtained, and the coordinates of the silk-screen dot on the planar rectangular coordinate system may be (X (t), Y (t)), t =1,2 \ 8230, and N is the serial number of the silk-screen dot. For example, taking mean filtering as an example, the mean filtering may be performed on the silk-screen edge according to the following formula:

where W is the filter width, x 'is the abscissa of the t-th filter point on the filter edge, and y' is the ordinate of the t-th filter point on the filter edge. And linearly connecting the filter points to obtain a filter edge Q (x ', y'). In the embodiment of the invention, a serial number can be set for each filtering point, and each silk-screen printing point has the same serial number as the corresponding filtering point.

S130, determining the distance between the filtering point corresponding to the silk screen point and the silk screen point for each silk screen point, and determining whether the silk screen point is a defect point according to the distance.

Wherein a defective dot may be understood as a dot that is capable of characterizing a silk-screen edge as having a defect at that point. It should be noted that, considering that the silk-screen edge curve is generally smooth, if there is a burr defect or a notch defect on the silk-screen edge curve, the silk-screen edge curve may be steeply shifted, and the distance difference between the curve at the defect position and other positions around the defect position is relatively large, if the defect position is filtered, the curve at the defect position may become smooth from steepness, and there is no obvious change after filtering at other positions around the defect position, so that it may be detected whether there is a defect on the silk-screen edge by using the characteristics of the silk-screen edge curve after filtering.

In the embodiment of the invention, for each silk-screen point, the distance between the silk-screen point and the filtering point can be determined according to the position of the filtering point corresponding to the silk-screen point and the position of the silk-screen point, so that whether the silk-screen point is a defect point or not is determined according to the distance. Exemplarily, comparing the distance with a preset distance range, and if the distance is not within the distance range, determining the silk-screen dot as a defect dot; in another example, the absolute value of the distance is compared with a preset distance threshold, and if the absolute value of the distance is greater than the distance threshold, the silk-screen dot is determined as a defective dot.

For example, a planar rectangular coordinate system may be established on the silk-screen image (or an image coordinate system of the silk-screen image itself is directly applied), and a serial number is set for each silk-screen point and each filtering point, where the serial number of each silk-screen point is the same as the serial number of the corresponding filtering point. Calculating the distance between the silk-screen points and the filtering points with the same serial number

And d is compared with a preset distance threshold value delta t, and if d is larger than delta t, the silk-screen point is determined as a defect point. Wherein x is the abscissa of the silk-screen points, y is the ordinate of the silk-screen points, x 'is the abscissa of the filtering points with the same sequence number as the silk-screen points, and y' is the ordinate of the filtering points with the same sequence number as the silk-screen points.

And S140, detecting whether the silk-screen edge has defects or not according to whether each silk-screen point is a defect point or not.

And when the silk-screen dots are the defective dots, indicating that the silk-screen edges at the defective dots are possibly defective. Therefore, in the embodiment of the present invention, whether a defect exists on the screen printing edge may be detected according to whether each screen printing point is a defective point, for example, when the proportion of the screen printing point which is the defective point in all the screen printing points exceeds a preset proportion threshold, or a candidate defect area formed by the screen printing point which is the defective point meets a preset defect condition, it is determined that the defect exists on the screen printing edge.

According to the technical scheme of the embodiment of the invention, a silk-screen image generated after image acquisition is carried out on a silk-screen product is obtained by aiming at the silk-screen product with the silk-screen edge detection requirement, and the silk-screen edge is extracted from the silk-screen image; filtering the silk-screen edge to obtain a filtering edge, wherein the filtering edge is provided with filtering points corresponding to all the silk-screen points on the silk-screen edge; then, for each silk-screen point, determining the distance between a filtering point corresponding to the silk-screen point and the silk-screen point, and determining whether the silk-screen point is a defect point according to the distance; and detecting whether the silk-screen edge has defects or not according to whether each silk-screen point is a defective point or not. According to the technical scheme of the embodiment of the invention, the defect points are determined according to the silk-screen points on the silk-screen edge and the filter points on the filter edge, and the defects of the silk-screen edge are detected according to the defect points, so that whether the defects exist on the silk-screen edge can be automatically detected according to the silk-screen edge of a silk-screen product, and the effect of quickly and accurately detecting the silk-screen defects is achieved.

Example two

Fig. 2 is a flowchart of another defect detection method provided in the second embodiment of the present invention. The present embodiment is optimized based on the above technical solutions. In this embodiment, optionally, detecting whether there is a defect on the silk-screen edge according to whether each silk-screen point is a defective point includes: extracting at least one defective point from each silk-screen point according to whether each silk-screen point is a defective point or not, and constructing at least one pseudo-defective area according to the at least one defective point; for each pseudo-defect area, determining whether the pseudo-defect area is a real defect area or not according to the area and/or the area size of the pseudo-defect area; and detecting whether the silk-screen edge has defects or not according to whether each pseudo-defect area is a real defect area or not. The explanations of the same or corresponding terms as those in the above embodiments are omitted.

Referring to fig. 2, the method of the present embodiment may specifically include the following steps:

s210, acquiring a silk-screen image generated after image acquisition is carried out on the silk-screen product aiming at the silk-screen product with the silk-screen edge detection requirement, and extracting the silk-screen edge from the silk-screen image.

S220, filtering the silk-screen edge to obtain a filtering edge, wherein filtering points respectively corresponding to all the silk-screen points on the silk-screen edge exist on the filtering edge.

S230, determining the distance between the filtering point corresponding to the silk-screen point and the silk-screen point for each silk-screen point, and determining whether the silk-screen point is a defect point according to the distance.

S240, extracting at least one defective point from each silk-screen point according to whether each silk-screen point is a defective point or not, and constructing at least one pseudo-defective area according to the at least one defective point.

If the silk-screen points are defective points, it is indicated that the silk-screen edges at the defective points may have defects, at least one defective point in each silk-screen point may be extracted, and at least one pseudo-defect region is constructed according to the at least one defective point, for example, a pseudo-defect region is constructed according to all the defective points; mutually communicating adjacent defect points in the at least one defect point to construct and obtain a pseudo-defect area, so as to obtain at least one pseudo-defect area; and the like, are not specifically limited herein.

It should be noted that, since the pseudo-defect regions constructed from a part of the defect points are smaller, and may be only uneven regions caused by slight variations of the contour, and the like, and cannot exist as real defect regions, each pseudo-defect region constructed from at least one defect point is a defect region that cannot be guaranteed to be a real defect region, but only may be a real defect region.

And S250, determining whether the pseudo-defect area is a real defect area or not according to the area and/or the area size of the pseudo-defect area aiming at each pseudo-defect area.

In an embodiment of the present invention, for each pseudo-defect region, in order to determine whether the pseudo-defect region is a real defect region, a region area and/or a region size of the pseudo-defect region may be calculated, and then, whether the pseudo-defect region is a real defect region may be determined according to the region area and/or the region size. For example, an area threshold and/or a size threshold may be preset, a region area and/or a region size of the pseudo-defect region may be calculated, the region area may be compared with the area threshold and/or the region size may be compared with the size threshold, and if the region area is greater than the area threshold and/or the region size is greater than the size threshold, the pseudo-defect region may be determined to be a real defect region. Wherein a real defect area may be understood as a pseudo-defect area within which defects do exist.

And S260, detecting whether the silk-screen edge has defects or not according to whether each pseudo-defect area is a real defect area or not.

Whether the silk-screen edge has defects can be detected according to whether each pseudo-defect area is a real defect area, for example, when at least one real defect area exists in each pseudo-defect area, each pseudo-defect area is a real defect area, or the ratio of the pseudo-defect areas belonging to the real defect areas in all the defect areas exceeds a preset ratio threshold, the silk-screen edge has defects, and the real defect area can be detected as the defect.

According to the technical scheme of the embodiment of the invention, at least one defect point is extracted from each silk-screen point according to whether each silk-screen point is a defect point, and at least one pseudo defect area is constructed according to the at least one defect point; for each pseudo-defect area, determining whether the pseudo-defect area is a real defect area or not according to the area and/or the area size of the pseudo-defect area; and detecting whether the silk-screen edge has defects or not according to whether each pseudo-defect area is a real defect area or not. The accuracy of defect detection is further improved by determining whether the pseudo-defect region is a real defect region.

An optional technical solution, the defect detection method, further includes: respectively obtaining the serial number of each silk-screen point, wherein the serial number of each silk-screen point is used for representing the position of the silk-screen point on the edge of the silk screen; constructing at least one pseudo-defect region according to at least one defect point, comprising: determining at least one defect group from at least one defect point, wherein the serial numbers of the defect points in each defect group are connected; and aiming at each defect group, constructing and obtaining a pseudo defect area based on each defect point in the defect group.

The serial number of each silk-screen point can be obtained after the silk-screen edge is extracted, and the serial number of the silk-screen point is used for representing the position of the silk-screen point on the silk-screen edge. In practical application, optionally, if the serial numbers of the screen printing dots are sequentially arranged, the serial number of any one screen printing dot on the screen printing edge may be obtained, and the serial numbers of other screen printing dots may be known in the clockwise or counterclockwise direction along the screen printing edge according to the serial number of the screen printing dot and the arrangement direction of the serial numbers of the screen printing dots. For example, the serial number of any one silk-screen dot on the edge of the silk screen is obtained to be 3, if the serial number is arranged in the clockwise direction, the serial number of the next silk-screen dot in the clockwise direction can be known to be 4, the serial number of the next silk-screen dot is known to be 5, and so on, so as to obtain the serial number of each silk-screen dot; the serial number of the next screen printing point in the anticlockwise direction can be known to be 2, and so on, so that the serial number of each screen printing point is obtained. In the embodiment of the present invention, a serial number of each filtering point may also be obtained, where the serial number of the filtering point is the same as the serial number of the corresponding silk-screen point, that is, the position of the filtering point on the filtering edge is the same as the position of the corresponding silk-screen point on the silk-screen edge.

Each defect point with a consecutive sequence number in the at least one defect point may be configured as a defect group, thereby obtaining at least one defect group. For each defect group, the defect points in the defect group can be linearly connected according to the respective sequence numbers, so that the connected region is used as a pseudo-defect region. In other words, a defect group is understood to be a group comprising at least two defect points with consecutive sequence numbers, on the basis of which a pseudo-defect region can be constructed on the basis of each defect group.

In the embodiment of the invention, the defect points in each defect group are connected according to respective serial numbers to construct a pseudo-defect region, so that the original independent defect points can be constructed into a pseudo-defect region with more integrity according to the positions of the defect points, and whether defects exist on the silk-screen edge or not can be conveniently judged subsequently.

Another optional technical solution is that the defect detection method further includes: determining that the defects on the silk-screen edge are located in the real defect area under the condition that the defects on the silk-screen edge are detected; and obtaining a gray average value of the real defect area according to the gray value of each area point in the real defect area, and determining the defect type corresponding to the real defect area based on the gray average value.

The region points can be understood as pixel points in the real defect region. The gray average value can be understood as the average level value of the gray values of the respective region points. The defect type may be understood as a type to which a defect on the edge of the screen print belongs, and may be, for example, a burr defect or a notch defect.

And under the condition that the defects exist on the silk-screen edge are detected according to whether each pseudo-defect area is a real defect area, the fact that the defects are located in the real defect area is shown. Therefore, for each real defect region, the gray average value of the real defect region can be obtained according to the gray values of the region points in the real defect region, and the defect type corresponding to the real defect region is determined based on the gray average value.

In the embodiment of the present invention, under the condition that the consumption of computing resources needs to be reduced, a region point selection rule may be preset for each real defect region, a partial region point capable of representing the gray value of the real defect region in the real defect region is selected according to the region point selection rule, and then the gray average value of the real defect region is obtained according to the gray value of the partial region point, so as to determine the defect type corresponding to the real defect region based on the gray average value. The area point selection rule may be understood as a rule that a partial area point that can represent the whole gray value of the real defect area can be selected, for example, the area point selection rule may be that an area point is selected every preset number of pixel points in the real defect area.

In the embodiment of the invention, under the condition that the defect on the silk-screen edge is located in the real defect area, the defect type corresponding to the real defect area is determined based on the gray average value, so that the defect type of the defect on the silk-screen edge located in the real defect area can be determined more simply and rapidly.

On the basis of the above scheme, another optional technical scheme is that determining the defect type corresponding to the real defect area based on the gray average value includes: acquiring a preset gray threshold; and under the condition that the gray average value is greater than or equal to the gray threshold value, the defect type corresponding to the real defect area is a notch defect, otherwise, the defect type is a burr defect.

Among them, it can be understood that, referring to fig. 3, the color of the burr defect in a convex state in the silk-screen defect is usually darker; referring to fig. 4, the notch defect in the recessed state is slightly bright in color. According to the characteristics of the silk-screen defects, the gray level threshold corresponding to the silk-screen product can be preset according to the type of the silk-screen product, the preset gray level threshold is obtained, and when the gray level mean value is larger than or equal to the gray level threshold, the defect type corresponding to the real defect area is a notch defect, otherwise, the defect is a burr defect.

In the embodiment of the invention, the defect type is determined according to the comparison result of the gray average value and the gray threshold value, so that the type of the defect at the edge of the silk screen can be more accurately judged.

EXAMPLE III

Fig. 5 is a flowchart of a defect detection method according to a third embodiment of the present invention. The present embodiment is optimized based on the above technical solutions. In this embodiment, optionally, extracting the silk-screen edge from the silk-screen image includes: extracting a drawing line from the silk-screen image, wherein the drawing line comprises a line to be drawn along the silk-screen edge extracted from the silk-screen image after the silk-screen image is generated; traversing pixel points on the silk-screen image along the normal direction by taking the drawing point as a starting point for each drawing point on the drawing line, and determining the silk-screen point from each pixel point, wherein the normal direction is a direction which faces the silk-screen edge and is vertical to the drawing line; and connecting all the silk-screen points to form an edge, and taking the edge as the extracted silk-screen edge. The explanations of the same or corresponding terms as those in the above embodiments are omitted.

Referring to fig. 5, the method of this embodiment may specifically include the following steps:

s310, acquiring a silk-screen image generated after image acquisition is carried out on the silk-screen product aiming at the silk-screen product with the silk-screen edge detection requirement.

And S320, extracting a drawing line from the silk-screen image, wherein the drawing line comprises a line to be drawn along the silk-screen edge extracted from the silk-screen image after the silk-screen image is generated.

The drawn lines can be lines drawn on the silk-screen image and are closer to the silk-screen edge to be extracted from the silk-screen image, which needs to be subjected to defect detection. The number of the drawn lines can be one or more; the position of the drawn lines can be on the inner side of the silk-screen edge or on the outer side of the silk-screen edge; the form of the drawn line can be a straight line or a curve; the drawing lines can be drawn manually according to the silk-screen edges, and can also be drawn automatically according to the positions of silk-screen products in silk-screen images. In the embodiment of the present invention, the number, the position, the form, and the drawing method of the drawn lines are not particularly limited.

S330, traversing pixel points on the silk-screen image along a normal direction by taking the drawing point as a starting point for each drawing point on the drawing line, and determining the silk-screen point from each pixel point, wherein the normal direction is a direction which faces to the silk-screen edge and is perpendicular to the drawing line.

The drawing points can be understood as points arranged on the drawing lines at intervals of a preset distance, and the drawing points can be pixel points occupied by the drawing lines on the silk-screen image.

For example, referring to fig. 6, for each drawing point on the drawing line, with the drawing point as a starting point, traversing pixel points on the silk-screen image within a preset distance range on a normal along a normal direction of the drawing line at the drawing point, and determining a silk-screen point from the pixel points, wherein the normal direction is a direction toward a silk-screen edge and perpendicular to the drawing line.

And S340, connecting all the silk-screen points to form an edge, and taking the edge as the extracted silk-screen edge.

The extracted silk-screen points are points on the edge of the silk-screen product in the silk-screen image, so that the edge formed by connecting all the silk-screen points can be used as the extracted silk-screen edge.

And S350, filtering the silk-screen edge to obtain a filtering edge, wherein filtering points respectively corresponding to all silk-screen points on the silk-screen edge exist on the filtering edge.

S360, determining the distance between the filtering point corresponding to the silk-screen point and the silk-screen point for each silk-screen point, and determining whether the silk-screen point is a defect point according to the distance.

And S370, detecting whether the silk-screen edge has defects or not according to whether each silk-screen point is a defect point or not.

According to the technical scheme of the embodiment of the invention, the drawing lines are extracted from the silk-screen image, the pixel points on the silk-screen image are traversed along the normal direction by taking the drawing points as the starting points for each drawing point on the drawing lines, the silk-screen points are determined from each pixel point, and then all the silk-screen points can be connected to form the edge which is taken as the extracted silk-screen edge, so that the accuracy of the extracted silk-screen edge can be improved.

An optional technical scheme for determining silk-screen points from all pixel points includes: calculating an absolute value of a gray difference between a gray value of a current point and a gray value of an adjacent point aiming at each current point in each pixel point, wherein the adjacent point is a pixel point which is traversed after the current point and is adjacent to the current point in each pixel point; and taking the current point corresponding to the maximum absolute value as a silk-screen point.

The current point can be understood as a pixel point which is currently calculated along the normal direction to determine whether the pixel point is a silk-screen point. In practical application, optionally, the current point may also be a pixel point of whether the calculation is a silk-screen point within a preset distance range along the normal direction at present.

It should be understood that, in consideration of the characteristics of silk-screen printing, the difference between the gray values of the pixel points on the silk-screen image (such as silk-screen text image) and the gray values of the pixel points not on the silk-screen image is significant, so based on this characteristic, the absolute value of the gray value difference between the gray value of the current point and the gray value of the adjacent point can be calculated for each current point in each pixel point, the absolute values corresponding to each current point are compared with each other, and the current point corresponding to the largest absolute value is used as the silk-screen point.

For example, a normal direction may be taken as a horizontal axis X, a drawing line perpendicular to the normal line is drawn at a drawing point as a vertical axis Y, an abscissa of a pixel point on a silk-screen image traversed along the normal direction is X, an ordinate is g (X), a gray value of a current point is f (X, g (X)), absolute values of gray differences between the gray value of each current point and the gray values of adjacent points are respectively calculated, and a maximum absolute value max (| f (X +1, g (X + 1)) -f (X, g (X)) |) is found from the absolute values, and the current point f (X) corresponding to the maximum absolute value is determined (X, g (X)) |) _a ，g(x _a ) As silk-screen dots. Wherein, the preset distance range can be used as the definition field of x.

And taking the current point corresponding to the absolute value of the gray difference between the gray value of the maximum current point and the gray value of the adjacent point as the silk-screen point, so that the silk-screen point can be accurately determined.

In order to better understand the technical solutions of the embodiments of the present invention, an alternative example is provided herein. Exemplarily, referring to fig. 7, image acquisition is performed on a silk-screen printing product, and preprocessing for removing reflective dots is performed on an acquired silk-screen printing image; extracting silk-screen edges from the pre-processed silk-screen image, and filtering the silk-screen edges to obtain filtering edges; determining the position of each silk-screen point on the silk-screen edge and the position of each filtering point on the filtering edge; further, for each silk-screen point, calculating the distance between the silk-screen point and the corresponding filter point according to the position of the silk-screen point and the position of the corresponding filter point, and determining whether the silk-screen point is a defect point according to the comparison result of the distance and the distance threshold value, so as to determine the defect point from the silk-screen points; constructing a pseudo-defect area according to the defect points, judging whether a real defect area exists in the pseudo-defect area, and if the real defect area does not exist in the pseudo-defect area, indicating that the silk-screen product is qualified; if the false defect area has a real defect area, respectively judging whether the gray average value of each real defect area is greater than a gray threshold, if so, indicating that the defect in the real defect area is a notch defect, and if not, indicating that the defect in the real defect area is a burr defect.

In order to better understand the technical solutions of the embodiments of the present invention, another alternative example is provided herein. Exemplarily, referring to fig. 8, image acquisition is performed on a silk-screen product, preprocessing for removing reflective dots is performed on an acquired silk-screen image, a silk-screen edge is extracted from the preprocessed silk-screen image, a filtering edge is obtained after filtering the silk-screen edge, and the silk-screen edge and the filtering edge are analyzed to determine whether the silk-screen edge has defects; if the defect exists, classifying the real defect area where the defect exists, and finishing the defect detection process after the classification is finished; if the defects do not exist, judging whether the photographing of the silk-screen product needing the defect detection is finished, if the photographing is finished, finishing the defect detection process, and if the photographing is not finished, carrying out image acquisition on the silk-screen product again.

Example four

Fig. 9 is a block diagram of a defect detection apparatus according to a fourth embodiment of the present invention, which is configured to execute the defect detection method according to any of the above embodiments. The apparatus and the defect detecting method of the above embodiments belong to the same inventive concept, and details that are not described in detail in the embodiments of the defect detecting apparatus may refer to the embodiments of the defect detecting method. Referring to fig. 9, the apparatus may specifically include: a silk-screen edge extraction module 410, a filtering edge obtaining module 420, a defect point determination module 430 and a defect detection module 440.

The silk-screen edge extraction module 410 is configured to, for a silk-screen product with a silk-screen edge detection requirement, obtain a silk-screen image generated after image acquisition is performed on the silk-screen product, and extract a silk-screen edge from the silk-screen image;

a filtering edge obtaining module 420, configured to filter the silk-screen edge to obtain a filtering edge, where there are filtering points on the filtering edge that correspond to each silk-screen point on the silk-screen edge, respectively;

the defective point determining module 430 is configured to determine, for each silk-screen point, a distance between a filtering point corresponding to the silk-screen point and the silk-screen point, and determine whether the silk-screen point is a defective point according to the distance;

and the defect detection module 440 is configured to detect whether a defect exists on the silk-screen edge according to whether each silk-screen point is a defective point.

Optionally, the defect detecting module 440 may include:

a pseudo-defect region obtaining unit, configured to extract at least one defect point from each silk-screen point according to whether each silk-screen point is a defect point, and construct at least one pseudo-defect region according to the at least one defect point;

a real defect region determining unit, configured to determine, for each pseudo defect region, whether the pseudo defect region is a real defect region according to a region area and/or a region size of the pseudo defect region;

and the defect detection unit is used for detecting whether the silk-screen edge has defects or not according to whether each pseudo-defect area is a real defect area or not.

On the basis of the above scheme, optionally, the defect detection apparatus may further include:

the serial number acquisition module is used for respectively acquiring the serial number of each silk-screen point, wherein the serial number of each silk-screen point is used for representing the position of the silk-screen point on the silk-screen edge;

the pseudo-defect region deriving unit may include:

a defect group determining subunit, configured to determine at least one defect group from the at least one defect point, where serial numbers of the defect points in each defect group are connected;

and the pseudo-defect area constructing subunit is used for constructing and obtaining a pseudo-defect area based on each defect point in each defect group aiming at each defect group.

On the basis of the above scheme, optionally, the defect detection apparatus may further include:

the defect position determining module is used for determining that the defects on the silk-screen edge are positioned in the real defect area under the condition that the defects on the silk-screen edge are detected;

and the defect type determining module is used for obtaining a gray average value of the real defect area according to the gray values of all the area points in the real defect area and determining the defect type corresponding to the real defect area based on the gray average value.

On the basis of the foregoing scheme, optionally, the defect type determining module may include:

a gray threshold value obtaining unit for obtaining a preset gray threshold value;

and the defect type determining unit is used for determining the defect type corresponding to the real defect area as a notch defect under the condition that the gray average value is greater than or equal to the gray threshold value, otherwise, determining the defect type as a burr defect.

Optionally, the silk-screen edge extracting module 410 may include:

the drawing line extracting unit is used for extracting drawing lines from the silk-screen image, wherein the drawing lines comprise lines drawn along silk-screen edges to be extracted from the silk-screen image after the silk-screen image is generated;

the silk-screen point determining unit is used for traversing pixel points on a silk-screen image along a normal direction by taking the drawing points as starting points for each drawing point on the drawing line, and determining the silk-screen points from the pixel points, wherein the normal direction is a direction which faces to the silk-screen edge and is vertical to the drawing line;

and the silk-screen edge extraction unit is used for connecting all the silk-screen points to form an edge as the extracted silk-screen edge.

On the basis of the foregoing scheme, optionally, the silk-screen dot determining unit may include:

a gray difference value calculating subunit, configured to calculate, for each current point in each pixel point, an absolute value of a gray difference value between a gray value of the current point and a gray value of an adjacent point, where the adjacent point is a pixel point, which is traversed after the current point and is adjacent to the current point, in each pixel point;

and the silk-screen point is used as a subunit and is used for taking the current point corresponding to the maximum absolute value as the silk-screen point.

According to the defect detection device provided by the fourth embodiment of the invention, aiming at a silk-screen product with a silk-screen edge detection requirement, a silk-screen image generated after image acquisition is carried out on the silk-screen product is obtained through the silk-screen edge extraction module, and a silk-screen edge is extracted from the silk-screen image; filtering the silk-screen edge through a filtering edge obtaining module to obtain a filtering edge, wherein filtering points respectively corresponding to all the silk-screen points on the silk-screen edge exist on the filtering edge; then, determining the distance between a filtering point corresponding to the silk-screen printing point and the silk-screen printing point by a defect point determining module aiming at each silk-screen printing point, and determining whether the silk-screen printing point is a defect point according to the distance; and detecting whether the silk-screen edge has defects or not through a defect detection module according to whether each silk-screen point is a defective point or not. According to the device provided by the embodiment of the invention, the defect points are determined according to the silk-screen points on the silk-screen edge and the filter points on the filter edge, and then the defects of the silk-screen edge are detected according to the defect points, so that whether the defects exist on the silk-screen edge can be automatically detected according to the silk-screen edge of a silk-screen product, and the effect of quickly and accurately detecting the silk-screen defects is achieved.

The defect detection device provided by the embodiment of the invention can execute the defect detection method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.

It should be noted that, in the embodiment of the defect detection apparatus, the included units and modules are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; 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.

EXAMPLE five

FIG. 10 illustrates a block diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 10, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM13, various programs and data necessary for the operation of the electronic apparatus 10 may also be stored. The processor 11, the ROM12, and the RAM13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The processor 11 performs the various methods and processes described above, such as the defect detection method.

In some embodiments, the defect detection method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM12 and/or the communication unit 19. When the computer program is loaded into the RAM13 and executed by the processor 11, one or more steps of the defect detection method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the defect detection method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the Internet.

The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired result of the technical solution of the present invention can be achieved.

The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and 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, comprising:

acquiring a silk-screen image generated after image acquisition is carried out on a silk-screen product with a silk-screen edge detection requirement, and extracting a silk-screen edge from the silk-screen image;

filtering the silk-screen edge to obtain a filtering edge, wherein filtering points respectively corresponding to the silk-screen points on the silk-screen edge exist on the filtering edge;

for each silk-screen point, determining the distance between a filter point corresponding to the silk-screen point and the silk-screen point, and determining whether the silk-screen point is a defect point according to the distance;

and detecting whether the silk-screen edge has defects or not according to whether each silk-screen point is a defective point or not.

2. The method of claim 1, wherein the detecting whether the silk-screen edge has defects according to whether each silk-screen dot is a defective dot comprises:

extracting at least one defective point from each silk-screen point according to whether each silk-screen point is a defective point or not, and constructing at least one pseudo-defective area according to the at least one defective point;

for each pseudo-defect area, determining whether the pseudo-defect area is a real defect area according to the area and/or the area size of the pseudo-defect area;

and detecting whether the silk-screen edge has defects or not according to whether each pseudo-defect area is a real defect area or not.

3. The method of claim 2, further comprising:

respectively acquiring the serial number of each silk-screen point, wherein the serial number of each silk-screen point is used for representing the position of the silk-screen point on the silk-screen edge;

the constructing at least one pseudo-defect region according to the at least one defect point includes:

determining at least one defect group from the at least one defect point, wherein the serial numbers of the defect points in each defect group are connected;

and constructing a pseudo-defect area based on each defect point in each defect group aiming at each defect group.

4. The method of claim 2, further comprising:

determining that the defects on the silk-screen edge are located in the real defect area under the condition that the defects on the silk-screen edge are detected;

and obtaining a gray average value of the real defect area according to the gray value of each area point in the real defect area, and determining the defect type corresponding to the real defect area based on the gray average value.

5. The method of claim 4, wherein the determining the defect type corresponding to the real defect region based on the gray-scale mean comprises:

acquiring a preset gray threshold;

and under the condition that the gray average value is greater than or equal to the gray threshold value, the defect type corresponding to the real defect area is a notch defect, otherwise, the defect type is a burr defect.

6. The method of claim 1, wherein extracting the silkscreen edges from the silkscreen image comprises:

extracting a drawing line from the silk-screen image, wherein the drawing line comprises a line to be drawn along the silk-screen edge extracted from the silk-screen image after the silk-screen image is generated;

traversing pixel points on the silk-screen image along a normal direction by taking the drawing points as starting points for each drawing point on the drawing line, and determining the silk-screen point from each pixel point, wherein the normal direction is a direction which faces the silk-screen edge and is perpendicular to the drawing line;

and connecting all the silk-screen points to form an edge, and taking the edge as the extracted silk-screen edge.

7. The method of claim 6, wherein said determining said silkscreen dots from each of said pixel dots comprises:

calculating an absolute value of a gray difference between a gray value of the current point and a gray value of an adjacent point for each current point of the pixels, wherein the adjacent point is a pixel point which is traversed after the current point and is adjacent to the current point in the pixels;

and taking the current point corresponding to the maximum absolute value as the silk-screen point.

8. A defect detection apparatus, comprising:

the device comprises a silk-screen edge extraction module, a detection module and a control module, wherein the silk-screen edge extraction module is used for acquiring a silk-screen image generated after image acquisition is carried out on a silk-screen product with a silk-screen edge detection requirement and extracting a silk-screen edge from the silk-screen image;

a filtering edge obtaining module, configured to filter the screen printing edge to obtain a filtering edge, where filtering points respectively corresponding to the screen printing points on the screen printing edge exist on the filtering edge;

the defect point determining module is used for determining the distance between a filtering point corresponding to each silk-screen point and the silk-screen point and determining whether the silk-screen point is a defect point according to the distance;

and the defect detection module is used for detecting whether the silk-screen edge has defects or not according to whether each silk-screen point is a defective point or not.

9. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to perform the defect detection method of any one of claims 1-7.

10. A computer-readable storage medium storing computer instructions for causing a processor to perform the method of any one of claims 1-7 when executed.

Images