WO2017032308A1

WO2017032308A1 - Pcb board detection method and apparatus

Info

Publication number: WO2017032308A1
Application number: PCT/CN2016/096546
Authority: WO
Inventors: 杨铭
Original assignee: 广州视源电子科技股份有限公司
Priority date: 2015-08-25
Filing date: 2016-08-24
Publication date: 2017-03-02
Also published as: CN105139397B; CN105139397A

Abstract

A PCB board detection method comprises the following steps: acquiring an image of a specified region (10) on a conveyance surface of a conveyor belt (S201); processing the image by using a Canny operator to obtain an edge image, the Canny operator comprising two parameters: a high threshold and a low threshold, and the high threshold and the low threshold being adaptively generated according to pixel information of the image (S203); counting the number of non-zero pixels in the edge image (S204); and detecting, according to a magnitude relationship between the number of non-zero pixels and at least one of the preset thresholds, a degree of entrance of the PCB board (20) into the specified region (10) (S205). The technical solutions also comprise a PCB board detection apparatus. The PCB board detection method and apparatus have strong robustness, improve efficiency and quality of PCB detection, and realize high automation of PCB detection.

Description

PCB board detecting method and device

Technical field

The invention relates to the field of automatic optical inspection of PCBs, in particular to a device for detecting PCB boards.

Background technique

The use of Automatic Optical Inspection (AOI) as a means of PCB detection has become a trend. The technology mainly includes four steps: image acquisition, image processing, feature extraction and decision-making. In the step of image processing, it is often necessary to perform preliminary analysis on the collected original image to determine whether the original image contains complete PCB boards, which play a vital role in improving the efficiency and quality of PCB inspection. However, the existing image processing schemes often have problems such as low robustness, slow calculation speed, and complicated operation, which cannot meet the requirements for use.

Summary of the invention

In view of the above problems, an object of the present invention is to provide a PCB board detecting method and device, which realizes fast and accurate PCB board testing and satisfies the use requirements.

Embodiments of the present invention provide a PCB board detecting method, including the following steps:

Acquiring an image of a designated area on the conveying surface of the conveyor belt;

The image is processed by using a Canny operator to obtain an edge image, wherein the Canny operator includes two parameters of a high threshold and a low threshold, and the high threshold and the low threshold are adaptively generated according to pixel information of the image;

Counting the number of non-zero pixels in the edge image;

And detecting, by the relationship between the number of the non-zero pixels and the at least one preset threshold, the extent to which the PCB board enters the designated area.

As an improvement of the foregoing solution, after the image of the area is specified on the transmission surface of the collection conveyor, before the image is processed by the Canny operator to obtain the edge image, the method further includes:

The size of the image is normalized.

As a modification of the above solution, the image is processed by using a Canny operator to obtain an edge image, wherein the Canny operator includes two parameters of a high threshold and a low threshold, and the high threshold and the low threshold are according to the The pixel information of the image is adaptively generated, and specifically includes:

Obtaining a pixel value range of the image, wherein the pixel takes a value range of [I _min , I _max ];

Calculating a pixel median value m of the image, wherein the pixel median value m is a pixel value in which the serial number is in the middle after the pixel values of the image are sorted by size;

Generating the high threshold and the low threshold, wherein the high threshold takes the smaller of I _max and (1 + σ) * m; the low threshold takes I _min and (1 - σ) * m The larger of them, σ is an empirical parameter;

The image is processed using the high threshold and the low threshold as threshold parameters of the Canny operator to obtain an edge image.

As a modification of the above scheme, the empirical parameter σ takes a value of 0.33.

As an improvement of the foregoing solution, the counting the number of non-zero pixels in the edge image includes:

The pixels in the edge image are traversed, the pixels whose pixel values are not zero are marked as non-zero pixels, and the number of non-zero pixels is counted.

As a modification of the foregoing solution, the detecting the extent to which the PCB board enters the designated area according to the relationship between the number of the non-zero pixels and the at least one preset threshold is:

When it is determined that the number of non-zero pixels in the edge image is less than the first threshold, it is determined that the PCB board is located outside the designated area.

As a modification of the above aspect, the designated area includes a boundary area, wherein the boundary area is a point in the specified area that a minimum distance to two sides perpendicular to a traveling direction of the conveyor belt is less than or equal to a predetermined length The area formed;

Then counting the number of non-zero pixels in the edge image is:

Counting the number of non-zero pixels in the edge image corresponding to the boundary region;

The detecting the extent to which the PCB board enters the designated area according to the relationship between the number of the non-zero pixels and the at least one preset threshold is:

When it is determined that the number of non-zero pixels in the edge image corresponding to the boundary region is greater than a preset second threshold, determining that the PCB board portion enters the designated region.

As a modification of the above aspect, the designated area further includes an inner area, the inner area being an area other than the boundary area in the designated area;

Then counting the number of non-zero pixels in the edge image is:

Statistically counting the number of non-zero pixels in the edge image corresponding to the boundary region and the number of non-zero pixels in the edge image corresponding to the internal region;

When it is determined that the number of non-zero pixels in the edge image corresponding to the inner region is greater than a preset third threshold, and the number of non-zero pixels in the edge image corresponding to the boundary region is less than a preset fourth At the threshold, it is determined that the PCB board completely enters the designated area.

The invention also provides a PCB board detecting device, comprising:

An acquisition unit for collecting an image of a designated area on a conveying surface of the conveyor belt;

An image processing unit, configured to process the image by using a Canny operator to obtain an edge image, wherein the Canny operator includes two parameters of a high threshold and a low threshold, and the high threshold and the low threshold are according to the image Pixel information adaptive generation;

a statistical unit, configured to count the number of non-zero pixels in the edge image;

And a detecting unit, configured to detect, according to a magnitude relationship between the number of the non-zero pixels and the at least one preset threshold, the extent to which the PCB board enters the designated area.

As an improvement of the above solution, the PCB board detecting device further includes:

A normalization unit for normalizing the size of the image.

As an improvement of the foregoing solution, the image processing unit specifically includes:

a pixel acquisition unit, configured to acquire a pixel value range of the image, where the pixel value range is [I _min , I _max ];

a calculating unit, configured to calculate a pixel median value m of the image, wherein the pixel median value m is a pixel value in which the serial number is in the middle after the respective pixel values of the image are sorted by size;

a threshold generating unit, configured to generate the high threshold and a low threshold, wherein the high threshold takes a smaller one of I _max and (1+σ)*m; the low threshold takes I _min and (1) The larger of -σ)*m, σ is an empirical parameter;

And a processing unit, configured to process the image by using the high threshold and the low threshold as a threshold parameter of the Canny operator to obtain an edge image.

The statistic unit is specifically configured to: count the number of non-zero pixels in the edge image corresponding to the boundary area;

The detecting unit is configured to determine that the PCB board portion enters the designated area when determining that the number of non-zero pixels in the edge image corresponding to the boundary area is greater than a preset second threshold.

As a modification of the above aspect, the designated area further includes an inner area, wherein the inner area is an area other than the boundary area in the designated area;

The statistic unit is specifically configured to separately count the number of non-zero pixels of the edge image corresponding to the inner region and the edge image corresponding to the boundary region;

The detecting unit is configured to: determine that the number of non-zero pixels in the edge image corresponding to the inner region is greater than a preset third threshold, and the non-zero pixels in the edge image corresponding to the boundary region When the number is less than the preset fourth threshold, it is determined that the PCB board completely enters the designated area.

The method and device for detecting a PCB board according to an embodiment of the present invention use an adaptive Canny operator to analyze an image of a specified area on a transmission surface of a conveyor belt, and detect the extent to which the PCB board enters a designated area, and determine that the PCB board completely enters. The image of the designated area, thereby filtering out unnecessary invalid images for subsequent processing, improving the speed and accuracy of PCB detection. Since the edge detection parameter of the adaptive Canny operator is adaptively generated according to the pixel information of the image, no manual basis is needed. The body condition adjustment parameters are highly robust and achieve a high degree of automation of PCB inspection.

DRAWINGS

In order to more clearly illustrate the technical solutions of the present invention, the drawings used in the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present invention, which are common in the art. For the skilled person, other drawings can be obtained from these drawings without any creative work.

FIG. 1 is a schematic flow chart of a PCB board detecting method according to a first embodiment of the present invention.

2 is a schematic view of a portion of a PCB board provided in a first embodiment of the present invention entering a designated area.

FIG. 3 is a schematic diagram of the PCB board provided in the first embodiment of the present invention completely entering a designated area.

4 is a schematic diagram of a PCB board according to a first embodiment of the present invention that has not entered or has left a designated area.

FIG. 5 is a schematic flow chart of a PCB board detecting method according to a second embodiment of the present invention.

FIG. 6 is a schematic structural diagram of a PCB board detecting apparatus according to a third embodiment of the present invention.

FIG. 7 is a schematic structural diagram of the image processing unit shown in FIG. 6.

FIG. 8 is a schematic structural diagram of a PCB board detecting apparatus according to a fourth embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

Embodiments of the present invention provide a PCB board detecting method and apparatus for detecting the extent to which a PCB board enters an image acquisition field of view, and improving the efficiency and quality of automatic optical inspection of the PCB. A detailed description will be given below.

Referring to FIG. 1 , a first embodiment of the present invention provides a PCB board detecting method. The PCB board detecting method is implemented by a PCB board detecting device, and includes at least the following steps:

S101. Acquire an image of a designated area on a conveying surface of the conveyor belt.

In the embodiment of the present invention, the conveyor belt can continuously transport the PCB board along a certain transmission direction, and the PCB board detecting device collects the image of the PCB board in the transportation. Specifically, the PCB board detecting device includes a camera. The camera is mounted above the conveyor belt and acquires an image of a designated area on the conveying surface in real time, wherein the image may be a color image or a black and white image. Since the PCB board is constantly moving relative to the camera, a PCB board portion may enter the designated area in the image of the designated area collected by the camera, and the PCB board completely enters the designated area. Or, the PCB board does not enter or has left the designated area and the like.

S102. The image is processed by using a Canny operator to obtain an edge image, where the Canny operator includes two parameters of a high threshold and a low threshold, and the high threshold and the low threshold are adaptive according to pixel information of the image. generate.

In the embodiment of the present invention, the Canny operator is generally used for detecting edge of an image. However, the high threshold and the low threshold of the traditional Canny operator are preset, and cannot be customized according to the current situation of the image. Adapt to the adjustment.

In the embodiment of the present invention, the PCB board detecting apparatus adopts an adaptive edge detection strategy, and automatically generates appropriate high thresholds and low thresholds according to pixel information of the image, thereby providing a preferred threshold for the Canny operator. Parameter, specifically,

First, the pixel value range of the image is obtained.

In the embodiment of the present invention, the PCB board detecting device acquires a gray value of each pixel of the image, and reads a maximum value I _max and a minimum value I _min from the gray values. The pixel value range is labeled as [I _min , I _max ].

Then, a pixel median value m of the image is calculated, wherein the pixel median value m is a pixel value in which the serial number is in the middle after the respective pixel values of the image are sorted by size.

Next, the high threshold t _high and the low threshold t _{low are} generated, wherein the high threshold t _high takes the smaller of I _max and (1+σ)*m, and the low threshold t _low takes I The larger of _min and (1-σ)*m.

In the embodiment of the present invention, the high threshold t _high takes the smaller of I _max and (1+σ)*m, and the low threshold t _low takes I _min and (1-σ)*m The larger of them is t _high =min(I _max ,(1+σ)*m), t _low =max(I _min ,(1-σ)*m), and σ is an empirical parameter.

In the embodiment of the present invention, preferably, the empirical parameter σ takes a value of 0.33. It is to be understood that the empirical parameter σ may also have a value of 0.2, 0.3, 0.4 or any other suitable value, which may be set according to actual needs, and is not specifically limited in the present invention.

Finally, the image is processed using the high threshold and the low threshold as threshold parameters of the Canny operator to obtain an edge image.

Specifically, in the embodiment of the present invention, the PCB board detecting apparatus processes the image by using the high threshold and the low threshold as threshold parameters of the Canny operator to obtain an edge image. The process of processing the edge image by the canny operator can refer to the calculation principle of the Canny operator, and the present invention is not described herein.

S103. Count the number of non-zero pixels in the edge image.

In the embodiment of the present invention, the PCB board detecting device traverses all the pixels in the edge image, and marks the pixels whose pixel values are not zero as non-zero pixels, and counts the number of the non-zero pixels.

S104. Detect the extent to which the PCB board enters the designated area according to the relationship between the number of the non-zero pixels and the at least one preset threshold.

In the embodiment of the present invention, the relationship between the PCB board and the designated area may include not entering or leaving, partially entering, and fully entering. The following embodiments of the present invention will be described one by one.

Please refer to FIG. 2 together for the judgment that the PCB board 20 has not entered or has left the designated area 10:

In the embodiment of the present invention, the PCB board detecting device counts the number of non-zero pixels in the edge image corresponding to the designated area 10, and respectively compares the number of non-zero pixels in the edge image with The first threshold is compared, and when the number of non-zero pixels in the edge image is less than the first threshold, it is determined that the PCB board 20 has not entered or has left the designated area 10, wherein Narrative A threshold can be zero, or a value close to zero.

Please refer to FIG. 3 together for the determination that the PCB board 20 partially enters the designated area 10: the designated area 10 includes a boundary area 11, wherein the boundary area 11 is within the designated area 10. An area composed of points having a minimum distance of two sides perpendicular to the advancing direction of the conveyor belt being less than or equal to a predetermined length, for example, the preset length may be set to one tenth of the width of the designated area Or one in twenty. After the PCB board detecting device counts the number of non-zero pixels in the edge image corresponding to the boundary region 11, the number of non-zero pixels in the edge image corresponding to the boundary region 11 is preset with The two thresholds are compared. When the number of non-zero pixels in the edge image corresponding to the boundary region 11 is greater than the second threshold, it is determined that the PCB board 20 partially enters the designated area 10.

Please refer to FIG. 4 together for the judgment that the PCB board 20 completely enters the designated area 10:

In the embodiment of the present invention, the designated area 10 may further include an inner area 12, wherein the inner area 12 is an area other than the boundary area 11 in the designated area 10. The PCB board detecting device separately counts the number of non-zero pixels in the edge image corresponding to the inner region 12 and the edge image corresponding to the boundary region 11, and respectively respectively outputs the edge image corresponding to the inner region 12 The number of non-zero pixels in the comparison is compared with a preset third threshold, and the number of non-zero pixels in the edge image corresponding to the boundary region 11 is compared with a preset fourth threshold. When the number of non-zero pixels in the edge image corresponding to the inner region 12 is greater than the third threshold, and the number of non-zero pixels in the edge image corresponding to the boundary region 11 is less than the fourth threshold At this time, it is determined that the PCB board 20 completely enters the designated area 10.

The method for detecting a PCB board according to an embodiment of the present invention uses an adaptive Canny operator to analyze an image of a specified area on a transmission surface of the conveyor belt, and detects the extent to which the PCB board enters the designated area, and determines that the PCB board completely enters the Specify an image of the area to filter out unnecessary invalid images for subsequent processing, improving the speed and accuracy of PCB inspection. Since the edge detection parameter of the adaptive Canny operator is adaptively generated according to the pixel information of the image, it is not necessary to manually adjust parameters according to specific conditions, and has strong robustness, and achieves high automation of PCB detection.

Please refer to FIG. 5. FIG. 5 is a schematic flowchart diagram of a PCB detecting method according to a second embodiment of the present invention. The PCB board detection method includes:

S201. Acquire an image of a designated area on a conveying surface of the conveyor belt.

S202: normalize the size of the image.

In the embodiment of the present invention, the PCB board detecting device may first downsample the image and reduce the image resolution to a predetermined size, wherein the predetermined size may be to keep the height pixel value of the image unchanged. , reducing the width pixel value to a preset threshold, or maintaining the width pixel value of the image unchanged, reducing the height pixel value to a preset threshold, or simultaneously reducing the width and height pixel values of the image to a preset threshold, which may be The actual needs are set, and the present invention is not specifically limited.

S203. The image is processed by using a Canny operator to obtain an edge image, where the Canny operator includes two parameters of a high threshold and a low threshold, and the high threshold and the low threshold are adaptive according to pixel information of the image. generate.

S204. Count the number of non-zero pixels in the edge image.

S205. Detect a degree of entering the PCB into the designated area according to a size relationship between the number of the non-zero pixels and the at least one preset threshold.

The PCB board detecting method provided by the embodiment of the invention reduces the image normalized processing by downsampling the collected image, thereby improving the detection efficiency.

Please refer to FIG. 6. FIG. 6 is a schematic structural diagram of a PCB board detecting apparatus according to a third embodiment of the present invention. The PCB board detecting device 300 includes an acquiring unit 310, an image processing unit 320, a statistic unit 330, and a detecting unit 340, wherein:

The collecting unit 310 is configured to collect an image of a designated area on a conveying surface of the conveyor belt.

The image processing unit 320 is configured to process the image by using a Canny operator to obtain an edge image, where the Canny operator includes two parameters of a high threshold and a low threshold, and the high threshold and the low threshold are according to the The pixel information of the image is adaptively generated.

Referring to FIG. 6, in the embodiment of the present invention, the image processing unit 320 includes:

The pixel obtaining unit 321 is configured to acquire a pixel value range of the image, where the pixel value ranges from [I _min , I _max ].

The calculating unit 322 is configured to calculate a pixel median value m of the image, wherein the pixel median value m is a pixel value in which the serial number is in the middle after the respective pixel values of the image are sorted by size.

The threshold generating unit 323 is configured to generate the high threshold and the low threshold, wherein the high threshold takes a smaller one of I _max and (1+σ)*m; the low threshold takes I _min and ( The larger of the two 1-σ)*m, σ is the empirical parameter.

The processing unit 324 is configured to process the image by using the high threshold and the low threshold as a threshold parameter of the Canny operator to obtain an edge image, where the edge image includes a first edge image and a second edge image The high threshold is applied to the image to obtain the first edge image, and the low threshold is applied to the image to obtain the second edge image.

The statistic unit 330 is configured to count the number of non-zero pixels in the edge image.

The detecting unit 340 is configured to detect, according to the size relationship between the number of the non-zero pixels and the at least one preset threshold, the extent to which the PCB board enters the designated area.

In the embodiment of the present invention, the relationship between the PCB board and the designated area may include not entering or leaving, partially entering, and fully entering, and the following description will be made one by one in the embodiment of the present invention.

In the embodiment of the present invention, after the statistics unit 330 counts the number of non-zero pixels in the edge image corresponding to the designated area 10, the detecting unit 340 selects the non-zero pixels in the edge image corresponding to the designated area 10. The number of zero pixels is compared with a preset first threshold. When the number of non-zero pixels in the edge image corresponding to the designated area 10 is less than the first threshold, the detecting unit 340 determines the The PCB board 20 has not entered or has left the designated area 10, wherein the first threshold may be zero, or a value close to zero.

Please refer to FIG. 3 together for the judgment that the PCB board 20 partially enters the designated area 10:

The designated area 10 includes a boundary area 11 , wherein the boundary area 11 is composed of points in the designated area 10 that have a minimum distance to two sides perpendicular to the traveling direction of the conveyor belt that is less than or equal to a predetermined length. The area, for example, may set the preset length to one tenth or one-twentieth of the width of the designated area, and the like. After the statistic unit 330 counts the number of non-zero pixels in the edge image corresponding to the boundary region 11, the detecting unit 340 compares the number of non-zero pixels in the edge image corresponding to the boundary region 11 with The second threshold is set for comparison. When the number of non-zero pixels in the edge image corresponding to the boundary region 11 is greater than the second threshold, the detecting unit 340 determines that the PCB board 20 partially enters the designated region 10.

In the embodiment of the present invention, the designated area 10 may further include an inner area 12, wherein the inner area 12 is an area other than the boundary area 11 in the designated area 10. After the statistic unit 330 separately counts the edge image corresponding to the inner region 12 and the number of non-zero pixels of the edge image corresponding to the boundary region 11, the detecting unit 340 respectively respectively the edge corresponding to the inner region 12 The number of non-zero pixels in the image is compared with a preset third threshold, and the number of non-zero pixels in the edge image corresponding to the boundary region 11 is compared with a preset fourth threshold. When the number of non-zero pixels in the edge image corresponding to the inner region 12 is greater than the third threshold, and the number of non-zero pixels in the edge image corresponding to the boundary region 11 is less than the fourth threshold The detecting unit 340 determines that the PCB board 20 completely enters the designated area 10.

The PCB board detecting apparatus 300 provided by the embodiment of the present invention processes the image collected by the collecting unit 310 by the image processing unit 320 to obtain an edge image, and then uses the statistical unit 330 to count the image processing unit 320. The number of non-zero pixels of the edge image is detected by the detecting unit 340 to the extent that the PCB board enters the image capturing field of view, and the image of the PCB board completely enters the image capturing field of view is determined, thereby filtering unnecessary portions for subsequent processing. Invalid images improve the speed and accuracy of PCB inspection. Since the edge detection parameter of the adaptive Canny operator adopted by the image processing unit 320 is adaptively generated according to the pixel information of the image, it is not necessary to manually adjust parameters according to specific conditions, and has strong robustness and realizes PCB. The detection is highly automated.

Please refer to FIG. 8. FIG. 8 is a schematic structural diagram of a PCB board detecting apparatus according to a fourth embodiment of the present invention. The PCB board detecting apparatus 400 includes an acquiring unit 410, a normalization unit 420, an image processing unit 430, a statistics unit 440, and a detecting unit 450, wherein:

The collecting unit 410 is configured to collect an image of a designated area on a conveying surface of the conveyor belt.

The normalization unit 420 is configured to normalize the size of the image.

In the embodiment of the present invention, the normalization unit 420 may first downsample the image of the collection unit 410 and reduce the image resolution to a predetermined size, wherein the predetermined size may be the height of the image. The pixel value is unchanged, the width pixel value is lowered to a preset threshold, or the width pixel value of the image is kept unchanged, the height pixel value is lowered to a preset threshold, or the image width and height pixel values are simultaneously lowered to a preset threshold. These can be set according to actual needs, and the invention is not specifically limited.

The image processing unit 430 is configured to process the image by using a Canny operator to obtain an edge image, where the Canny operator includes two parameters of a high threshold and a low threshold, and the high threshold and the low threshold are according to the The pixel information of the image is adaptively generated.

The statistics unit 440 is configured to count the number of non-zero pixels in the edge image.

The detecting unit 450 is configured to detect, according to the relationship between the number of the non-zero pixels and the at least one preset threshold, the extent to which the PCB board enters the designated area.

The PCB board detecting apparatus 400 provided by the embodiment of the present invention performs down-sampling on the image collected by the collecting unit 410 by the normalization unit 420, thereby realizing normalization processing of the image, and improving the detection efficiency.

In the description of the present specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" and the like means a specific feature described in connection with the embodiment or example. A structure, material or feature is included in at least one embodiment or example of the invention. In the present specification, the schematic representation of the above terms is not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. In addition, various embodiments or examples described in the specification, as well as features of various embodiments or examples, may be combined and combined.

Moreover, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" or "second" may include at least one of the features, either explicitly or implicitly. In the description of the present invention, the meaning of "a plurality" is at least two, such as two, three, etc., unless specifically defined otherwise.

Any process or method description in the flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a particular logical function or process. And the scope of the preferred embodiments of the invention includes additional implementations, in which the functions may be performed in a substantially simultaneous manner or in an opposite order depending on the functions involved, in the order shown or discussed. It will be understood by those skilled in the art to which the embodiments of the present invention pertain.

The logic and/or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer readable medium, Used in conjunction with, or in conjunction with, an instruction execution system, apparatus, or device (eg, a computer-based system, a system including a processor, or other system that can fetch instructions and execute instructions from an instruction execution system, apparatus, or device) Or use with equipment. For the purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the software for use by the instruction execution system, apparatus, or apparatus, or in conjunction with the instruction execution system, apparatus, or apparatus. More specific examples (non-exhaustive list) of computer readable media include the following: electrical connections (electronic devices) having one or more wires, portable computer disk cartridges (magnetic devices), random access memory (RAM), Read only memory (ROM), erasable editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM). In addition, the computer readable medium may even be a paper or other suitable medium on which the software may be printed, as it may be optically scanned, for example by paper or other medium, followed by editing, interpretation or, if appropriate, other suitable The method proceeds to obtain the software electronically and then store it in computer memory.

In the above-described embodiments, a plurality of steps or methods may be stored in a memory and understood by appropriate instructions, and portions of the invention may be implemented in hardware, software, firmware or a combination thereof. The software or firmware executed by the system is implemented. For example, if implemented in hardware, and in another implementation As in the formula, it can be implemented by any one of the following techniques known in the art or a combination thereof: a discrete logic circuit having logic gates for implementing logic functions on data signals, dedicated to suitable combinational logic gates Integrated circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

One of ordinary skill in the art can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by software to instruct related hardware, and the software can be stored in a computer readable storage medium. When executed, one or a combination of the steps of the method embodiments is included.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. The integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.

The above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like. Although the embodiments of the present invention have been shown and described, it is understood that the above-described embodiments are illustrative and are not to be construed as limiting the scope of the invention. The embodiments are subject to variations, modifications, substitutions and variations.

Claims

A method for detecting a PCB board, comprising the steps of:

Acquiring an image of a designated area on the conveying surface of the conveyor belt;

The image is processed by using a Canny operator to obtain an edge image, wherein the Canny operator includes two parameters of a high threshold and a low threshold, and the high threshold and the low threshold are adaptively generated according to pixel information of the image;

Counting the number of non-zero pixels in the edge image;

And detecting, by the relationship between the number of the non-zero pixels and the at least one preset threshold, the extent to which the PCB board enters the designated area.
The PCB board detecting method according to claim 1, wherein after the image of the area is specified on the conveying surface of the collecting conveyor, before the image is processed by the Canny operator to obtain an edge image, include:

The size of the image is normalized.
The PCB board detecting method according to claim 1, wherein the image is processed by using a Canny operator to obtain an edge image, wherein the Canny operator includes two parameters of a high threshold and a low threshold, and The high threshold and the low threshold are adaptively generated according to the pixel information of the image, and specifically include:

Obtaining a pixel value range of the image, wherein the pixel takes a value range of [I min , I max ];

Calculating a pixel median value m of the image, wherein the pixel median value m is a pixel value in which the serial number is in the middle after the pixel values of the image are sorted by size;

Generating the high threshold and the low threshold, wherein the high threshold takes the smaller of I max and (1 + σ) * m; the low threshold takes I min and (1 - σ) * m The larger of them, σ is an empirical parameter;

The image is processed using the high threshold and the low threshold as threshold parameters of the Canny operator to obtain an edge image.
The PCB board detecting method according to claim 3, wherein the empirical parameter σ has a value of 0.33.
The method for detecting a PCB according to claim 1, wherein the counting the number of non-zero pixels in the edge image comprises:

The pixels in the edge image are traversed, the pixels whose pixel values are not zero are marked as non-zero pixels, and the number of non-zero pixels is counted.
The PCB board detecting method according to claim 1, wherein the detecting the extent to which the PCB board enters the designated area according to the magnitude relationship of the number of the non-zero pixels and the at least one preset threshold ,for:

When it is determined that the number of non-zero pixels in the edge image is less than the first threshold, it is determined that the PCB board is located outside the designated area.
The PCB board detecting method according to claim 1, wherein the designated area includes a boundary area, wherein the boundary area is a minimum distance to two sides perpendicular to a traveling direction of the conveyor belt in the designated area An area consisting of points that are less than or equal to a predetermined length;

Then counting the number of non-zero pixels in the edge image is:

Counting the number of non-zero pixels in the edge image corresponding to the boundary region;

The detecting the extent to which the PCB board enters the designated area according to the relationship between the number of the non-zero pixels and the at least one preset threshold is:

When it is determined that the number of non-zero pixels in the edge image corresponding to the boundary region is greater than a preset second threshold, determining that the PCB board portion enters the designated region.
The PCB board detecting method according to claim 7, wherein the designated area further includes an inner area, wherein the inner area is an area other than the boundary area in the designated area;

Then counting the number of non-zero pixels in the edge image is:

Statistically counting the number of non-zero pixels in the edge image corresponding to the boundary region and the number of non-zero pixels in the edge image corresponding to the internal region;

The detecting the extent to which the PCB board enters the designated area according to the relationship between the number of the non-zero pixels and the at least one preset threshold is:

When it is determined that the number of non-zero pixels in the edge image corresponding to the inner region is greater than a preset third threshold, and the number of non-zero pixels in the edge image corresponding to the boundary region is less than a preset fourth At the threshold, it is determined that the PCB board completely enters the designated area.
A PCB board detecting device, comprising:

An acquisition unit for collecting an image of a designated area on a conveying surface of the conveyor belt;

An image processing unit, configured to process the image by using a Canny operator to obtain an edge image, wherein the Canny operator includes two parameters of a high threshold and a low threshold, and the high threshold and the low threshold are according to the image Pixel information adaptive generation;

a statistical unit, configured to count the number of non-zero pixels in the edge image;

And a detecting unit, configured to detect, according to a magnitude relationship between the number of the non-zero pixels and the at least one preset threshold, the extent to which the PCB board enters the designated area.
The PCB board detecting device according to claim 9, wherein the PCB board detecting device further comprises:

A normalization unit for normalizing the size of the image.
The PCB board detecting device according to claim 9, wherein the image processing unit specifically comprises:

a pixel acquisition unit, configured to acquire a pixel value range of the image, where the pixel value range is [I min , I max ];

a calculating unit, configured to calculate a pixel median value m of the image, wherein the pixel median value m is a pixel value in which the serial number is in the middle after the respective pixel values of the image are sorted by size;

a threshold generating unit, configured to generate the high threshold and a low threshold, wherein the high threshold takes a smaller one of I max and (1+σ)*m; the low threshold takes I min and (1) The larger of -σ)*m, σ is an empirical parameter;

And a processing unit, configured to process the image by using the high threshold and the low threshold as a threshold parameter of the Canny operator to obtain an edge image.
The PCB board detecting device according to claim 9, wherein the designated area includes a boundary area, wherein the boundary area is a minimum distance to two sides perpendicular to a traveling direction of the conveyor belt in the designated area An area consisting of points that are less than or equal to a predetermined length;

The statistic unit is specifically configured to: count the number of non-zero pixels in the edge image corresponding to the boundary area;

The detecting unit is configured to determine that the PCB board portion enters the designated area when determining that the number of non-zero pixels in the edge image corresponding to the boundary area is greater than a preset second threshold.
The PCB board detecting device according to claim 12, wherein the designated area further includes an inner area, wherein the inner area is an area other than the boundary area in the designated area;

The statistic unit is configured to separately count the edge image corresponding to the inner region and the number of non-zero pixels in the edge image corresponding to the boundary region;

The detecting unit is configured to: determine that the number of non-zero pixels in the edge image corresponding to the inner region is greater than a preset third threshold, and the non-zero pixels in the edge image corresponding to the boundary region When the number is less than the preset fourth threshold, it is determined that the PCB board completely enters the designated area.