CN113674260A - SMT welding spot defect detection method - Google Patents
SMT welding spot defect detection method Download PDFInfo
- Publication number
- CN113674260A CN113674260A CN202110990192.5A CN202110990192A CN113674260A CN 113674260 A CN113674260 A CN 113674260A CN 202110990192 A CN202110990192 A CN 202110990192A CN 113674260 A CN113674260 A CN 113674260A
- Authority
- CN
- China
- Prior art keywords
- image
- neural network
- defect detection
- detection method
- smt
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003466 welding Methods 0.000 title claims abstract description 21
- 230000007547 defect Effects 0.000 title claims abstract description 19
- 238000001514 detection method Methods 0.000 title claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000003062 neural network model Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 230000002068 genetic effect Effects 0.000 claims description 6
- 238000005286 illumination Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 229910000679 solder Inorganic materials 0.000 description 3
- 238000005476 soldering Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 238000001303 quality assessment method Methods 0.000 description 2
- 239000011521 glass Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012887 quadratic function Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a SMT welding spot defect detection method, which comprises the following steps: step 1: collecting an original picture of an SMT welding spot to be detected by image collecting equipment; step 2: preprocessing the original picture; and step 3: calculating the gradient size and direction of each pixel point of the image obtained in the step 2 by using a direction gradient histogram method; and 4, step 4: counting and combining the gradient size and the gradient direction to obtain a corresponding characteristic point descriptor; the invention can effectively improve the detection precision.
Description
Technical Field
The invention relates to the technical field of defect detection, in particular to an SMT welding spot defect detection method.
Background
Currently, Surface Mount Technology (SMT) is the most popular technology and process in the electronic assembly industry, and is a circuit connection technology that mounts a leadless or short-lead surface-mounted device (SMC/SMD, hereinafter referred to as a chip device) on a surface of a Printed Circuit Board (PCB) or other substrate, and performs soldering assembly by means of reflow soldering or dip soldering.
However, at present, for the quality assessment of welding spots, a checking method is generally adopted: one is a visual inspection method, which inspects the quality of the welding spot by visual observation, and if disputed, the quality can be evaluated by using a magnifying glass with 10 times or more of magnification, and the method has larger error according to the appearance quality condition of the welding spot.
Therefore, how to provide a high-precision SMT solder joint defect detection method is an urgent problem to be solved by those skilled in the art.
Disclosure of Invention
In view of this, the invention provides a method for detecting SMT solder joint defects, aiming to improve the efficiency of print quality assessment.
In order to achieve the purpose, the invention adopts the following technical scheme:
a SMT welding spot defect detection method comprises the following steps:
step 1: collecting an original picture of an SMT welding spot to be detected by image collecting equipment;
step 2: preprocessing the original picture;
and step 3: calculating the gradient size and direction of each pixel point of the image obtained in the step 2 by using a direction gradient histogram method;
and 4, step 4: counting and combining the gradient size and the gradient direction to obtain a corresponding feature point descriptor;
and 5: detecting a spatial extreme value by a feature point descriptor, and preliminarily determining the position and the scale of a key point;
step 6: determining the positions and the scales of the key points, removing noise points and assigning direction parameters to each key point;
and 7: generating a feature vector by using the specified direction parameter;
and 8: and taking the characteristic vector as a training sample, putting the training sample into a BP neural network model for training, and outputting a defect detection result of the welding spot picture according to the sample to be detected.
Preferably, the step 8 specifically includes:
dividing an existing data set into a training set and a testing set;
and training the BP neural network model by using a training set, testing the BP neural network model by using a test set, and judging whether the BP neural network model meets the requirements.
Preferably, the step 2 comprises: the image is subjected to any one or more of gray level adjustment, filtering, noise reduction, edge extraction and segmentation, and the contrast of the image is adjusted.
Preferably, the step 4 comprises: the adjusting the contrast of the image in the step 2 and reducing the influence caused by the local shadow and illumination change of the image specifically includes:
normalizing the color space of the input image by adopting a Gamma correction method, adjusting the contrast of the image and reducing the influence caused by the local shadow and illumination change of the image;
and acquiring the normalized image gradient information to further obtain the contour information.
Preferably, the BP neural network model is a genetic algorithm improved based on a particle swarm algorithm to optimize an initial weight threshold of the BP neural network and establish a BP neural network prediction model of the improved genetic algorithm.
According to the technical scheme, compared with the prior art, the SMT welding spot defect detection method can accurately extract the welding spot image by using the image processing technology and SIFT image characteristics, improves the image processing precision, completes the quality evaluation of the welding spot image through the constructed BP neural network model, provides accurate judgment on whether the welding spot has a problem or not, and improves the processing efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a detailed flowchart of a SMT welding spot defect detection method provided by the present invention.
Detailed Description
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.
Referring to fig. 1, an embodiment of the present invention discloses a method for detecting an SMT solder joint defect, including:
step 1: collecting an original picture of an SMT welding spot to be detected by image collecting equipment;
step 2: preprocessing the original picture;
and step 3: calculating the gradient size and direction of each pixel point of the image obtained in the step 2 by using a direction gradient histogram method;
and 4, step 4: counting and combining the gradient size and the gradient direction of the pixel points to obtain corresponding feature point descriptors;
and 5: detecting a spatial extreme value by a feature point descriptor, and preliminarily determining the position and the scale of a key point;
step 6: determining the positions and the scales of the key points, removing noise points and assigning direction parameters to each key point;
and 7: generating a feature vector by using the specified direction parameter;
and 8: and taking the characteristic vector as a training sample, putting the training sample into a BP neural network model for training, and outputting a defect detection result of the welding spot picture according to the sample to be detected.
Specifically, the specific processes of the steps 2 to 7 are as follows:
carrying out scale transformation on the original image by using a Gaussian kernel to obtain a scale space representation sequence under the multi-scale of the image and generate a scale space;
accurately determining the position and the scale of the key point by fitting a three-dimensional quadratic function in a scale space;
assigning a direction parameter to each key point by using the gradient direction distribution characteristic of the neighborhood pixels of the key points;
each keypoint is described by 16 seed points of 4 × 4, so that 128 data can be generated for one keypoint, namely, a 128-dimensional SIFT feature vector is finally formed.
In a specific embodiment, the step 8 specifically includes:
dividing an existing data set into a training set and a testing set;
and training the BP neural network model by using a training set, testing the BP neural network model by using a test set, and judging whether the BP neural network model meets the requirements.
In a specific embodiment, the step 2 includes: the image is subjected to any one or more of gray level adjustment, filtering, noise reduction, edge extraction and segmentation, and the contrast of the image is adjusted.
In a specific embodiment, the step 4 includes: the adjusting the contrast of the image in the step 2 and reducing the influence caused by the local shadow and illumination change of the image specifically includes:
normalizing the color space of the input image by adopting a Gamma correction method, adjusting the contrast of the image and reducing the influence caused by the local shadow and illumination change of the image;
and acquiring the normalized image gradient information to further obtain the contour information.
In a specific embodiment, the BP neural network model is a genetic algorithm improved based on a particle swarm optimization to optimize an initial weight threshold of the BP neural network, and establish a BP neural network prediction model of the improved genetic algorithm.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (5)
1. A SMT welding spot defect detection method is characterized by comprising the following steps:
step 1: collecting an original picture of an SMT welding spot to be detected by image collecting equipment;
step 2: preprocessing the original picture;
and step 3: calculating the gradient size and direction of each pixel point of the image obtained in the step 2 by using a direction gradient histogram method;
and 4, step 4: counting and combining the gradient size and the gradient direction to obtain a corresponding feature point descriptor;
and 5: detecting a spatial extreme value by a feature point descriptor, and preliminarily determining the position and the scale of a key point;
step 6: determining the positions and the scales of the key points, removing noise points and assigning direction parameters to each key point;
and 7: generating a feature vector by using the specified direction parameter;
and 8: and taking the characteristic vector as a sample to be detected, putting the sample to be detected into a BP neural network model for training, and outputting a defect detection result of the welding spot picture according to the sample to be detected.
2. An SMT weld spot defect detection method according to claim 1, wherein the step 8 specifically comprises:
dividing an existing data set into a training set and a testing set;
and training the BP neural network model by using a training set, testing the BP neural network model by using a test set, and judging whether the BP neural network model meets the requirements.
3. An SMT weld spot defect detection method according to claim 2, wherein the step 2 comprises: the image is subjected to any one or more of gray level adjustment, filtering, noise reduction, edge extraction and segmentation, and the contrast of the image is adjusted.
4. An SMT weld spot defect detection method according to claim 3, wherein the step 4 comprises: the adjusting the contrast of the image in the step 2 and reducing the influence caused by the local shadow and illumination change of the image specifically includes:
normalizing the color space of the input image by adopting a Gamma correction method, adjusting the contrast of the image and reducing the influence caused by the local shadow and illumination change of the image;
and acquiring the normalized image gradient information to further obtain the contour information.
5. An SMT weld spot defect detection method according to claim 3, wherein the BP neural network model is a genetic algorithm improved based on a particle swarm optimization to optimize an initial weight threshold of the BP neural network and establish a BP neural network prediction model of the improved genetic algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110990192.5A CN113674260A (en) | 2021-08-26 | 2021-08-26 | SMT welding spot defect detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110990192.5A CN113674260A (en) | 2021-08-26 | 2021-08-26 | SMT welding spot defect detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113674260A true CN113674260A (en) | 2021-11-19 |
Family
ID=78546818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110990192.5A Pending CN113674260A (en) | 2021-08-26 | 2021-08-26 | SMT welding spot defect detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113674260A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114998356A (en) * | 2022-08-08 | 2022-09-02 | 山东恩信特种车辆制造有限公司 | Axle defect detection method based on image processing |
| CN115018833A (en) * | 2022-08-05 | 2022-09-06 | 山东鲁芯之光半导体制造有限公司 | Processing defect detection method of semiconductor device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101819680A (en) * | 2010-05-12 | 2010-09-01 | 上海交通大学 | Detection method of picture matching point pair |
| CN103077512A (en) * | 2012-10-18 | 2013-05-01 | 北京工业大学 | Feature extraction and matching method and device for digital image based on PCA (principal component analysis) |
| US20180001426A1 (en) * | 2012-12-18 | 2018-01-04 | Senju Metal Industry Co., Ltd. | Lead-free solder alloy |
| CN111145175A (en) * | 2020-01-10 | 2020-05-12 | 惠州光弘科技股份有限公司 | SMT welding spot defect detection method based on iForest model verification |
| CN113298146A (en) * | 2021-05-25 | 2021-08-24 | 上海海洋大学 | Image matching method, device, equipment and medium based on feature detection |
-
2021
- 2021-08-26 CN CN202110990192.5A patent/CN113674260A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101819680A (en) * | 2010-05-12 | 2010-09-01 | 上海交通大学 | Detection method of picture matching point pair |
| CN103077512A (en) * | 2012-10-18 | 2013-05-01 | 北京工业大学 | Feature extraction and matching method and device for digital image based on PCA (principal component analysis) |
| US20180001426A1 (en) * | 2012-12-18 | 2018-01-04 | Senju Metal Industry Co., Ltd. | Lead-free solder alloy |
| CN111145175A (en) * | 2020-01-10 | 2020-05-12 | 惠州光弘科技股份有限公司 | SMT welding spot defect detection method based on iForest model verification |
| CN113298146A (en) * | 2021-05-25 | 2021-08-24 | 上海海洋大学 | Image matching method, device, equipment and medium based on feature detection |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115018833A (en) * | 2022-08-05 | 2022-09-06 | 山东鲁芯之光半导体制造有限公司 | Processing defect detection method of semiconductor device |
| CN115018833B (en) * | 2022-08-05 | 2022-11-04 | 山东鲁芯之光半导体制造有限公司 | Processing defect detection method of semiconductor device |
| CN114998356A (en) * | 2022-08-08 | 2022-09-02 | 山东恩信特种车辆制造有限公司 | Axle defect detection method based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111145175B (en) | SMT welding spot defect detection method based on iForest model verification | |
| CN107945184B (en) | Surface-mounted component detection method based on color image segmentation and gradient projection positioning | |
| CN109472271B (en) | Printed circuit board image contour extraction method and device | |
| CN106501272B (en) | Machine vision soldering tin positioning detection system | |
| CN113674260A (en) | SMT welding spot defect detection method | |
| EP1675067A2 (en) | Image processing method, substrate inspection method, substrate inspection apparatus and method of generating substrate inspection data | |
| CN111899241A (en) | Quantitative on-line detection method and system for defects of PCB (printed Circuit Board) patches in front of furnace | |
| CN110473165A (en) | A kind of welding quality of circuit board detection method and device | |
| CN111681235B (en) | IC welding spot defect detection method based on learning mechanism | |
| CN114998314B (en) | PCB defect detection method based on computer vision | |
| CN115880288B (en) | Detection method, system and computer equipment for electronic element welding | |
| CN115294114A (en) | Quality detection method based on ECU circuit welding | |
| CN114092448B (en) | Plug-in electrolytic capacitor mixed detection method based on deep learning | |
| CN116168218A (en) | Circuit board fault diagnosis method based on image recognition technology | |
| CN114862817A (en) | Circuit board golden finger area defect detection method, system, device and medium | |
| CN111882547A (en) | PCB missing part detection method based on neural network | |
| CN116337869A (en) | Machine vision-based detection system for production of double-sided circuit board | |
| CN115170497A (en) | PCBA online detection platform based on AI visual detection technology | |
| CN116993725B (en) | Intelligent patch information processing system of flexible circuit board | |
| CN114445410A (en) | Circuit board detection method based on image recognition, computer and readable storage medium | |
| CN115719326A (en) | PCB defect detection method and device | |
| CN117825931A (en) | Intelligent automatic processing method and device in PCB circuit quality inspection | |
| Cai et al. | PCB defect detection system based on image processing | |
| CN116993654B (en) | Camera module defect detection method, device, equipment, storage medium and product | |
| CN114926417B (en) | Microscopic imaging detection method and system for weak scratches on surface of high-density flexible FPC |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |