CN111145164A - IC chip defect detection method based on artificial intelligence - Google Patents
IC chip defect detection method based on artificial intelligence Download PDFInfo
- Publication number
- CN111145164A CN111145164A CN201911396775.4A CN201911396775A CN111145164A CN 111145164 A CN111145164 A CN 111145164A CN 201911396775 A CN201911396775 A CN 201911396775A CN 111145164 A CN111145164 A CN 111145164A
- Authority
- CN
- China
- Prior art keywords
- chip
- image
- detection method
- artificial intelligence
- defect detection
- 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
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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4007—Interpolation-based scaling, e.g. bilinear interpolation
-
- 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
- G06T2207/30148—Semiconductor; IC; Wafer
Abstract
The invention discloses an IC chip defect detection method based on artificial intelligence, which comprises the following steps: preparing equipment: the system comprises a high-definition camera unit, an AI visual center host and an annular light source; the IC chip can clearly show the defect image characteristics through the annular light source; acquiring different types of image characteristics of the IC chip through a high-definition camera unit; the invention has the beneficial effects that: the method is beneficial to improving the efficiency of detecting the defects of the IC chip and reducing the labor intensity of people; generating sample data by using the GAN, so that the recognition model obtained by training mass real pictures is more accurate; the marking module and the extraction module are additionally arranged, so that the marking of the defective part of the IC chip is facilitated, and the accuracy of image recognition of the IC chip is improved; and when the image features of the IC chip are extracted, the image is zoomed by using a bilinear interpolation algorithm, and the image is convoluted by using a convolution kernel, so that the reliable extraction of the image features is further improved.
Description
Technical Field
The invention belongs to the technical field of IC chip defect detection, and particularly relates to an IC chip defect detection method based on artificial intelligence.
Background
An integrated circuit is a miniature electronic device or component, and the components and wiring of transistor, diode, resistor, capacitor and inductor required in a circuit are interconnected together by a certain process, and then are made into a small piece or several small pieces of semiconductor wafers or medium substrates, and then are packaged in a package, so that the miniature structure with the required circuit function is formed.
An IC chip is a chip formed by placing an integrated circuit formed by a large number of microelectronic components (transistors, resistors, capacitors, etc.) on a plastic substrate. The IC chip comprises a wafer chip and a packaging chip, and the corresponding IC chip production line consists of a wafer production line and a packaging production line.
Artificial intelligence, abbreviated in english as AI. In the field of industrial inspection, the number of defect samples that a customer can provide is very limited. In order to ensure high recognition accuracy, the AI vision technique must perform model training based on a large amount of sample data. Therefore, how to solve the contradiction between the small number of samples and the large requirement of training data is one of the key factors for whether the AI technology can be used in the field of industrial detection.
In order to improve the IC chip defect detection efficiency and reduce the labor intensity of people, an IC chip defect detection method based on artificial intelligence is provided.
Disclosure of Invention
The invention aims to provide an IC chip defect detection method based on artificial intelligence, which improves the IC chip defect detection efficiency and reduces the labor intensity of people.
In order to achieve the purpose, the invention provides the following technical scheme: an IC chip defect detection method based on artificial intelligence comprises the following steps:
the method comprises the following steps: preparing equipment: the system comprises a high-definition camera unit, an AI visual center host and an annular light source;
step two: the IC chip can clearly show the defect image characteristics through the annular light source;
step three: acquiring different types of image characteristics of the IC chip through a high-definition camera unit;
step four: the AI visual center host performs IC chip defect recognition model training based on the collected image data to generate an IC chip defect recognition model;
step five: and loading an IC chip defect identification model by the AI vision center host, and carrying out defect detection and identification on the IC chip to be detected.
As a preferred technical solution of the present invention, the method further includes increasing the number of samples, and the manner of increasing the number of samples is as follows:
slightly changing the existing picture, and increasing the number of samples by turning, translating, changing brightness, scaling and increasing noise;
and generating a large amount of brand-new sample data with different styles by using a generating countermeasure network GAN based on the small sample picture.
As a preferred technical scheme of the invention, the IC chip defects are one or more of flash, starved material, pores, scratches, stains and pressure damages.
As a preferred technical solution of the present invention, the present invention further includes a storage module, which is used for storing the acquired data.
As a preferred technical solution of the present invention, the present invention further includes an extraction module, which is configured to extract image features of the IC chip.
As a preferred technical solution of the present invention, the image processing apparatus further includes a labeling module, which is used for labeling the image defect of the IC chip.
As a preferable technical scheme of the invention, when the image features of the IC chip are extracted, a bilinear interpolation algorithm is used for zooming the image, and a convolution kernel is used for performing convolution processing on the image.
Compared with the prior art, the invention has the beneficial effects that:
(1) the method is beneficial to improving the efficiency of detecting the defects of the IC chip and reducing the labor intensity of people;
(2) generating sample data by using the GAN, so that the recognition model obtained by training mass real pictures is more accurate;
(3) the marking module and the extraction module are additionally arranged, so that the marking of the defective part of the IC chip is facilitated, and the accuracy of image recognition of the IC chip is improved;
(4) and when the image features of the IC chip are extracted, the image is zoomed by using a bilinear interpolation algorithm, and the image is convoluted by using a convolution kernel, so that the reliable extraction of the image features is further improved.
Drawings
FIG. 1 is a flow chart of the detection method of 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, the present invention provides a technical solution: an IC chip defect detection method based on artificial intelligence comprises the following steps:
the method comprises the following steps: preparing equipment: the system comprises a high-definition camera unit, an AI visual center host and an annular light source; the annular light source equipment is used for providing an annular light source, so that the IC chip can clearly show the defect image characteristics; a high-definition imaging unit that generates a high-definition image with a resolution of 4K (4096 × 2160) or more using 1000 ten thousand or more pixels; the AI visual center host is used for training an IC chip identification model, storing the acquired image and identifying the IC chip defect content in the image, and uses a high-performance GPU;
step two: the IC chip can clearly show the defect image characteristics through the annular light source;
step three: acquiring different types of image characteristics of the IC chip through a high-definition camera unit;
step four: the AI visual center host performs IC chip defect recognition model training based on the collected image data to generate an IC chip defect recognition model;
step five: and loading an IC chip defect identification model by the AI vision center host, and carrying out defect detection and identification on the IC chip to be detected.
In this embodiment, it is preferable that the method further includes increasing the number of samples, and the manner of increasing the number of samples is as follows:
slightly changing the existing picture, and increasing the number of samples by turning, translating, changing brightness, scaling and increasing noise;
generating a large amount of sample data with different styles and brand new styles based on the small sample picture by using a generating countermeasure network GAN; the GAN is utilized to generate sample data, the sample data is more and more real and more diverse, and the identification model obtained based on the training of the massive real pictures is more and more accurate.
In this embodiment, the IC chip defect is preferably one or more of flash, missing material, air hole, scratch, stain, and pressure damage.
In this embodiment, preferably, the data processing system further includes a storage module, and the storage module is configured to store the acquired data, so as to facilitate calling of the stored data.
In this embodiment, preferably, the system further includes an extraction module, and the extraction module is configured to extract image features of the IC chip, so that accuracy of image recognition of the IC chip is improved.
In this embodiment, it is preferable that the system further includes a labeling module, where the labeling module is configured to label the image defects of the IC chip, and can correctly distinguish the defect types, contours, sizes, and defect positions, and after the machine learns more samples, the system can identify defects with more types of features.
In this embodiment, preferably, the image feature extraction of the IC chip uses a bilinear interpolation algorithm to scale the image, and uses a convolution kernel to perform convolution processing on the image.
The IC chip defect detection method based on artificial intelligence inputs training samples, so that: the object distance change, the brightness change, the position/fine shape change and the angle change can be identified; has the following effects: the defect position and the type are known; the adaptation is fast: the visual field, the brightness and the angle are not limited, and the generalization is strong; multiple types and defects can be identified simultaneously.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (7)
1. An IC chip defect detection method based on artificial intelligence is characterized in that: the detection method comprises the following steps:
the method comprises the following steps: preparing equipment: the system comprises a high-definition camera unit, an AI visual center host and an annular light source;
step two: the IC chip can clearly show the defect image characteristics through the annular light source;
step three: acquiring different types of image characteristics of the IC chip through a high-definition camera unit;
step four: the AI visual center host performs IC chip defect recognition model training based on the collected image data to generate an IC chip defect recognition model;
step five: and loading an IC chip defect identification model by the AI vision center host, and carrying out defect detection and identification on the IC chip to be detected.
2. The IC chip defect detection method based on artificial intelligence as claimed in claim 1, wherein: the method also comprises the following steps of increasing the number of samples:
slightly changing the existing picture, and increasing the number of samples by turning, translating, changing brightness, scaling and increasing noise;
and generating a large amount of brand-new sample data with different styles by using a generating countermeasure network GAN based on the small sample picture.
3. The IC chip defect detection method based on artificial intelligence as claimed in claim 1, wherein: the IC chip defects are one or more of flash, starved, air holes, scratches, stains and pressure damages.
4. The IC chip defect detection method based on artificial intelligence as claimed in claim 1, wherein: the device also comprises a storage module which is used for storing the acquired data.
5. The IC chip defect detection method based on artificial intelligence as claimed in claim 1, wherein: the system also comprises an extraction module which is used for realizing the extraction of the image characteristics of the IC chip.
6. The IC chip defect detection method based on artificial intelligence as claimed in claim 1, wherein: the marking module is used for marking the image defects of the IC chip.
7. The IC chip defect detection method based on artificial intelligence as claimed in claim 1, wherein: and zooming the image by using a bilinear interpolation algorithm during the image feature extraction of the IC chip, and performing convolution processing on the image by using a convolution kernel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911396775.4A CN111145164A (en) | 2019-12-30 | 2019-12-30 | IC chip defect detection method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911396775.4A CN111145164A (en) | 2019-12-30 | 2019-12-30 | IC chip defect detection method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111145164A true CN111145164A (en) | 2020-05-12 |
Family
ID=70521866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911396775.4A Pending CN111145164A (en) | 2019-12-30 | 2019-12-30 | IC chip defect detection method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111145164A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561902A (en) * | 2020-12-23 | 2021-03-26 | 天津光电通信技术有限公司 | Chip inverse reduction method and system based on deep learning |
| CN112950560A (en) * | 2021-02-20 | 2021-06-11 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Electronic component defect detection method, device and system |
| CN113103256A (en) * | 2021-04-22 | 2021-07-13 | 达斯琪(重庆)数字科技有限公司 | Service robot vision system |
| CN113916893A (en) * | 2021-09-29 | 2022-01-11 | 逸美德科技股份有限公司 | Method for detecting die-cutting product defects |
| CN116343213A (en) * | 2023-05-31 | 2023-06-27 | 成都数之联科技股份有限公司 | Model training and chip character recognition method, device, equipment and medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018000731A1 (en) * | 2016-06-28 | 2018-01-04 | 华南理工大学 | Method for automatically detecting curved surface defect and device thereof |
| CN208313802U (en) * | 2018-07-05 | 2019-01-01 | 厦门福信光电集成有限公司 | A kind of chip pin defect detecting system based on machine vision |
| CN109724984A (en) * | 2018-12-07 | 2019-05-07 | 上海交通大学 | A kind of defects detection identification device and method based on deep learning algorithm |
| CN109919908A (en) * | 2019-01-23 | 2019-06-21 | 华灿光电（浙江）有限公司 | The method and apparatus of light-emitting diode chip for backlight unit defects detection |
| CN110197259A (en) * | 2019-05-30 | 2019-09-03 | 浙江大学 | Wafer defect detection method based on small lot data set Yu deep learning algorithm |
| CN110322433A (en) * | 2019-05-27 | 2019-10-11 | 苏州佳赛特智能科技有限公司 | A kind of data set amplification method towards the detection of appearance defective vision |
| CN110333238A (en) * | 2019-06-18 | 2019-10-15 | 东华大学 | A kind of SMT chip defect detection system and method |
| CN110349125A (en) * | 2019-06-17 | 2019-10-18 | 武汉大学 | A kind of LED chip open defect detection method and system based on machine vision |
| CN110530875A (en) * | 2019-08-29 | 2019-12-03 | 珠海博达创意科技有限公司 | A kind of FPCB open defect automatic detection algorithm based on deep learning |
-
2019
- 2019-12-30 CN CN201911396775.4A patent/CN111145164A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018000731A1 (en) * | 2016-06-28 | 2018-01-04 | 华南理工大学 | Method for automatically detecting curved surface defect and device thereof |
| CN208313802U (en) * | 2018-07-05 | 2019-01-01 | 厦门福信光电集成有限公司 | A kind of chip pin defect detecting system based on machine vision |
| CN109724984A (en) * | 2018-12-07 | 2019-05-07 | 上海交通大学 | A kind of defects detection identification device and method based on deep learning algorithm |
| CN109919908A (en) * | 2019-01-23 | 2019-06-21 | 华灿光电（浙江）有限公司 | The method and apparatus of light-emitting diode chip for backlight unit defects detection |
| CN110322433A (en) * | 2019-05-27 | 2019-10-11 | 苏州佳赛特智能科技有限公司 | A kind of data set amplification method towards the detection of appearance defective vision |
| CN110197259A (en) * | 2019-05-30 | 2019-09-03 | 浙江大学 | Wafer defect detection method based on small lot data set Yu deep learning algorithm |
| CN110349125A (en) * | 2019-06-17 | 2019-10-18 | 武汉大学 | A kind of LED chip open defect detection method and system based on machine vision |
| CN110333238A (en) * | 2019-06-18 | 2019-10-15 | 东华大学 | A kind of SMT chip defect detection system and method |
| CN110530875A (en) * | 2019-08-29 | 2019-12-03 | 珠海博达创意科技有限公司 | A kind of FPCB open defect automatic detection algorithm based on deep learning |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561902A (en) * | 2020-12-23 | 2021-03-26 | 天津光电通信技术有限公司 | Chip inverse reduction method and system based on deep learning |
| CN112950560A (en) * | 2021-02-20 | 2021-06-11 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Electronic component defect detection method, device and system |
| CN113103256A (en) * | 2021-04-22 | 2021-07-13 | 达斯琪(重庆)数字科技有限公司 | Service robot vision system |
| CN113916893A (en) * | 2021-09-29 | 2022-01-11 | 逸美德科技股份有限公司 | Method for detecting die-cutting product defects |
| CN116343213A (en) * | 2023-05-31 | 2023-06-27 | 成都数之联科技股份有限公司 | Model training and chip character recognition method, device, equipment and medium |
| CN116343213B (en) * | 2023-05-31 | 2023-08-25 | 成都数之联科技股份有限公司 | Model training and chip character recognition method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111145164A (en) | IC chip defect detection method based on artificial intelligence | |
| CN109829914B (en) | Method and device for detecting product defects | |
| CN107492091B (en) | Label appearance detection method based on machine vision and terminal equipment | |
| JP2004077164A (en) | Defect inspection method | |
| US11657599B2 (en) | Method for detecting appearance of six sides of chip multi-layer ceramic capacitor based on artificial intelligence | |
| WO2019101027A1 (en) | Commodity identification method and device | |
| WO2017107529A1 (en) | Positioning method and device for diodes arranged side by side | |
| CN112288741A (en) | Product surface defect detection method and system based on semantic segmentation | |
| CN103245667A (en) | Method and system for automatically detecting mechanical scratches | |
| CN107507130A (en) | A kind of quickly QFN chip pins image obtains and amplification method | |
| CN109870463B (en) | Electronic chip fault detection device | |
| KR20060022350A (en) | Test handler and method for test of semiconductor package | |
| Klco et al. | Automated detection of soldering splashes using YOLOv5 algorithm | |
| CN111539955A (en) | Defect detection method | |
| CN116908185A (en) | Method and device for detecting appearance defects of article, electronic equipment and storage medium | |
| CN116309532A (en) | Method, device, equipment and medium for detecting quality of target object | |
| JP2008185395A (en) | Mounting substrate visual inspection method | |
| JP2023535005A (en) | Method and system or apparatus for recognizing objects in electronic images | |
| CN113205505A (en) | Insulator defect detection method based on improved ResNeSt-RPN | |
| CN111899248A (en) | Automatic PCB soldering paste defect detection method based on machine learning | |
| Fabrice et al. | SMD Detection and Classification Using YOLO Network Based on Robust Data Preprocessing and Augmentation Techniques | |
| TWI764473B (en) | Method, terminal device, electronic device and storage medium for object detection | |
| Anitha et al. | BARE BOARD MULTILAYER PRINTED CIRCUIT BOARD DEFECT IDENTIFICATION FOLLOWED BY LOCALIZATION | |
| CN116883434B (en) | Acceleration sensor chip packaging defect detection method based on semantic segmentation | |
| CN114820613B (en) | Incoming material measuring and positioning method for SMT (surface mount technology) patch processing |
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 |