CN102982155A - System and method for searching defects based on pattern identification - Google Patents
System and method for searching defects based on pattern identification Download PDFInfo
- Publication number
- CN102982155A CN102982155A CN2012105017777A CN201210501777A CN102982155A CN 102982155 A CN102982155 A CN 102982155A CN 2012105017777 A CN2012105017777 A CN 2012105017777A CN 201210501777 A CN201210501777 A CN 201210501777A CN 102982155 A CN102982155 A CN 102982155A
- Authority
- CN
- China
- Prior art keywords
- defective
- defect database
- feature data
- contour feature
- defect
- 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
Landscapes
- Image Analysis (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The invention discloses a system and a method for searching defects based on pattern identification. The method comprises the following steps of establishing a defect database, calculating each defect pattern in the defect database by a pattern boundary contour algorithm, and respectively and correspondingly establishing contour feature data of each defect; receiving the inputted image of the defect to be found; operating the image of the defect to be found by the pattern boundary contour algorithm to obtain the contour feature data; comparing the extracted contour feature data with the contour feature data established in the defect database; and according to the comparison result, finding the same or similar defect data information from the defect database and the related solutions. The system and the method have the advantages that the defect database can be searched, and the labor, the material and the resource are saved.
Description
Technical field
The present invention particularly relates to defective searching system and method based on figure identification in a kind of integrated circuit fabrication process about a kind of defective searching system and method based on figure identification.
Background technology
Along with the constantly lifting of integrated circuit technique, minimum design size is also in continuous reduction, and defective is increasing on the impact of yield, and the simultaneously introducing of new technology, new material also makes the kind of defective more and more, and the origin cause of formation becomes increasingly complex.
At present the most frequently used the most intuitively form of presentation of defective is figure, and Fig. 1 is the pictorial diagram of defect database commonly used in the prior art.Defect database for Fig. 1, often can only inquire about by keyword, even therefore set up defect database, also can't from database, find related data by the mode of retrieval, can only rely on original experience accumulation to search problem, solve a defect problem and often expend a large amount of manpower and materials.
Summary of the invention
The deficiency that exists for overcoming above-mentioned prior art, the present invention's purpose is to provide a kind of defective searching system and method based on figure identification, it sets up digitized defect database by graphic limit profile algorithm, compare so that carry out contour feature data and defect database that defective when retrieval only need obtain defective to be checked, find the former defective data information solution of being correlated with for referencial use, realize the purpose of retrieval defect database, saved human and material resources.
For reaching above-mentioned and other purpose, the present invention proposes a kind of defective searching system based on figure identification, comprises at least:
Defect database is set up module, sets up defect database, and adopts graphic limit profile algorithm that the various defective patterns in the defect database are calculated, and sets up one to one the contour feature data of various defectives;
Picture receives module, receives the picture of the defective to be checked of inputting;
Extract module, obtain its contour feature data after the picture computing of employing graphic limit profile algorithm to defective to be checked;
Comparison module is compared extracting contour feature data that module obtains and the contour feature data of this defect database; And
Comparison result is processed module, according to the result of comparison, finds same or analogous defective data information and relevant solution.
Further, this defective searching system also comprises classification die set, classifies for the contour feature data of the various defectives that defect database is set up, and obtains sorted digitized defect database.
Further, this defect database is set up in the defect database that module sets up and is comprised various defective patterns and corresponding relevant solution.
Further, this defective patterns is the electron micrograph of taking according to certain visual field.
Further, this defective patterns is the electron micrograph of taking according to 2 microns visual fields.
Further, this picture receives that module receives is the typical photo of the defective to be checked uploaded.
For reaching above-mentioned and other purpose, the present invention also provides a kind of defective search method based on figure identification, comprises the steps:
Step 1 is set up defect database, and adopts graphic limit profile algorithm that the various defective patterns in the defect database are calculated, and sets up one to one the contour feature data of various defectives;
Step 2, the picture of the defective to be checked that reception is inputted;
Step 3 obtains its contour feature data after the picture computing of employing graphic limit profile algorithm to defective to be checked;
Step 4 is compared the contour feature data of setting up in the contour feature data that extract to obtain and the defect database; And
Step 5 according to the result of comparison, finds same or analogous defective data information and relevant solution from defect database.
Further, in step 1, the contour feature data of various defectives are classified, obtain sorted digitized defect database.
Further, the defective patterns in this defect database is the electron micrograph of taking according to certain visual field.
Further, this defective search method is used for integrated circuit fabrication process.
Compared with prior art, the present invention a kind of defective searching system and method based on figure, by setting up defect database, utilize graphic limit profile algorithm the defective patterns in the defect database to be calculated the contour feature data of setting up various defectives, as long as upload the typical photo of defective to be checked when carrying out the defective retrieval, and obtain its contour feature data after adopting graphic limit profile algorithm to this photo computing, compare by defect database, find former defective data information and relevant solution for referencial use, thereby solve this defect problem, realize the purpose of retrieval defect database, saved human and material resources.
Description of drawings
Fig. 1 is the pictorial diagram of defect database commonly used in the prior art;
Fig. 2 is the system architecture diagram of a kind of defective searching system based on figure identification of the present invention;
Fig. 3 utilizes graphic limit profile algorithm to the digitized synoptic diagram of defective patterns in the defect database in the preferred embodiment of the present invention;
Fig. 4 is the synoptic diagram that 206 pairs of defective patterns boundary profiles of classification die set data are classified in the preferred embodiment of the present invention;
Fig. 5 is the flow chart of steps of a kind of defective search method based on figure identification of the present invention;
Fig. 6 is the flow chart of steps of the preferred embodiment of a kind of defective search method based on figure identification of the present invention.
Embodiment
Below by specific instantiation and accompanying drawings embodiments of the present invention, those skilled in the art can understand other advantage of the present invention and effect easily by content disclosed in the present specification.The present invention also can be implemented or be used by other different instantiation, and the every details in this instructions also can be based on different viewpoints and application, carries out various modifications and change under the spirit of the present invention not deviating from.
Fig. 2 is the system architecture diagram of a kind of defective searching system based on figure identification of the present invention.As shown in Figure 2, a kind of defective searching system based on figure identification of the present invention comprises at least: defect database is set up module 201, picture receives module 202, extraction module 203, comparison module 204 and comparison result and processes module 205.
Defect database is set up module 201, set up defect database, and adopt graphic limit profile algorithm that the various defective patterns in the defect database are calculated, set up one to one the contour feature data of various defectives, specifically, defect database is set up module 201 and by graphic limit profile algorithm the various defective patterns in the defect database is calculated defect profile, thereby the digitizing of defect profile feature, as shown in Figure 3.Comprise various defective patterns and corresponding relevant solution in the defect database, in preferred embodiment of the present invention, the picture in the defect database is the electron micrograph of taking according to certain visual field (2 microns).Because graphic limit profile algorithm is computer graphics extraction algorithm common in the prior art, does not repeat them here.
Picture receives the picture that module 202 is used for receiving the defective to be checked of inputting, and in preferred embodiment of the present invention, picture receives the typical photo that module 202 receives the defective to be checked of uploading, and certainly the invention is not restricted to this; Extract module 203, obtain its contour feature data after the picture computing of employing graphic limit profile algorithm to defective to be checked; Comparison module 204 is compared extracting module 203 the contour feature data that obtain and the contour feature data that defect database is set up module 201 foundation; Comparison result is processed module 205 according to the result of comparison, finds same or analogous defective data information and relevant solution, thereby solves the defect problem of this defective to be checked.
Better, in preferred embodiment of the present invention, the present invention's the defective searching system based on figure identification also comprises classification die set 206, classification die set 206 is classified for the contour feature data of the various defectives of defect database being set up module 201 foundation, obtain digitized defect database, so that comparison module 204 is compared, improve comparison efficiency, Fig. 4 is the synoptic diagram that 206 pairs of defective patterns boundary profiles of classification die set data are classified in the preferred embodiment of the present invention, as shown in Figure 4, as according to the contour feature data defect database being divided into circle, conical, square and linear.
Fig. 5 is the flow chart of steps of a kind of defective search method based on figure identification of the present invention.As shown in Figure 5, a kind of defective search method based on figure identification of the present invention comprises the steps:
Step 501, set up defect database, and adopt graphic limit profile algorithm that the various defective patterns in the defect database are calculated, set up one to one the contour feature data of various defectives, be about to the contour feature Data Digital of various defectives, comprise various defective patterns and corresponding relevant solution in the defect database of setting up, in preferred embodiment of the present invention, the picture in the defect database is the electron micrograph of taking according to certain market (2 microns);
Step 502 receives the picture of the defective to be checked input, and in preferred embodiment of the present invention, what receive here is the typical photo of the defective to be checked uploaded, the invention is not restricted to this;
Step 503 obtains its contour feature data after the picture computing of employing graphic limit profile algorithm to defective to be checked;
Step 504 is compared the contour feature data of setting up in the contour feature data that extract to obtain and the defect database; And
Step 505 according to the result of comparison, finds same or analogous defective data information and relevant solution from defect database, thereby solves the defect problem of this defective to be checked.
Better, in step 501, can also obtain sorted digitized defect database by the contour feature data of various defectives are classified, so that follow-up comparison operation improves comparison efficiency.
Fig. 6 is the flow chart of steps of the preferred embodiment of a kind of defective search method based on figure identification of the present invention.Below will cooperate Fig. 6 that the present invention's preferred embodiment is described further.As shown in Figure 6, in preferred embodiment of the present invention, a kind of defective search method based on figure identification of the present invention comprises the steps:
In sum, the present invention a kind of defective searching system and method based on figure, by setting up defect database, utilize graphic limit profile algorithm the defective patterns in the defect database to be calculated the contour feature data of setting up various defectives, as long as upload the typical photo of defective to be checked when carrying out the defective retrieval, and obtain its contour feature data after adopting graphic limit profile algorithm to this photo computing, compare by defect database, find former defective data information and relevant solution for referencial use, thereby solve this defect problem, realize the purpose of retrieval defect database, saved human and material resources.Through practice, utilize know-why of the present invention, in the production run of reality, run into defect problem, utilize the present invention to carry out data-searching, the realization experience is shared, and the fix the defect problem has been safeguarded that volume production is stable and has been promoted yield rapidly.
Above-described embodiment is illustrative principle of the present invention and effect thereof only, but not is used for restriction the present invention.Any those skilled in the art all can be under spirit of the present invention and category, and above-described embodiment is modified and changed.Therefore, the scope of the present invention should be listed such as claims.
Claims (10)
1. defective searching system based on figure identification comprises at least:
Defect database is set up module, sets up defect database, and adopts graphic limit profile algorithm that the various defective patterns in the defect database are calculated, and sets up one to one the contour feature data of various defectives;
Picture receives module, receives the picture of the defective to be checked of inputting;
Extract module, obtain its contour feature data after the picture computing of employing graphic limit profile algorithm to defective to be checked;
Comparison module is compared extracting contour feature data that module obtains and the contour feature data of this defect database; And
Comparison result is processed module, according to the result of comparison, finds same or analogous defective data information and relevant solution.
2. the defective searching system based on figure identification as claimed in claim 1, it is characterized in that: this defective searching system also comprises classification die set, contour feature data for the various defectives that defect database is set up are classified, and obtain sorted digitized defect database.
3. the defective searching system based on figure identification as claimed in claim 1 is characterized in that: this defect database is set up in the defect database that module sets up and is comprised various defective patterns and corresponding relevant solution.
4. the defective searching system based on figure identification as claimed in claim 1 is characterized in that: the electron micrograph of this defective patterns for taking according to certain visual field.
5. the defective searching system based on figure identification as claimed in claim 4 is characterized in that: the electron micrograph of this defective patterns for taking according to 2 microns visual fields.
6. the defective searching system based on figure identification as claimed in claim 1 is characterized in that: this picture receives that module receives is the typical photo of the defective to be checked uploaded.
7. the defective search method based on figure identification comprises the steps:
Step 1 is set up defect database, and adopts graphic limit profile algorithm that the various defective patterns in the defect database are calculated, and sets up one to one the contour feature data of various defectives;
Step 2, the picture of the defective to be checked that reception is inputted;
Step 3 obtains its contour feature data after the picture computing of employing graphic limit profile algorithm to defective to be checked;
Step 4 is compared the contour feature data of setting up in the contour feature data that extract to obtain and the defect database; And
Step 5 according to the result of comparison, finds same or analogous defective data information and relevant solution from defect database.
8. a kind of defective search method based on figure identification as claimed in claim 7 is characterized in that: in step 1, the contour feature data of various defectives are classified, obtain sorted digitized defect database.
9. a kind of defective search method based on figure identification as claimed in claim 7 is characterized in that: the electron micrograph of the defective patterns in this defect database for taking according to certain visual field.
10. a kind of defective search method based on figure identification as claimed in claim 7, it is characterized in that: this defective search method is used for integrated circuit fabrication process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012105017777A CN102982155A (en) | 2012-11-29 | 2012-11-29 | System and method for searching defects based on pattern identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012105017777A CN102982155A (en) | 2012-11-29 | 2012-11-29 | System and method for searching defects based on pattern identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102982155A true CN102982155A (en) | 2013-03-20 |
Family
ID=47856172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012105017777A Pending CN102982155A (en) | 2012-11-29 | 2012-11-29 | System and method for searching defects based on pattern identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102982155A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106920219A (en) * | 2015-12-28 | 2017-07-04 | 力晶科技股份有限公司 | Article defect detection method, image processing system and computer readable recording medium |
| CN103295930B (en) * | 2013-06-04 | 2017-07-07 | 上海华力微电子有限公司 | A kind of brilliant back of the body defect identification method rapidly and efficiently |
| CN107590511A (en) * | 2017-08-30 | 2018-01-16 | 武汉华星光电技术有限公司 | A kind of defect identification method and identifying system the defects of for automatic check machine |
| CN107886495A (en) * | 2017-09-30 | 2018-04-06 | 北京得华机器人技术研究院有限公司 | A kind of auto-parts defect identification method based on similarity mode |
| CN109727887A (en) * | 2018-12-29 | 2019-05-07 | 上海华力微电子有限公司 | The monitoring method of the crystal edge defect of wafer |
| CN110599484A (en) * | 2019-09-19 | 2019-12-20 | 京东方科技集团股份有限公司 | Defect detection method, device and storage medium |
| CN111391520A (en) * | 2020-03-31 | 2020-07-10 | 虔东稀土集团股份有限公司 | Method and equipment for automatic marking and weighing |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901233A (en) * | 2009-05-25 | 2010-12-01 | 元智大学 | Method for searching data and image searching engine |
| CN102142355A (en) * | 2010-02-02 | 2011-08-03 | 吕一云 | Application method of object manufacture defect |
| CN102683165A (en) * | 2011-03-18 | 2012-09-19 | 敖翔科技股份有限公司 | Intelligent defect screening and sampling method |
-
2012
- 2012-11-29 CN CN2012105017777A patent/CN102982155A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901233A (en) * | 2009-05-25 | 2010-12-01 | 元智大学 | Method for searching data and image searching engine |
| CN102142355A (en) * | 2010-02-02 | 2011-08-03 | 吕一云 | Application method of object manufacture defect |
| CN102683165A (en) * | 2011-03-18 | 2012-09-19 | 敖翔科技股份有限公司 | Intelligent defect screening and sampling method |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103295930B (en) * | 2013-06-04 | 2017-07-07 | 上海华力微电子有限公司 | A kind of brilliant back of the body defect identification method rapidly and efficiently |
| CN106920219A (en) * | 2015-12-28 | 2017-07-04 | 力晶科技股份有限公司 | Article defect detection method, image processing system and computer readable recording medium |
| CN107590511A (en) * | 2017-08-30 | 2018-01-16 | 武汉华星光电技术有限公司 | A kind of defect identification method and identifying system the defects of for automatic check machine |
| CN107886495A (en) * | 2017-09-30 | 2018-04-06 | 北京得华机器人技术研究院有限公司 | A kind of auto-parts defect identification method based on similarity mode |
| CN107886495B (en) * | 2017-09-30 | 2020-04-14 | 北京得华机器人技术研究院有限公司 | Automobile part defect identification method based on similarity matching |
| CN109727887A (en) * | 2018-12-29 | 2019-05-07 | 上海华力微电子有限公司 | The monitoring method of the crystal edge defect of wafer |
| CN110599484A (en) * | 2019-09-19 | 2019-12-20 | 京东方科技集团股份有限公司 | Defect detection method, device and storage medium |
| CN110599484B (en) * | 2019-09-19 | 2023-01-10 | 京东方科技集团股份有限公司 | Defect detection method, device and storage medium |
| CN111391520A (en) * | 2020-03-31 | 2020-07-10 | 虔东稀土集团股份有限公司 | Method and equipment for automatic marking and weighing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102982155A (en) | System and method for searching defects based on pattern identification | |
| CN109002824B (en) | OpenCV-based building drawing label information detection method | |
| US20200151434A1 (en) | Face image retrieval methods and systems, photographing apparatuses, and computer storage media | |
| CN107392141B (en) | Airport extraction method based on significance detection and LSD (least squares distortion) line detection | |
| CN105574524B (en) | Based on dialogue and divide the mirror cartoon image template recognition method and system that joint identifies | |
| Althubiti et al. | Circuit manufacturing defect detection using VGG16 convolutional neural networks | |
| CN109753953A (en) | The method, apparatus of localization of text, electronic equipment and storage medium in image | |
| US20130223730A1 (en) | Scalable feature descriptor extraction and matching method and system | |
| CN104239909A (en) | Method and device for recognizing images | |
| CN103440035A (en) | Gesture recognition system in three-dimensional space and recognition method thereof | |
| CN111144300B (en) | Pdf table structure identification method based on image identification | |
| CN106203454A (en) | The method and device that certificate format is analyzed | |
| CN112926621B (en) | Data labeling method, device, electronic equipment and storage medium | |
| CN105825228A (en) | Image identification method and apparatus | |
| US9256780B1 (en) | Facilitating dynamic computations for performing intelligent body segmentations for enhanced gesture recognition on computing devices | |
| CN113298809B (en) | Composite material ultrasonic image defect detection method based on deep learning and superpixel segmentation | |
| CN103353881A (en) | Method and device for searching application | |
| CN103077236A (en) | System and method for realizing video knowledge acquisition and marking function of portable-type device | |
| JPWO2015136709A1 (en) | Image processing apparatus, image sensor, and image processing method | |
| CN104834891A (en) | Method and system for filtering Chinese character image type spam | |
| CN105095468A (en) | Novel image retrieval method and system | |
| CN102722732A (en) | Image set matching method based on data second order static modeling | |
| CN104268214B (en) | A kind of user's gender identification method and system based on microblog users relation | |
| CN108536769B (en) | Image analysis method, search method and device, computer device and storage medium | |
| CN103020630A (en) | Processing method and device of image features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130320 |