| Presentation | 2011-12-16 Automatic defect classification using Bag-of-Keypoints Tsutomu SAKUYAMA, Akira MATSUMURA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Bag-of-Keypoints (BoK) is an algorithm for image classification. The BoK is based on Scale-Invariant Feature Transform (SIFT) which is an algorithm for deteting keypoints and extracting local feature descriptors. In this paper, we proposed a novel approach for Automatic defect classification (ADC) using BoK. First, to remove a noise in the image, we used a background removing technique. Secondly, to detect the keypoints on subject in the image, we fix the SIFT parameter that is a best value for increasing the number of keyopints. In the result, we could classified the image at the same level as human in factory line. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Bag-of-Keypoints / SIFT / ADC / semiconductor / SVM |
| Paper # | PRMU2011-134 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2011/12/8(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Pattern Recognition and Media Understanding (PRMU) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Automatic defect classification using Bag-of-Keypoints |
| Sub Title (in English) | |
| Keyword(1) | Bag-of-Keypoints |
| Keyword(2) | SIFT |
| Keyword(3) | ADC |
| Keyword(4) | semiconductor |
| Keyword(5) | SVM |
| 1st Author's Name | Tsutomu SAKUYAMA |
| 1st Author's Affiliation | DAINIPPON SCREEN MFG. CO., LTD.() |
| 2nd Author's Name | Akira MATSUMURA |
| 2nd Author's Affiliation | DAINIPPON SCREEN MFG. CO., LTD. |
| Date | 2011-12-16 |
| Paper # | PRMU2011-134 |
| Volume (vol) | vol.111 |
| Number (no) | 353 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |