Presentation | 2013-09-18 Study on Processor Architecture for Image Recognition Masayuki MIYAMA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper proposes a novel classification method using gradient moments as image features. The quantity can also be used for image segmentation and object tracking. Experimental results show the proposed method achieves 99% accuracy rate. It is higher than those of conventional methods such as hear-like and HOG. The paper also describes an efficient processor architecture dedicated to the image recognition. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | affine motion model estimation / motion segmentation / gradient moment / SVM / image recognition |
Paper # | RECONF2013-20 |
Date of Issue |
Conference Information | |
Committee | RECONF |
---|---|
Conference Date | 2013/9/11(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 | Reconfigurable Systems (RECONF) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Study on Processor Architecture for Image Recognition |
Sub Title (in English) | |
Keyword(1) | affine motion model estimation |
Keyword(2) | motion segmentation |
Keyword(3) | gradient moment |
Keyword(4) | SVM |
Keyword(5) | image recognition |
1st Author's Name | Masayuki MIYAMA |
1st Author's Affiliation | School of Electrical and Computer Engineering, College of Science and Engineering, Kanazawa University() |
Date | 2013-09-18 |
Paper # | RECONF2013-20 |
Volume (vol) | vol.113 |
Number (no) | 221 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |