Presentation | 2015-06-08 Generation of Learning Images Using the Bi-dimensional Empirical Mode Decomposition in Facial recognition Teruaki Fujiyoshi, Kuntpong Woraratpanya, Yoshimitsu Kuroki, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The Empirical Mode Decomposition (EMD) divides a signal into narrowband signals called Intrinsic Mode Function (IMF), and the EMD is applied for analysis of an unsteady signal. The Bi-dimensional Empirical Mode Decomposition (BEMD), which is an extension of the EMD, is applied for image processing field widely such as illumination removal. This study purposes to generate additional learning images in facial image recognition by compounding IMFs of different images in a class. The Cone-restricted Subspace Method (CSM) is used for the recognition, which assigns a convex cone in the non-negative region for each class, and demonstrates better recognition ratio than the conventional subspace method. Experimental results show that the proposed method improves he recognition ration. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Bi-dimensional Empirical Mode Decomposition / Cone-restricted Subspace Method / Facial recognition |
Paper # | SIS2015-5 |
Date of Issue | 2015-06-01 (SIS) |
Conference Information | |
Committee | SIS |
---|---|
Conference Date | 2015/6/8(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Arkas SASEBO |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Smart Personal Systems, etc. |
Chair | Mitsuji Muneyasu(Kansai Univ.) |
Vice Chair | Hirokazu Tanaka(Toshiba) / Takayuki Nakachi(NTT) |
Secretary | Hirokazu Tanaka(Nagoya City Univ.) / Takayuki Nakachi(Toshiba) |
Assistant | Hiroyuki Tsuji(Kanagawa Inst. of Tech.) / Hakaru Tamukoh(Kyushu Inst. of Tech.) |
Paper Information | |
Registration To | Technical Committee on Smart Info-Media System |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Generation of Learning Images Using the Bi-dimensional Empirical Mode Decomposition in Facial recognition |
Sub Title (in English) | |
Keyword(1) | Bi-dimensional Empirical Mode Decomposition |
Keyword(2) | Cone-restricted Subspace Method |
Keyword(3) | Facial recognition |
1st Author's Name | Teruaki Fujiyoshi |
1st Author's Affiliation | National Institute of Technology, Kurume College(NIT, Kurume College) |
2nd Author's Name | Kuntpong Woraratpanya |
2nd Author's Affiliation | King Mongkut's Institute of Technology Ladkrabang(KMITL) |
3rd Author's Name | Yoshimitsu Kuroki |
3rd Author's Affiliation | National Institute of Technology, Kurume College(NIT, Kurume College) |
Date | 2015-06-08 |
Paper # | SIS2015-5 |
Volume (vol) | vol.115 |
Number (no) | SIS-75 |
Page | pp.pp.25-28(SIS), |
#Pages | 4 |
Date of Issue | 2015-06-01 (SIS) |