| Presentation | 2005-10-27 Face Recognition Using Self Quotient Images based on Classification of Surface Appearance Masashi NISHIYAMA, Osamu YAMAGUCHI, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper we present a new method for synthesizing illumination invariant images for face recognition. The method classifies the appearance caused by illumination according to four properties : diffuse reflection, specular reflection, attached shadow and cast shadow. Among these properties, the shadow and the specular reflection dynamically change the appearance. Classification from a single image is difficult because shadows and specular reflection depend on the facial shape and the light source. Therefore, we use a simple model defined by a few basis images for classification. For each pixel in the original image, we design a filter based on the classification result, which is used to compute the Self Quotient Image (SQI). At each location the SQI contains the ratio of the albedo at that pixel and a locally smoothed value of the albedo. Through experimental results we show the effectiveness of this method for face identification on a public database and on a database used in practice, using only a single image for each individual reference. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Face recognition / Illumination invariance / Self Quotient Image / Linearization |
| Paper # | PRMU2005-89 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2005/10/20(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) | Face Recognition Using Self Quotient Images based on Classification of Surface Appearance |
| Sub Title (in English) | |
| Keyword(1) | Face recognition |
| Keyword(2) | Illumination invariance |
| Keyword(3) | Self Quotient Image |
| Keyword(4) | Linearization |
| 1st Author's Name | Masashi NISHIYAMA |
| 1st Author's Affiliation | Corporate Research and Development Center, TOSHIBA Corporation() |
| 2nd Author's Name | Osamu YAMAGUCHI |
| 2nd Author's Affiliation | Corporate Research and Development Center, TOSHIBA Corporation |
| Date | 2005-10-27 |
| Paper # | PRMU2005-89 |
| Volume (vol) | vol.105 |
| Number (no) | 374 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |