| Presentation | 1999/11/19 Skin-Color Based Segmentation and Invariant Detection of Human Faces in Still Scene Images by Use of Support Vector Machines Jean-Christophe Terrillon, Mahdad N. Shirazi, Mohamed Sadek, Hideo Fukamachi, Shigeru Akamatsu, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper presents an analysis of the performance of Support Vector Machines (SVMs) for the automatic detection of human faces in static color images of cluttered scenes. SVMs are a new interesting type of classifier based on a novel statistical learning technique that has been developed in recent years by V. Vapnik et al. at AT&T Bell Labs [1] [2] [3] [4]. Skin-color based image segmentation is first performed for two different chrominance spaces by use of the single Gaussian chrominance model, as described in [5]. Feature extraction in the segmented images is then implemented by use of invariant orthogonal Fourier-Mellin moments (OFMMs) [6]. The application of SVMs to the invariant moments obtained from a set of 100 test images yields a slightly higher face detection performance than when applying a neural network, but training of SVMs is easier, faster, always finds a global minimum and SVMs have a better generalization abilitv [7]. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Face Detection / Image Segmentation / Invariant Moments / Support Vector Machines |
| Paper # | HIP99-47 |
| Date of Issue |
| Conference Information | |
| Committee | HIP |
|---|---|
| Conference Date | 1999/11/19(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 | Human Information Processing (HIP) |
|---|---|
| Language | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Skin-Color Based Segmentation and Invariant Detection of Human Faces in Still Scene Images by Use of Support Vector Machines |
| Sub Title (in English) | |
| Keyword(1) | Face Detection |
| Keyword(2) | Image Segmentation |
| Keyword(3) | Invariant Moments |
| Keyword(4) | Support Vector Machines |
| 1st Author's Name | Jean-Christophe Terrillon |
| 1st Author's Affiliation | ATR Human Information Processing Research Laboratories() |
| 2nd Author's Name | Mahdad N. Shirazi |
| 2nd Author's Affiliation | Kansai Advanced Research Center, Communications Research Laboratory |
| 3rd Author's Name | Mohamed Sadek |
| 3rd Author's Affiliation | ATR Human Information Processing Research Laboratories |
| 4th Author's Name | Hideo Fukamachi |
| 4th Author's Affiliation | ATR Human Information Processing Research Laboratories |
| 5th Author's Name | Shigeru Akamatsu |
| 5th Author's Affiliation | ATR Human Information Processing Research Laboratories |
| Date | 1999/11/19 |
| Paper # | HIP99-47 |
| Volume (vol) | vol.99 |
| Number (no) | 452 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |