 |
Technical Program
Paper Detail
| Paper: | WP-P1.5 |
| Session: | Visual Object/Event Detection, Segmentation, and Classification |
| Time: | Wednesday, October 11, 14:20 - 17:00 |
| Presentation: |
Poster
|
| Title: |
SKIN DETECTION IN WEB IMAGERY: COMPARISON OF TECHNIQUES AND PROPOSAL |
| Authors: |
Heitor Ramos; Universidade Federal de Alagoas | | | | | Alejandro Frery; Universidade Federal de Alagoas | | | | | José Alencar-Neto; Justiça Federal de Primeira Instância | | |
| Abstract: |
This paper presents a quantitative comparison of the performance of skin detection techniques for a Web-based system. The procedures under analysis employ dimensionality reduction, with or without color correction. We propose a rule for deciding if an image requires color correction and, if needed, which is the best procedure. Geometric rules, parametric methods and histogram-based techniques are compared in terms of accuracy and performance. With the proposed heuristic for color correction, the best performances are achieved by a classifier based on the mixture of two Gaussian laws applied to data projected with principal component analysis and a by a KDD-based rule that operates on the RGB space. |
|
