1-403 Improving Face Detection Using Skin Color Information

スポンサーリンク

概要

• 論文の詳細を見る

• Face detection is the fundamental step before face recognition or identification procedure. Its reliability and time-response have a heavy influence on the performance of the whole face recognition system. The algorithms therefore should be computationally fast enough to allow an online detection. In our previous work we have presented an ANN/GA based approach to perform robust, high-speed face localization : ANN (Artificial Neural Network) serves as a face filter while GA (Genetic Algorithm) is used to search the image efficiently. In this paper, we investigate the use of another feature of face images-skin color to make a further improvement. Specifically, by punishing the sub-images with few skin color information with a low fitness, the genetic search can be conducted to the area only with skin color information and thus will greatly speed the search process. Experiment results show that the skin color information improves the performance greatly.

• 一般社団法人日本機械学会の論文
• 2002-11-14

著者

• Sugisaka Masanori

  Dept. Of Electrical & Electronic Eng. Oita University

• Fan X

  Oita Univ. Oita‐shi Jpn

• Fan Xinjian

  Dept. of Electrical & Electronic Eng., Oita University

関連論文

• 1-403 Improving Face Detection Using Skin Color Information
• 1-402 Applications of Adaptive Strategies to an Intelligent Mobile Vehicle
• Feature Point-Based Object Tracking
• Neural Network Based Non-parametric Confidence Bound Estimation for MSPC Chart

スポンサーリンク