상세정보
학술대회
Tiny Frontal Face Detection for Robots
- 발행일
- 201008
- 출처
- International Conference on Human-Centric Computing (HumanCom) 2010, pp.1-4
- 협약과제
- 10MC4300, u-로봇 HRI 솔루션 및 핵심 소자 기술 개발, 조재일
- 초록
- This paper proposes a novel face detection method that finds tiny faces located at a long range even with low-resolution input images captured by a moving robot. The proposed approach can locate extremely small-sized face regions of 12×12 pixels by combining the results from mean-shift color tracking, short- and long-range face detection, and omega shape detection. According to the experimental results on realistic databases, the performance of the proposed approach is at a sufficiently practical level for various robot applications. © 2010 IEEE.
- KSP 제안 키워드
- Color Tracking, Detection Method, Frontal face detection, Long-range, Mean-shift(MS), Moving robot, Omega shape, Robot applications, Shape detection, Short-, Small-sized