Đang chuẩn bị liên kết để tải về tài liệu:
Báo cáo hóa học: "Research Article DOOMRED: A New Optimization Technique for Boosted Cascade Detectors on Enforced Training Set"

Tuyển tập báo cáo các nghiên cứu khoa học quốc tế ngành hóa học dành cho các bạn yêu hóa học tham khảo đề tài: Research Article DOOMRED: A New Optimization Technique for Boosted Cascade Detectors on Enforced Training Set | Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2008 Article ID 183804 11 pages doi 10.1155 2008 183804 Research Article DOOMRED A New Optimization Technique for Boosted Cascade Detectors on Enforced Training Set Dong Woo Park1 and Kyoung Mu Lee2 1 Information Technology Laboratory LG Electronics Institute of Technology 16 Woomyeon-dong Seocho-gu Seoul 137-724 Korea 2 Department of Electrical Engineering ASRI Seoul National University 599 Gwanangno Gwanak-gu Seoul 151-742 Korea Correspondence should be addressed to Kyoung Mu Lee kyoungmu@snu.ac.kr Received 31 August 2007 Revised 27 December 2007 Accepted 19 February 2008 Recommended by Olivier Lezoray We propose a new method to optimize the completely-trained boosted cascade detector on an enforced training set. Recently due to the accuracy and real-time characteristics of boosted cascade detectors like the Adaboost a lot of variant algorithms have been proposed to enhance the performance given a fixed number of training data. And most of algorithms assume that a given training set well exhibits the real world distributions of the target and non-target instances. However this is seldom true in real situations and thus often causes higher false-classification ratio. In this paper to solve the optimization problem of completely trained boosted cascade detector on false-classified instances we propose a new base hypothesis weight optimization algorithm called DOOMRED Direct Optimization Of Margin for Rare Event Detection using a mathematically derived error upper bound of boosting algorithms. We apply the proposed algorithm to a cascade structured frontal face detector trained by AdaBoost algorithm. Experimental results demonstrate that the proposed algorithm has competitive ability to maintain accuracy and realtime characteristic of the boosted cascade detector compared to those of other heuristic approaches while requiring reasonably small amount of optimization time. Copyright