Fast Training Algorithm by Particle Swarm Optimization for Rectangular Feature Based Boosted Detector
Akinori Hidaka, Takio Kurita · 대한전자공학회 기타 간행물 · 2008
Adaboost is an ensemble learning algorithm that combines many other learning algorithms to improve their performance. Starting with Viola and Jones’ researches [14][15], Adaboost has often been used to local-feature selection for object detection. Adaboost by ViolaJones consists of following two optimization schemes: (1) parameter fitting of local features, and (2) selection of the best local feature. Because the number of local features becomes usually more than tens of thousands, the learning algorithm is very time consuming if ones completely do the two optimizations. In this paper, we propose fast boosting algorithms by using particle swarm optimization (PSO). Proposed learning algorithm is 25 times faster than the usual Adaboost while keeping comparable classification accuracy.