Efficient incremental learning of boosted classifiers for object detection
Pramod Kumar Sharma, Chang Huang, Ram Nevatia · 2012
Significant progress has been made towards learning a generalized offline object detector. However, when a generalized offline detector is applied on new datasets, it often makes mistakes by missing some specific instances of the object or by producing false detections in the background scene. In order to rectify these mistakes made by the offline detector, we present a novel and efficient incremental learning method, which adjusts the parameters of offline trained cascade of boosted classifiers using manually labeled online samples. Experiments demonstrate both the efficiency and effectiveness of our approach. 1.