A New Method for Hand Detection Based on Hough Forest

Dongyue Chen, Zongwen Chen, Xiaosheng Yu

Abstract: We present a discriminative Hough transform based object detector where each local part casts a weighted vote for the possible locations of the object center. We formulate such an object model with an ensemble of randomized trees trained by splitting tree nodes so as to lessen the variance of object location and the entropy of class label. Hough forests can be regarded as task-adapted codebooks of local appearance that allow fast supervised training and fast matching. Experimental results demonstrate that our method has a significant improvement. Compared to other approach such as implicit shape models, Hough forests improve the performance for hands detection on a categorical level.