A binary based HMAX model for object recognition

In this paper, we propose a fast binary based HMAX model (B-HMAX). In our method, we detect corner based interest points after the second layer C1 to extract fewer numbers of features with better distinctiveness, and use binary string to describe the image patches extracted around detected corners, then use hamming distance for matching between two patches in the third layer S2, which is much faster than Euclidean method. Experimental results demonstrate that our proposed B-HMAX model can significantly reduce the total process time, while keeping the accuracy performance as the same with or better than standard HMAX.