Real Time Non-rigid Surface Detection Based on Binary Robust Independent Elementary Features

The Feature Descriptor sometimes called descriptors has been a hot research topic and is a difficult challenge, a common feature descriptor algorithm is used to detect target, and further do other application cases automatically control, product inspection, face recognition and object tracking. For subsequent applications will therefore need to address issues related to extending such an object view to change, scale, rotation and multi-target detection, etc., so they need for effective algorithms to solve the above problems. In this paper we proposed based BRIEF (Binary Robust Independent Elementary Features)[1] binary feature descriptor to improve the non-rotational invariance of the shortcomings.