A DCT-based multiscale Binary descriptor robust to complex brightness changes

Binary descriptors have been very popular in recent years. One reason is that the algorithms that use them become computationally and memory-wise efficient. Furthermore, they tend to have some inherent robustness against some geometrical variations and against various brightness changes. These changes might result from both internal factors and external factors such as location of the light source, viewing angle, scene properties. In this paper, we describe a binary descriptor which proves to be robust to complex brightness changes such as gamma correction, noise and photometric distortions. The experimental results demonstrate that performance of the descriptor in object recognition and local image analysis tasks.