An improved local feature descriptor via soft binning

Abstract

We describe a robust feature descriptor called soft ordinal spatial intensity distribution (soft OSID) that is invariant to any monotonically increasing brightness changes. In traditional histogram-based feature descriptors, each pixel is explicitly assigned to a single histogram bin, making them not robust to image deformations and appearance changes. In this paper, we present a feature descriptor that is obtained by assigning each pixel to more than one bin where the fraction is determined by a weight function to put more weight on close bins. This makes the descriptor more robust to image changes like viewpoint changes, image blur, and JPEG compression. Extensive experiments show that the proposed descriptor significantly outperforms many state-of-the-art descriptors such as OSID, SIFT, GLOH, and PCA-SIFT under complex brightness changes. The proposed descriptor has far reaching implications for many applications in computer vision.