Issue No. 01 - Jan. (2014 vol. 36)
Xin Yang , Electr. & Comput. Eng. Dept., Univ. of California, Santa Barbara, Santa Barbara, CA, USA
Kwang-Ting Cheng , Electr. & Comput. Eng. Dept., Univ. of California, Santa Barbara, Santa Barbara, CA, USA
The efficiency and quality of a feature descriptor are critical to the user experience of many computer vision applications. However, the existing descriptors are either too computationally expensive to achieve real-time performance, or not sufficiently distinctive to identify correct matches from a large database with various transformations. In this paper, we propose a highly efficient and distinctive binary descriptor, called local difference binary (LDB). LDB directly computes a binary string for an image patch using simple intensity and gradient difference tests on pairwise grid cells within the patch. A multiple-gridding strategy and a salient bit-selection method are applied to capture the distinct patterns of the patch at different spatial granularities. Experimental results demonstrate that compared to the existing state-of-the-art binary descriptors, primarily designed for speed, LDB has similar construction efficiency, while achieving a greater accuracy and faster speed for mobile object recognition and tracking tasks.
Robustness, Training, Real-time systems, Face, Training data, Detectors, Databases
Xin Yang and Kwang-Ting Cheng, "Local Difference Binary for Ultrafast and Distinctive Feature Description," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 36, no. 1, pp. 188-194, 2013.