Constructing Binary Descriptors with a Stochastic Hill Climbing Search
This work addresses the need for efficient image processing methods in computer vision, though it appears incremental as it builds on existing binary descriptor techniques.
The paper tackled the problem of constructing binary descriptors for image patches to improve processing speed and reduce storage compared to real-number vectors, and demonstrated that a stochastic hill climbing bit selection procedure outperforms recent alternatives on a standard discriminative power benchmark.
Binary descriptors of image patches provide processing speed advantages and require less storage than methods that encode the patch appearance with a vector of real numbers. We provide evidence that, despite its simplicity, a stochastic hill climbing bit selection procedure for descriptor construction defeats recently proposed alternatives on a standard discriminative power benchmark. The method is easy to implement and understand, has no free parameters that need fine tuning, and runs fast.