Automatic Thresholding of SIFT Descriptors
This addresses image matching accuracy for computer vision applications, but it is incremental as it builds on existing SIFT methodology.
The paper tackles the problem of improving SIFT descriptor matching by introducing an automatic thresholding method, resulting in at least a 15.9% performance gain on the Oxford image matching benchmark.
We introduce a method to perform automatic thresholding of SIFT descriptors that improves matching performance by at least 15.9% on the Oxford image matching benchmark. The method uses a contrario methodology to determine a unique bin magnitude threshold. This is done by building a generative uniform background model for descriptors and determining when bin magnitudes have reached a sufficient level. The presented method, called meaningful clamping, contrasts from the current SIFT implementation by efficiently computing a clamping threshold that is unique for every descriptor.