SCK: A sparse coding based key-point detector
This provides a novel key-point detection method for computer vision applications, offering an alternative to hand-crafted and learning-based detectors.
The paper tackles the problem of key-point detection in images by proposing a sparse coding based detector that measures block complexity to identify key-points without pre-designed structures. Experimental results show it achieves high repeatability and outperforms state-of-the-art learning based detectors in matching scores on Webcam and EF datasets.
All current popular hand-crafted key-point detectors such as Harris corner, MSER, SIFT, SURF... rely on some specific pre-designed structures for the detection of corners, blobs, or junctions in an image. In this paper, a novel sparse coding based key-point detector which requires no particular pre-designed structures is presented. The key-point detector is based on measuring the complexity level of each block in an image to decide where a key-point should be. The complexity level of a block is defined as the total number of non-zero components of a sparse representation of that block. Generally, a block constructed with more components is more complex and has greater potential to be a good key-point. Experimental results on Webcam and EF datasets [1, 2] show that the proposed detector achieves significantly high repeatability compared to hand-crafted features, and even outperforms the matching scores of the state-of-the-art learning based detector.