SCK: A sparse coding based key-point detector

02/07/2018 ∙ by Thanh Hong Phuoc, et al. ∙ 0

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 the total number of non-zero components of a sparse representation of the block. Generally, a block constructed with more components is more complex and has more 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.



There are no comments yet.


page 4

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.