SCK: A sparse coding based key-point detector.
All current popular hand-crafted key-point detectors such as Harris corner,MSER, SIFT, SURF... rely on some specific pre-designed structures for thedetection of corners, blobs, or junctions in an image. In this paper, a novelsparse coding based key point detector which requires no particularpre-designed structures is presented. The key-point detector is based onmeasuring the complexity level of each block in an image to decide where akey-point should be. The complexity level of a block is the total number ofnon-zero components of a sparse representation of the block. Generally, a blockconstructed with more components is more complex and has more potential to be agood key-point. Experimental results on Webcam and EF datasets [1, 2] show thatthe proposed detector achieves significantly high repeatability compared tohand-crafted features, and even outperforms the matching scores of thestate-of-the-art learning based detector.
Continue reading and listening
Stay in the loop.
Subscribe to our newsletter for a weekly update on the latest podcast, news, events, and jobs postings.