SCK: A sparse coding based key-point detector

TL;DR

This paper introduces a novel sparse coding based key-point detector that measures block complexity to identify key-points, outperforming traditional hand-crafted and some learning-based detectors in repeatability and matching scores.

Contribution

The paper presents a new key-point detection method based on sparse coding complexity, eliminating the need for pre-designed structures and improving detection performance.

Findings

Achieves higher repeatability than traditional detectors

Outperforms some state-of-the-art learning-based detectors

Demonstrates effectiveness on Webcam and EF datasets

Abstract

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.