A Scale and Rotational Invariant Key-point Detector based on Sparse Coding

Abstract

Most popular hand-crafted key-point detectors such as Harris corner, SIFT, SURF aim to detect corners, blobs, junctions, or other human-defined structures in images. Though being robust with some geometric transformations, unintended scenarios or non-uniform lighting variations could significantly degrade their performance. Hence, a new detector that is flexible with context change and simultaneously robust with both geometric and non-uniform illumination variations is very desirable. In this article, we propose a solution to this challenging problem by incorporating Scale and Rotation Invariant design (named SRI-SCK) into a recently developed Sparse Coding based Key-point detector (SCK). The SCK detector is flexible in different scenarios and fully invariant to affine intensity change, yet it is not designed to handle images with drastic scale and rotation changes. In SRI-SCK, the scale invariance is implemented with an image pyramid technique, while the rotation invariance is realized by combining multiple rotated versions of the dictionary used in the sparse coding step of SCK. Techniques for calculation of key-points’ characteristic scales and their sub-pixel accuracy positions are also proposed. Experimental results on three public datasets demonstrate that significantly high repeatability and matching score are achieved.

Image Enhancement for the Improved Extraction of Local Image Features Using Image Offsets

“…One such detector that has shown exceptional performance in recent years is SRI-SCK [9,27]. This method breaks up an input image into patches and expresses each patch using sparse coding principles.…”

“…Similar to the experiments conducted in [74,75], testing is conducted with SIFT [8], SURF [14], FAST [31], STAR [73], ORB [44] and SRI-SCK-1 [27] keypoint detectors. All these detectors perform detection in drastically different ways.…”

“…The experiments discussed in this section relate to the distinctiveness of the detected keypoints. Two metrics are used to gauge keypoint strength, these being the Hessian measurement carried out through Equation 2.10 which dictates distinct corner candidacy and the SRI-SCK-1 strength measure proposed in [27] and shown in Equation 3.19.…”