An Efficient Single Chord-based Accumulation Technique (SCA) to Detect More Reliable Corners

TL;DR

This paper introduces an efficient single chord-based accumulation technique (SCA) that improves the reliability and accuracy of corner detection in computer vision, addressing limitations of the CPDA detector.

Contribution

The paper proposes a novel SCA method that reduces localization errors and enhances repeatability compared to the existing CPDA detector, with similar preprocessing steps.

Findings

SCA achieves lower localization error than CPDA.

SCA demonstrates higher repeatability and robustness.

Experimental results confirm improved detection performance.

Abstract

Corner detection is a vital operation in numerous computer vision applications. The Chord-to-Point Distance Accumulation (CPDA) detector is recognized as the contour-based corner detector producing the lowest localization error while localizing corners in an image. However, in our experiment part, we demonstrate that CPDA detector often misses some potential corners. Moreover, the detection algorithm of CPDA is computationally costly. In this paper, We focus on reducing localization error as well as increasing average repeatability. The preprocessing and refinements steps of proposed process are similar to CPDA. Our experimental results will show the effectiveness and robustness of proposed process over CPDA.