Evaluation of Feature Detector-Descriptor for Real Object Matching under Various Conditions of Ilumination and Affine Transformation

TL;DR

This paper evaluates the robustness of various feature detector-descriptor combinations like SIFT, SURF, MSER, BRISK, and FREAK under different illumination and affine transformations using stereo image matching.

Contribution

It provides a comprehensive comparison of popular feature detection and description algorithm combinations under varying conditions, focusing on their matching performance.

Findings

SIFT and SURF show high repeatability under illumination changes.

BRISK and FREAK perform well with affine transformations.

Combination effectiveness varies with image variation types.

Abstract

This study attempts to provide explanations, descriptions and evaluations of some most popular and current combinations of description and descriptor frameworks, namely SIFT, SURF, MSER, and BRISK for keypoint extractors and SIFT, SURF, BRISK, and FREAK for descriptors. Evaluations are made based on the number of matches of keypoints and repeatability in various image variations. It is used as the main parameter to assess how well combinations of algorithms are in matching objects with different variations. There are many papers that describe the comparison of detection and description features to detect objects in images under various conditions, but the combination of algorithms attached to them has not been much discussed. The problem domain is limited to different illumination levels and affine transformations from different perspectives. To evaluate the robustness of all combinations of algorithms, we use a stereo image matching case.