Evaluation of Feature Detector-Descriptor for Real Object Matching under Various Conditions of Ilumination and Affine Transformation
This work provides an incremental analysis for computer vision researchers by comparing algorithm combinations in specific conditions, but does not introduce new methods.
The study evaluated combinations of popular feature detector-descriptor algorithms (SIFT, SURF, MSER, BRISK, FREAK) for object matching under varying illumination and affine transformations, using keypoint matches and repeatability as metrics in a stereo image matching case.
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.