Comparative evaluation of 2D feature correspondence selection algorithms
It provides a comprehensive user guide for developers in computer vision to choose appropriate algorithms for feature-matching tasks, though it is incremental as it focuses on evaluation rather than new methods.
This paper tackles the problem of selecting correct feature correspondences in 2D images by evaluating eight algorithms on four standard datasets, finding that no single algorithm excels across all metrics like precision, recall, F-measure, and efficiency.
Correspondence selection aiming at seeking correct feature correspondences from raw feature matches is pivotal for a number of feature-matching-based tasks. Various 2D (image) correspondence selection algorithms have been presented with decades of progress. Unfortunately, the lack of an in-depth evaluation makes it difficult for developers to choose a proper algorithm given a specific application. This paper fills this gap by evaluating eight 2D correspondence selection algorithms ranging from classical methods to the most recent ones on four standard datasets. The diversity of experimental datasets brings various nuisances including zoom, rotation, blur, viewpoint change, JPEG compression, light change, different rendering styles and multi-structures for comprehensive test. To further create different distributions of initial matches, a set of combinations of detector and descriptor is also taken into consideration. We measure the quality of a correspondence selection algorithm from four perspectives, i.e., precision, recall, F-measure and efficiency. According to evaluation results, the current advantages and limitations of all considered algorithms are aggregately summarized which could be treated as a "user guide" for the following developers.