COnfusion REduction (CORE) algorithm for local descriptors, floating-point and binary cases

Frederic Bouchara (1) , Emilien Royer (1) , Thibault Lelore (1)

1 LIS - Laboratoire d'Informatique et Systèmes

In this paper, we propose a generic pre-filtering method of point descriptors which addresses the confusion problem due to repetitive patterns. This confusion often leads to wrong descriptor matches and prevents further processes such as object recognition, image indexation, super-resolution or stereo-vision. Our method sorts keypoints by their unicity without taking into account any visual element but the feature vectors's statistical properties thanks to a kernel density estimation approach. Both binary descriptors and floating point based descriptors are studied, regardless of their dimensions. Even if highly reduced in number, results show that keypoints subsets extracted are still relevant and our algorithm can be combined with classical post-processing methods.

Keywords: keypoints filtering; computer vision; feature matching; kernel density

Domains: Computer Science [cs]; Image Processing [eess.IV]; Artificial Intelligence [cs.AI]

Frederic Bouchara, Emilien Royer, Thibault Lelore. COnfusion REduction (CORE) algorithm for local descriptors, floating-point and binary cases. Computer Vision and Image Understanding, 2017, 158, pp.115 - 125. ⟨10.1016/j.cviu.2017.01.005⟩. ⟨hal-01873102⟩