원문정보
초록
영어
In this paper, a novel affine invariant descriptor for object matching is proposed. The advantage of Maximally Stable Extremal Regions (MSER) method is applied to get the most stable regions in the image. Inside each region, we pick the seeds as keypoints since MSER regions are invariant to affine transformation. Besides that, Voronoi diagram is employed to split the image into small Voronoi cells or local regions based on the key points picked in the previous step. Finally, local features inside each local region including color, texture and geometric properties are extracted to generate the descriptor. Our experiments demonstrate that the proposed affine invariant local descriptor based on Voronoi tessellation is more stable and robust to object matching than SIFT descriptor while using the same keypoints.
목차
1. Introduction
2. Keypoint Detector
3. Local Feature Extraction
3.1. Geometric Feature Extraction
3.2. Color Feature Extraction
3.3. Texture and Region Feature Extraction
3.4. Feature Descriptors
4. Experimental Results and Conclusions
4.1. Dataset and Ground Truth
4.2. Experimental Results
Acknowledgements
References