2004/11/13 by Sai Ravela · 1 citation
Computer Science · Mathematics · Engineering · #Image Retrieval and Classification Techniques #Advanced Image and Video Retrieval Techniques #Affine transformation #Kernel (algebra) #Pattern recognition (psychology) #Feature (linguistics) #Filter (signal processing) #Feature extraction #Artificial intelligence #Matching (statistics) #Differential (mechanical device) #Computer science #Mathematics #Gaussian #Harris affine region detector #Affine combination #Affine shape adaptation #Algorithm #Computer vision #Engineering #Physics
paper · doi:10.1109/cvpr.2004.1315236
openalex publication_date 2004/11/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29
The Gaussian kernel has played a central role in multi-scale methods for feature extraction and matching. In this paper, a method for shaping the filter using the local image structure is presented. We propose an optimization formulation that densely estimates the filter's affine parameters by minimizing an objective constructed from differential feature responses and seek iterative, approximate solutions. A consequence of shaping the filters is affine invariance of the differential feature vector and it is shown that the shaped responses improve recognition performance.