Abstract
Scale and affine-invariant local features have shown excellent performance in image matching, ob ject and texture recognition. This pa- per optimizes keypoint detection to achieve stable local descriptors, and therefore, an improved image representation. The technique performs scale selection based on a region descriptor, here SIFT, and chooses re- gions for which this descriptor is maximally stable. Maximal stability is obtained, when the difference between descriptors extracted for consec- utive scales reaches a minimum. This scale selection technique is applied to multi-scale Harris and Laplacian points. Affine invariance is achieved by an integrated affine adaptation process based on the second moment matrix. An experimental evaluation compares our detectors to Harris- Laplace and the Laplacian in the context of image matching as well as of category and texture classification. The comparison shows the improved performance of our detector.