This paper presents how to extract non-linear features by linear PCA. KPCA is effective but the computational cost is the drawback. To realize both non-linearity and low computati...
Sparse coding which encodes the original signal in a sparse signal space, has shown its state-of-the-art performance in the visual codebook generation and feature quantization pro...
We report performance evaluation of our automatic feature discovery method on the publicly available Gisette dataset: a set of 29 features discovered by our method ranks 129 among...
Most of vision-based algorithms for motion and localization estimation requires matching some interest points in a pair of images. After building feature correspondence, it is pos...
The advances in image acquisition techniques make recording images never easier and brings a great convenience to our daily life. It raises at the same time the issue of privacy p...