Complex Salient Regions for Computer Vision Problems

The goal of interest point detectors is to find in an unsupervised way, keypoints easy to extract and at the same rime robust to image transformations. We present a novel set of saliency features based on image singularities that takes into account the region content in terms of intensity and local structure. The region complexity is estimated by means of the entropy of the grey-level information: shape information is obtained by measuring the entropy of significant orientations. The regions are located in their representative scale and categorized by their complexity level. Thus, the regions are highly discriminable and less sensitive to confusion and false alarm titan the traditional approaches. We compare the novel complex salient regions with the state-of-the-art keypoint detectors. The presented interest points show robustness to a wide set of image transformations and high repeatability, as well as allow matching from different camera points of view. Besides, we show the temporal robustness of the novel salient regions in real video sequences, being potentially useful for matching, image retrieval and object categorization problems.