We construct an image segmentation scheme that combines top-down (TD) with bottom-up (BU) processing. In the proposed scheme, segmentation and recognition are intertwined rather th...
The calculation of local features at points of interest is a vital part of many current image retrieval and object detection systems. The wavelet-based interest point detector by ...
Abstract. This paper presents an algorithm for the estimation of multiple regions with unknown shapes and positions using multiple active contour models (ACM’s). The algorithm or...
We describe and demonstrate CBGIR, a web-based system for performing content-based image retrieval in large sets of high-resolution overhead images. The system provides a familiar...
Shawn Newsam, Daniel Leung, Oscar Caballero, Justi...
Abstract. In recent years the problem of object recognition has received considerable attention from both the machine learning and computer vision communities. The key challenge of...