Zhuhan Jiang

Learn More
We propose an iterative method of Weighted Region Consolidation to track a camouflaged object within a background of very close colour in an image sequence, where the colours for both the object and the background are unsteady with large noises. More precisely, we will first detect the object motion based on both spatial and intensity densities by locating(More)
Grouping images into semantically meaningful categories using basic low-level visual features is a challenging and important problem in content-based image retrieval. The enormity and diversity of the visual contents on the Web images adds another dimension to this challenging task. Moreover, the retrieval of Web images cannot be easily achieved with images(More)
We propose a wavelet-based watermarking scheme by dynamically constructing the filters embedded within the watermark as well as the potential of the private key patterns associated with the individual images. This scheme explores the watermark dissemination in a non-traditional dimension, allows the dual purpose of the embedded data as either watermarks or(More)