Image Feature Extraction Subsystem of the ImageRover WWW Image Search System.

The focus of this project was to modify the image feature extraction subsystem of the ImageRover system[11]. The subsystem was extended to use color and texture measures which more closely correspond to the human perception. The feature implemented for color is the color histogram in L u v color space. The texture measure implemented is 2D Wold decomposition, which incorporates the three most important for human perception measures, \directionality", \periodicity" and \randomness." Texture module performance was evaluated on the Brodatz texture album. The resulting modules are now part of the ImageRover system.