Abstract: Systems and methods for automatic generation of a browsing path across image content to present areas with high attention value are described. In particular, an image is modeled via multiple visual attentions to create a respective set of attention objects for each modeled attention. The attention objects and their respective attributes are analyzed to generate a browsing path to select ones of the attention objects. The browsing path is generated to optimize the rate of information gain from the attention objects as a function of information unit cost in terms of time constraints associated with multiple image browsing modes.

Abstract: In one embodiment, mapping color data from CMY to CMYK is performed in a manner which allows selection between creating better harmony between process-neutral and K-only neutral images when printed side-by-side, or creating better-looking images individually. In the course the mapping, adjustment is made over a degree to which BG (black generation) color coefficient generation is similar for process-neutral and K-only neutral images to produce BG coefficients. Similarly, adjustment is made over a degree to which UCR (under color removal) color coefficient generation is similar for process-neutral and K-only neutral images to produce UCR coefficients. Color data is them mapped, using the produced BG coefficients and the produced UCR coefficients.

Abstract: To provide an image coding apparatus that can generate a code that can be decoded by a general decoding apparatus while attaining a high coding speed. As a result of processing in a plurality of prediction units 21, a control unit 11 generates a predicted pixel value for a pixel of interest based on a pixel value of a predicting pixel located at a distance from the pixel of interest, the distance being predetermined for each pixel value prediction unit 21, counts, as a run-length for each pixel value prediction unit 21, the number of times that the pixel value of the pixel of interest successively correspond with the predicted pixel value, selects any of pixel value prediction units related to a run-length of one pixel or more, and outputs a code by referring to a predetermined code table with respect to a distance between the pixel of interest and the predicting pixel for the selected pixel value prediction unit 21 and the run-length thereof.