| 摘要 |
A method of processing image data comprising generating saliency data for the image by determining a series of features of the image, using the determined features to generate a probability measure for each point of the image representing a location of a subject in the image, processing the saliency data using weighting functions of a plurality of different sized areas in order to determine the positions of regions of interest in the image in the respective areas, and generating response data for each area representing the relative strength of response of the saliency data at the positions of the regions of interest to the weighting function for that area and sequentially displaying these regions according to this. |
