摘要 |
Read image data is divided into a plurality of regions, and a histogram is generated and edges are counted for each region. Blank page detection is performed based on a variance value computed from the histogram of each region. Also, the variance between regions is computed from the edge count of each region, and blank page detection is performed according to the amount of variance. It is then determined whether the document is blank or content based on the result of detection by histogram and the result of detection by edge count. |