A document processing apparatus for segmenting a color document image into regions obtains a binary image by binarizing a color image, and extracts regions having different background colors from the color image to generate region information indicating the position and size of each extracted region. By making region segmentation on the basis of the binary image and region information, a region segmentation result that reflects the background colors can be obtained. In this way, region segmentation which can maintain region differences expressed by colors in a color document can be implemented.