Abstract: An image processing apparatus comprises: an image input unit to input an image; an image thinner for getting the OR of (m dots in the vertical direction)×(n dots in the horizontal direction) for the input image from the image input unit, thereby thinning out the (m×n) pixels and newly forming one pixel; a labeler for adding labels every line to black pixels of the image which was thinned out by the image thinner and adding the same label to the pixels which are continuous in the vertical, horizontal, or oblique direction and simultaneously tracing a rectangle; and a separator detector for distinguishing a rectangle corresponding to a sentence portion, a rectangle corresponding to a figure or photograph, a rectangle corresponding to a table, a rectangle corresponding to a separator, and the like by using a width, a height, an area, and a pixel density (the number of pixels to the area) of the rectangle added with the label by the labeler.

Abstract: An image processing apparatus includes an image input unit which inputs an image, and an image thinner for taking the OR of (m dots in the vertical direction).times.(n dots in the horizontal direction) of the input image, thereby thinning out the (m.times.n) pixels and newly forming one pixel. A labeler adds labels to black pixels of every line of the thinned out image. The same label is added to pixels which are continuous in the vertical, horizontal or oblique direction and simultaneously traces a rectangle. A separator detector distinguishes a rectangle corresponding to a sentence portion, a rectangle corresponding to a figure or photograph, a rectangle corresponding to a table, and a rectangle corresponding to a separator, by using a width, a height, an area, and a pixel density (the number of pixels in the area) of the rectangle added to the label by the labeler. The area of the input image is divided based on the result of the detection of the separator detector.

Abstract: There is provided an image processing method whereby a slope at a first position on an outline of character data in input image data is extracted and phase data at a second position on a background of the character data is also extracted. The second position exists in the normal direction of the slope at the first position and is away from the first position by a predetermined distance. The phase data is based on states of black pixels in a plurality of predetermined directions at a target point. The predetermined distance depends on the size of character data.