| 摘要 |
A line region segmentation method includes the steps of grouping pixels of an input image indicated by image signals into three sets of black, gray and white pixels, performing a pattern matching of black pixels in a region of the input image with a set of matrix patterns to determine if a black pixel is closely associated with other pixels and determine if a black pixel is one of screened black pixels for each pixel of the set of black pixels, deciding if the black pixel being considered is one of black bilevel pixels by checking the number of black pixels that are determined as being associated black pixels and as being non-screened black pixels, performing a pattern matching of white pixels in a region of the input image with a set of matrix patterns to determine if a white pixel is closely associated with other pixels for each pixel of the set of white pixels, deciding if the white pixel being considered is one of white bilevel pixels by checking the number of white pixels that are determined as being associated white pixels, and determining if a pixel being considered is one of bilevel pixels by checking the number of the black bilevel pixels and the number of the white bilevel pixels.
|
