BI-TONAL IMAGE NON-TEXT MATTER REMOVAL WITH RUN LENGTH AND CONNECTED COMPONENT ANALYSIS

摘要

In processing a text image prior to optical character recognition processing, non-text graphical material is removed from the image by first discarding all lines in accordance with the length of the line and/or the percentage of black pixels in the entire pixel row (or column) in which the line is located. The line length and black pixel percentage are parameters which are traded off against one another on a sliding scale. Then, the remaining objects in the image are processed in a two-step process in which: (a) objects whose size is above a maximum threshold or below a minimum threshold are discarded and (b) individual sub-objects comprised within any of the discarded objects whose individual area and height are within threshold percentages of the median area and height of all objects in the image are restored to the image.