Segmentation Toolkit

In IMPACT we introduce hierarchical segmentation models that allow the discrete problems of text block, text line, word and character segmentation to be addressed separately. In order to test IMPACT toolkits for each segmentation level, we assume as input the correct result from the previous level. For the case of character segmentation, we present the output (CharSegm_1_Output.jpg, CharSegm_2_Output.jpg, CharSegm_3_Output.jpg) when starting from the correct word segmentation result (CharSegm_1_Input.jpg, CharSegm_2_Input.jpg, CharSegm_3_Input.jpg). The algorithm is based on finding all possible segmentation paths by linking the feature points on the skeleton of the word and its background.


NB: Please note that the word segmentation files correspond to the correct word segmentation (ground truth) and not to a word segmentation output.



Character Segmentation 1 Input
Character Segmentation 1 Output
Character Segmentation 2 Input
Character Segmentation 2 Output
Character Segmentation 3 Input
Character Segmentation 3 Output