Morphology and integral projection-based printed Uygur document segmentation method

Abstract

The invention discloses a morphology and integral projection-based printed Uygur document segmentation method, and mainly solves the problem of flexibility limitation during acquisition of a row document image and the problem of missing segmentation of a character define in the specification during acquisition of a single-character image in an existing segmentation method. The method comprises the steps of (1) inputting a binary image; (2) acquiring the row document image; (3) acquiring a sub-word image; (4) acquiring a connected segment image; (5) acquiring a connected segment image only with a main body stroke part; (6) determining a baseline domain of the connected segment image only with the main body stroke part; and (7) acquiring the single-character image. Compared with an existing printed Uygur document segmentation method, the morphology and integral projection-based printed Uygur document segmentation method has the advantages that a threshold is not set during the acquisition of the row document image, so that the flexibility is better, the problem of the missing segmentation of the character define in the specification is avoided, and the accuracy of printed Uygur document segmentation can be improved.

Description

technical field [0001] The invention belongs to the field of character segmentation in optical character classification, and further relates to a method for segmenting printed Uighur documents based on morphology and integral projection in the field of character segmentation in optical character classification. The invention can be used to segment the paper Uyghur document image scanned by a scanner into individual Uyghur character images, and do precondition work for the segmentation-based printed Uyghur document recognition. Background technique [0002] At present, printed Uyghur document recognition based on segmentation is widely used. Therefore, accurately segmenting Uyghur characters from Uyghur document images is the premise and basis for printed Uyghur document recognition. However, because the Uyghur language borrows the writing form of Arabic and Persian alphabets, which belongs to the cohesive phonetic alphabet, and its shape is similar to our Chinese cursive sc...

AI Technical Summary

Problems solved by technology

Although this method can segment the line document image in the entire Uyghur document image, the method still has the disadvantage that: this method sets a threshold in the line segmentation step to distinguish whether it is line spacing or Intra-line spacing limits the flexibility of this method; when character segmentation, there are some over-segmentation and omission-segmentation problems, which will be in the form of Such characters are over-segmented and will look like Such upper and lower covered characters are split when splitting

Although this method can avoid the missing segmentation when there is upper and lower coverage, the disadvantage of this method is that it will also affect the shape such as This character causes the problem of missing segmentation

Images