Method for segmenting handwritten Chinese characters at position of amount in words of financial bill

Abstract

The invention discloses a method for segmenting handwritten Chinese characters at the position of an amount in words of a financial bill, and the method comprises the following steps: selecting a handwritten Chinese character region at the position of an amount in words; calculating the optimal segmentation threshold of the image by using the Otsu algorithm: traversing the gray value of the image,summing and averaging to obtain the threshold of preliminary segmentation, traversing the threshold from 0 to 255, calculating the variance value of the foreground and the background for each traversing, judging that the difference between the foreground and the background is maximum when the variance value is maximum, and taking the obtained threshold as the optimal segmentation threshold at themoment; binarizing the image by using the optimal segmentation threshold to obtain a binary image of handwritten Chinese character and background segmentation; calculating the Chinese character average height through transverse projection; determining an optimal width sequence through longitudinal projection; and segmenting handwritten Chinese characters at the position of the amount in words byusing the average height and the optimal width sequence.

Description

technical field [0001] The invention relates to the field of sheet-like paper medium processing, in particular to a method for segmenting handwritten Chinese characters at capitalized amounts at financial notes. Background technique [0002] At present, in the field of character processing, handwritten Chinese character segmentation and recognition technology is developing rapidly, its recognition accuracy is gradually improving, its application scenarios are expanding, and its related products are becoming more and more mature. The application effect in the recognition scene is not ideal. [0003] Different from other Chinese handwriting application scenarios, there are fewer types of Chinese characters in uppercase amounts on financial bills. There are about 20 Chinese characters such as one, two, three, four, five, six, seven, etc. Due to the limitation of the length of the handwriting area, the Chinese characters are close to each other and stick together The situation ...

AI Technical Summary

Problems solved by technology

[0002] At present, in the field of character processing, handwritten Chinese character segmentation and recognition technology is developing rapidly, its recognition accuracy is gradually improving, its application scenarios are expanding, and its related products are becoming more and more mature. The application effect in the recognition scene is not ideal

[0003] Different from other Chinese handwriting application scenarios, there are fewer types of Chinese characters in uppercase amounts on financial bills. There are about 20 Chinese characters such as one, two, three, four, five, six, seven, etc. Due to the limitation of the length of the handwriting area, the Chinese characters are close to each other and stick together The situation is very common, and when handwriting Chinese characters, the font style varies from person to person, the font size is inconsistent, and phenomena such as continuous strokes and chaotic strokes occur frequently, which makes it very difficult to accurately segment characters

Images