A method and terminal for detecting integrity of character segments

Abstract

The invention relates to a method and a terminal for detecting the integrity of character segments, belonging to the field of data processing. The present invention obtains the first coordinate information of the character segment in the image; calculates the second coordinate information according to the first coordinate information, so that the range of the area corresponding to the second coordinate information is larger than that corresponding to the first coordinate information area range; detecting a single character within the area range corresponding to the second coordinate information according to a preset target detection algorithm to obtain the coordinate information of the single character; counting the pixel points of a single character according to the coordinate information of a single character number, to obtain the first number of pixels; to count the number of pixels corresponding to the single character within the area corresponding to the first coordinate information, to obtain the second number of pixels; if the first number of pixels is obtained; If the ratio of the number of two pixels to the number of the first pixel is greater than a preset threshold, then the information marking the single character is complete. Improve the accuracy of OCR recognition.

Description

technical field [0001] The invention relates to a method and a terminal for detecting the integrity of character segments, belonging to the field of data processing. Background technique [0002] With the development of science and technology, and the demand for electronicization, more and more optical images need to be entered into the computer for text recognition. In the fields of finance and taxation, economic investigation, etc., the staff need to spend a lot of time carefully inputting bill information, and the tedious and repetitive input work is prone to errors. In order to reduce the tedious input work and the occurrence of errors, the input algorithm based on OCR recognition has changed become more and more important. [0003] Although the recognition accuracy of many OCRs is very high, even the accuracy rate can reach 99%, but in fields such as taxation, such an amount of errors is intolerable, and the point where the error occurs is uncertain, making it impossib...

AI Technical Summary

Problems solved by technology

In the fields of finance and taxation, economic investigation, etc., the staff need to spend a lot of time carefully inputting bill information, and the tedious and repetitive input work is prone to errors. In order to reduce the tedious input work and the occurrence of errors, the input algorithm based on OCR recognition has changed more and more important

[0003] Although the recognition accuracy of many OCRs is very high, even the accuracy rate can reach 99%, but in fields such as taxation, such an amount of errors is intolerable, and the point where the error occurs is uncertain, making it impossible for OCR to know in advance where it will be. Recognition error, after the recognition is completed, it is not known whether the recognized result is the real value

Images