Character recognition method based on fitting functions

Abstract

The invention discloses a character recognition method based on fitting functions, which comprises the following steps of: fitting lines forming a character to be recognized, converting the character into a plurality of polynomial functions and describing and then taking out a template with the highest similarity as a recognition result by analyzing the similarity of fitting functions and standard functions of a template base. The invention not only can recognize Chinese characters but also can recognize numbers, letters and some special symbols and has higher executing efficiency and accuracy.

Description

technical field [0001] The invention belongs to the fields of pattern recognition, artificial intelligence and text information processing, and in particular relates to a text recognition method based on a fitting function. Background technique [0002] With the promotion and application of computer technology, especially the increasing popularity of the Internet, human beings rely more and more on computers to obtain various information. A large amount of information processing work is also transferred to the computer. In daily life and work, there are a large number of text information processing problems, so the requirement of quickly inputting text information into the computer has become very urgent. [0003] The current general character recognition algorithm is based on the dot matrix analysis of the graphics to be recognized. There are great limitations in the recognition of characters with more complex lines that make up the characters. For example, there are speci...

AI Technical Summary

Problems solved by technology

Only by taking these distributions into account can more accurate classification and identification be carried out, so it is not enough to describe the characteristics with only the average value of the characteristics

[0005] The Bayesian classification algorithm uses a probability density function method to describe the characteristics of Chinese characters with a piecewise linear function, which can well identify the characteristic distribution of Chinese characters, but because the distribution of characteristic values ​​​​is usually not a simple statistical distribution, If there is no simple way to describe these probability density functions, the storage space required by the probability density functions representing all Chinese characters' dimensional features will be unbearable for practical systems

[0006] The above two methods cannot classify complex graphics very well, and the accuracy and efficiency of text recognition are very low.

Images