Manchu recognition method and system

Abstract

The invention discloses a Manchu recognition method and system, and the method and system can achieve the quick recognition of a part of letters in a text image, so that the Manchu stored in the database corresponding to the Manchu composed of letters can be quickly and accurately positioned according to the recognized letters, and characters and serial numbers of the letters corresponding to allthe letter standard images marked as the associated letters in the database are output. All similar letters are sequentially recognized on the Manchu image through the sliding window, the letters arelocally recognized according to the sliding window, and the local adjustment image is compared according to the letter standard image, so that the operation complexity is reduced, the recognition precision is improved, part of letter areas can be indicated with high accuracy, and local identification ensures letter identification reliability and reduces false detection identification probability.

Description

technical field [0001] The invention relates to the technical field of character recognition, in particular to a method and system for manchu recognition. Background technique [0002] At present, Manchu is the language used by the Manchu, Xibe and other ethnic minorities in my country, although Manchu is a phonetic script. However, due to the particularity of continuous writing and deformation of the letters of the Manchu alphabet system, and it is completely different from the writing rules of modern Chinese, similar to ancient Chinese, it is read and written from top to bottom, from left to right, because Manchu is Pinyin characters are divided into single sounds, compound vowels, consonants and specific letters in letters. The lengths of radicals in different Manchu characters corresponding to these letters are different; in the process of translation and interpretation of Manchu books, Some radicals are often difficult to quickly and accurately identify the correspondi...

AI Technical Summary

Problems solved by technology

However, due to the particularity of continuous writing and deformation of the letters of the Manchu alphabet system, and it is completely different from the writing rules of modern Chinese, similar to ancient Chinese, it is read and written from top to bottom, from left to right, because Manchu is Pinyin characters are divided into single sounds, compound vowels, consonants and specific letters in letters. The lengths of radicals in different Manchu characters corresponding to these letters are different; in the process of translation and interpretation of Manchu books, Some radicals are often difficult to quickly and accurately identify the corresponding characters due to letter continuation, deformation, etc., and there are often many mistakes in recognition, and there are scratches and cracks in the scanned book image due to preservation reasons. and other reasons lead to a significant increase in the error rate of misdetection of Manchu images by existing Manchu recognition methods. This situation often occurs when handwriting Manchu, resulting in inconvenient handwritten Manchu input; therefore, for Manchu recognition methods often need to first segment Manchu into basic units (such as letters, etc.), and then recognize them. Therefore, the improvement of Manchu recognition is often only from improving the segmentation accuracy, but it has not actually solved the problem. The problem of low recognition accuracy caused by letter continuation and deformation; in addition, since Manchu words are composed of one or more Manchu letters connected by the vertical central axis, there is no gap between letters and letters in the same word. The spelling of the letters is located on the central axis of the Manchu word image, so it is difficult for traditional segmentation methods to quickly and accurately identify the Manchu characters formed by the positioning image or handwriting

Images