Semantic recognition-oriented paper translation method and translation pen device

Abstract

The invention relates to a semantic recognition-oriented paper translation method and a semantic recognition-oriented translation pen device. The semantic recognition-oriented paper translation method comprises the following steps: (1) carrying out basic encoding on English characters; establishing a character encoding library, a rule library and a font library; combining and arraying the character encoded library, the rule library and the font library to form an encoding preparation library; (2) carrying out scanning recognition on paper English to be translated by using OCR (Optical Character Recognition); (3) encoding recognized character strings by using the encoding preparation library; (4) carrying out semantic processing on the encoded character strings so as to finish encoding semantic description; (5) obtaining accurately-recognized English words by using cognitive inference of OCR for recognizing words; (6) connecting the English words which are accurately recognized by the OCR with an electronic dictionary so as to realize automatic translation. Compared with the prior art, encoding, semantic processing, inference and traditional OCR are combined so that the false accepted rate caused by traditional OCR file recognition is reduced.

Description

technical field [0001] The invention belongs to the cross field of the combination of semantic recognition and optics, and in particular relates to a semantic recognition-oriented paper translation method and a translation pen device. Background technique [0002] With the advent of the "Internet +" era, the information industry has gradually become a supporting industry, and people's lives and thinking patterns have undergone important changes. The way to obtain services has shifted from the traditional face-to-face and telephone contact to the Internet. Online transactions and payments; the way to acquire knowledge has also shifted from traditional books, dictionaries, and single databases to the Internet. In this way, not only can you quickly obtain services that meet your needs on the Internet, but you can also obtain more accurate and effective service results as much as possible. As the field of translation, it has become an important language link for people to furth...

AI Technical Summary

Problems solved by technology

As the field of translation, it has become an important language link for people to further integrate with the world. However, because different countries and regions use different languages, and English is the international standard, English has become an international language and the communication of documents, documents, etc. the mainstream; as people in non-English-speaking countries and regions, they are still not familiar with and proficient in using English to complete their work

Therefore, in recent years, electronic translation (mouse word extraction) software based on Internet technology has been used to solve the problem of small vocabulary encountered by people. These software have good translation results for electronic documents, documents and documents, and can also effectively satisfy People's work and life needs; but because of the long-term existence of paper English documents, documents and files in people's work and life, the mouse word retrieval function in these electronic translation software cannot give full play to its advantages, and it is difficult to quickly obtain translation results. At this time, in order to obtain a good word-taking translation result, it is necessary to manually input the word into the relevant translation software, which not only prolongs the translation time, but also fails to obtain a good coherent translation result; although these translation software are available on the Internet and related networks With support, it is also possible to manually input words for translation through mobile smart terminals, but there are still problems such as troublesome input and inconvenient operation. Can easily realize mutual translation of paper-based English documents

[0003] Some translation devices for paper documents involved in the prior art, such as the utility model patent CN203133843U, relate to a translation scanning pen, which uses a camera at the end of the scanning pen to collect character images, and then calls the recognition library to recognize the images as characters. Character recognition and translation of paper documents, but can not solve the problem of high misrecognition rate of text recognition; In addition, the traditional OCR scanning paper documents into text, in the implementation of feature extraction, recognition, conversion to text, comparison and other operations , there is still a considerable misrecognition rate, and the discrimination between words is not accurate enough

Images