Text recognition method and equipment for mobile terminal

Abstract

The invention aims to provide a text recognition method and equipment for a mobile terminal. The text recognition method comprises the following steps: acquiring a text picture of at least two text images corresponding to a to-be-recognized target area through a rear camera; performing puzzle operation on the at least two text images to obtain an overall text image corresponding to the target area; carrying out text content recognition on the overall text image corresponding to the target area, and obtaining target text content corresponding to the target area, wherein the target text content comprises one or more characters; and displaying the target text content corresponding to the target area is displayed in the front display screen. Thus, the problem of low efficiency caused by word-by-word scanning is solved, scanning result errors caused by uplink and downlink mobile scanning are improved, the scanning result is more accurate while the scanning efficiency is improved, meanwhile, the font size in a book is not limited, and the application range of equipment is expanded.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a text recognition method and device for a mobile terminal. Background technique [0002] As intelligent technology is getting closer to people's lives, and continuous learning has become the current mainstream, in order to make people more convenient to study and work, obtaining text content in books has become an indispensable part of the process, but in obtaining text However, people still cannot efficiently extract the text in books through original methods such as copying and printing, which brings inconvenience and obstacles to our learning. In the prior art, people use the camera of the scanning device to scan word by word, and during the scanning process, it is easy to move up and down, resulting in wrong line scanning, and the speed of obtaining text content is slow, and scanning errors are prone to occur, resulting in the extraction of text The efficiency i...

AI Technical Summary

Problems solved by technology

[0002] As intelligent technology is getting closer to people's lives, and continuous learning has become the current mainstream, in order to make people more convenient to study and work, obtaining text content in books has become an indispensable part of the process, but in obtaining text When it comes to content, people still cannot efficiently extract the text in books through original methods such as copying and printing, which brings inconvenience and obstacles to our learning

In the prior art, people use the camera of the scanning device to scan word by word, and during the scanning process, it is easy to move up and down, resulting in wrong line scanning, and the speed of obtaining text content is slow, and scanning errors are prone to occur, resulting in the extraction of text The efficiency is low and the expected effect cannot be achieved; for example, when a character error occurs in the scanned content, the overall recognition will fail, which brings great inconvenience to the extraction of text; There are clear requirements for the font size in the middle, if the font size exceeds the requirement, it will not be able to scan and recognize

It can be seen that the existing scanning equipment is inefficient in extracting text, and the process of obtaining content is unstable. If you do not pay attention, the result will be wrong. Therefore, when obtaining text content, we urgently need a text scanning device that can scan efficiently and output accurate text.

Images