Text detection and recognition method combining character level classification and character string level classification

Abstract

The invention discloses a text detection and recognition method combining character level and character string level classification. According to the method, pixel sets possibly belonging to the same character are extracted from images to form alternate characters; alternate characters which do not meet the geometric feature statistic rule are filtered out; a character level classifier based on the character rotation and dimension invariance features is adopted for classifying the alternate characters, and the probability that the alternate characters are certain characters is determined; the characters are combined two by two, and initial character strings are formed; the similarity between every two character strings is calculated, two character strings with the highest similarity are combined into new character strings until no character strings capable of being combined exist; a character level classifier based on the character string structure feathers is adopted for classifying the character strings to determine the character strings with semanteme; and the probability that character strings to be recognized are certain characters is utilized for recognizing the character strings, and the semantic text is obtained. The text detection and recognition method has the advantages that the text detection and recognition process is used as a whole, the interaction of the text detection and the recognition is utilized for improving the result precision, and simplicity and high efficiency are realized.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and more specifically relates to a text detection and recognition method combining character-level classification and string-level classification. Background technique [0002] In today's era of information explosion, it is becoming more and more important to use computer vision technology to quickly and effectively analyze and extract useful information from visual information (pictures, videos, etc.). Text detection and recognition is to judge whether there is text in the input natural scene image, if it exists, mark its position, and then perform semantic recognition on these texts. Text detection and recognition in natural images is one of the important research topics in the field of computer vision technology, and has a wide range of applications, such as robot navigation, image retrieval, human-computer interaction, etc. In the past few decades, the research on text detection and ...

AI Technical Summary

Problems solved by technology

However, the above two types of methods basically focus on the detection and recognition of horizontal text, which cannot solve the problem of text diversity and complex background.

Images