Scene text recognition method based on sparse coding characteristics

Abstract

The invention discloses a scene text recognition method based on sparse coding characteristics, and relates to computer vision and pattern recognition. The method includes the steps: inputting a natural scene text image to be recognized; by the aid of a multi-scale sliding window method, detecting and recognizing a window area in the image by a character classifier, for each character class, determining a large output area of the classifier as a candidate character area, determining a small output area as a background area, finding the candidate character area in the image, retaining the area with the largest output value of the classifier and the corresponding character class for the area with a large overlapping ratio by the aid of a non-maximum suppression method, and removing the repetitive and redundant candidate character area to obtain a character detection result; combining detected characters into a word or text line; outputting a scene text recognition result. Structural characteristics of the characters can be more effectively expressed and extracted, so that the recognition rate of a scene text is increased.

Description

technical field [0001] The invention relates to computer vision and pattern recognition, in particular to a scene text recognition method based on sparse coding features. Background technique [0002] As products such as smart phones and digital cameras become more and more popular, obtaining pictures and videos has become a breeze, and the analysis and understanding of images and videos has become one of the research directions with broad application prospects. In images and videos, text information contains important semantic information, which is of great value to the understanding of images and videos, such as book covers, billboards next to roads, road sign information, subtitles in videos, etc. contain a lot of information , this information is easier for humans and computers to understand and store. Therefore, in the field of computer vision, scene image text recognition has attracted more and more attention. Due to the complex background of the scene image, the siz...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a scene text recognition method based on sparse coding features to solve the problem that the feature extraction of the character classifier in the current scene text recognition cannot effectively express the character structure information.

Images