Connected domain-based natural scene text detection method

Abstract

The invention discloses a connected domain-based natural scene text detection method, and mainly solves the problem of low accuracy of an existing text detection method. The method is implemented by the steps of 1) performing grayscale transform on an input original image to obtain a grayscale image IG; 2) extracting character candidate regions from the IG, and obtaining a character candidate region image Im; 3) filtering a few candidate regions containing no characters in the Im to obtain a preliminarily filtered image I1; 4) filtering a few candidate regions containing no characters in the I1 to obtain a final image I2; 5) combining the residual character candidate regions in the I2 into text line regions; and 6) inputting the text line regions to a convolutional neural network text detector in sequence, and filtering the text line regions containing no texts to obtain final text-containing text line regions. According to the method, by filtering the candidate regions containing no texts for multiple times, the text detection accuracy is improved; and the method can be used for automatically extracting the texts in the image.

Description

technical field [0001] The invention belongs to the technical field of computer vision, in particular to a method for detecting characters in natural scene images, which can be used to automatically extract characters in images. Background technique [0002] With the rapid development of the mobile Internet and the popularity of mobile electronic devices such as smartphones, the acquisition and transmission of natural scene images has become more and more convenient. The text in natural scene images contains a wealth of information. People expect that computers can replace humans to automatically detect and extract text information in images, and this technology will be industrialized and used in daily production and life, such as text recognition The technology is applied in areas such as driverless cars, navigation for the blind, industrial automation, Internet information mining, e-commerce anti-counterfeiting, and brand exposure research. [0003] Different from traditi...

AI Technical Summary

Problems solved by technology

At the same time, because there are many scene elements similar to text in natural scenes, such as doors and windows, railings, leaf meshes, lampposts, etc., and these non-text elements are very similar to text in shape and color, so many non-text elements are detected. The MSER connected area of ​​the text leads to a decrease in the accuracy of text detection

This is one of the main challenges of text localization based on the largest extremum stable region

Images