A method for detecting and recognizing sensitive characters in natural scene images

Abstract

The invention discloses a method for detecting and recognizing sensitive characters in natural scene images, which comprises the following steps of obtaining a training sample, wherein the training sample data comprises a self-built natural scene sensitive text data set and a public text data set; the training sample data comprises a self-built natural scene sensitive text data set and a public text data set; establishing and training the model of direct recognition of sensitive characters based on improved DSSD network; obtaining a test sample image in a natural scene, inputting that test sample image into the sensitive character direct recognition model, detecting and recognizing the sensitive character in the test image, and realizing the sensitive word recognition of a multi-directional and complex changing text region under the natural scene. The method of the invention solves the problem of the stability of the character recognition based on the single character, solves the character sample problem, simplifies the recognition process, and greatly improves the detection and recognition speed and the precision of the sensitive character in the natural scene, and can recognize the sensitive words in multi-directional and complex text regions in natural scenes.

Description

technical field [0001] The invention belongs to the technical field of image detection and recognition, in particular to a detection and recognition method for sensitive characters in natural scene images. Background technique [0002] In natural scenes, scene text, as a common visual object, widely exists in various occasions, such as on the street, on the wall, etc. Due to the complex background of text in natural scenes, the changeable direction, size and scale, and often affected by uncontrollable factors such as materials and lights, it has great diversity and obvious uncertainty. For example, the text contains multiple languages, and each language contains multiple characters, and each character can have different sizes, fonts, colors, brightness, contrast, etc.; the text usually exists in the form of text lines, but the text lines may have different Arrangement and alignment, such as: multiple lines, horizontal, vertical, curved, etc.; moreover, due to the randomness...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above problems, the present invention proposes a detection and recognition method for sensitive characters in natural scene images, which solves the stability of recognition based on single characters, solves the problem of character samples, simplifies the recognition process, and greatly improves the sensitivity of natural scenes. Text detection and recognition speed and accuracy; able to identify sensitive words in multi-directional, complex-changing text areas in natural scenes

Images