A text image super-resolution reconstruction method based on a conditional generative adversarial network

Abstract

The invention discloses a text image super-resolution reconstruction method based on a conditional generative adversarial network. According to the method, the structure of a common conditional generative adversarial network is modified, so that the method is more suitable for a super-resolution reconstruction task of a text image; Non-text binary segmentation image is used as extra training supervision information of a super-resolution reconstruction model, and text-text binary segmentation image is combined with extra training supervision information of a super-resolution reconstruction model; the non-text binary segmentation information constructs a loss function of the model to constrain the training of the model, so that the super-resolution reconstruction model is more concentrated in the text part in the image. Compared with a common image super-resolution method, the text image super-resolution reconstruction method disclosed by the invention fully and specifically utilizes theinformation of the text, and the quality of text image super-resolution reconstruction is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a text image super-resolution reconstruction method. Background technique [0002] With the increasingly widespread use of various smart devices with camera / camera functions such as mobile phones, digital cameras / video cameras, and monitoring equipment, as well as the rapid development of the Internet as a carrier of information sharing and dissemination, people can come into contact with a large number of How to efficiently extract useful semantic information from these image data is of great significance to the effective use of image data resources. Among them, text objects in images carry rich semantic content about images and scenes, and their effective extraction can play an important role in image analysis, understanding, classification, retrieval, recommendation and other applications. On the other hand, due to the influence of many factors such as th...

AI Technical Summary

Problems solved by technology

On the other hand, due to the influence of many factors such as the resolution of the image acquisition equipment in the natural scene, the intensity of the scene illumination, and the distance of the text, the resolution of the actually obtained text image is relatively low in many cases. processing such as identification poses considerable difficulties

Images