Text image super-resolution reconstruction method and related equipment thereof

Abstract

The embodiment of the invention belongs to the technical field of artificial intelligence, is applied to the field of intelligent medical treatment, and relates to a text image super-resolution reconstruction method and related equipment thereof. The method comprises the steps of inputting a low-resolution picture into a scene text recognition model to acquire text position and text content information; generating a text mask based on the text position information and the text content information, and upsampling the text mask to obtain a target mask; inputting the low-resolution picture and the target mask into the adversarial network to obtain a discrimination result, and calculating discrimination accuracy based on the discrimination result; calculating a loss function based on the low-resolution picture and the target mask until the loss function converges and the judgment accuracy is lower than an accuracy threshold, and obtaining a trained adversarial network; and inputting a received low-resolution picture to be converted into the trained adversarial network to obtain a target super-resolution picture. The trained adversarial network can be stored in the block chain. Quality of super-resolution reconstruction of the text image is ensured.

Description

technical field [0001] The present application relates to the field of artificial intelligence technology, and in particular, to a text image super-resolution reconstruction method and related equipment. Background technique [0002] Super-resolution reconstruction refers to generating a corresponding high-resolution image through a convolutional neural network for a given low-resolution image, and preserving and restoring the details and textures in the image as much as possible. Super-resolution reconstruction technology plays a good role in promoting the development of image classification, segmentation, tracking and dehazing and other related fields, and plays an important role in the development of neural networks. [0003] However, text pictures are different from natural scenes, and the text content has a fixed shape and sharp edges, which requires higher reconstruction. For ordinary pictures, most of the scenes in the picture are natural and random, and it is easier...

AI Technical Summary

Problems solved by technology

For the text in the scene, if there are distortions, sudden changes in color, or fusion of text edges with other scenes in the reconstructed image, the quality of the reconstructed image will be significantly reduced

Images