Super-resolution text image recognition method and device, equipment and storage medium

Abstract

The invention relates to the technical field of image recognition, and discloses a super-resolution text image recognition method and device, equipment and a storage medium. The method comprises the following steps: acquiring a to-be-detected image; inputting the to-be-detected image into a convolutional neural network layer of a preset super-resolution reconstruction model for processing to obtain pixel data of the to-be-detected image; inputting the pixel data into a sub-pixel convolutional layer of the super-resolution reconstruction model for pixel extraction to obtain a target high-resolution image; inputting the target high-resolution image into a preset text detection network model for detection to obtain a text region of the target high-resolution image; and inputting the text region of the target high-resolution image into a preset text recognition model for recognition, and determining text content in the text region according to a recognition result. According to the method, the deep learning ability of the model is improved through the gaan network, and the technical problems that the text detection network is low in accuracy and the detection speed cannot be balanced are solved.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to a super-resolution text image recognition method, device, equipment and storage medium. Background technique [0002] The main feature of the existing key information extraction technology of express delivery documents is: the text content on the entire note is obtained through text recognition and detection technology. Extract key information through template matching or regular expressions. [0003] However, due to the influence of environment, equipment and other factors in daily operation, the images obtained by people are often of low quality. With the continuous expansion of the demand for intelligence, the difficulty of low-quality image recognition is still a problem worthy of attention. The difficulty of low-quality image recognition is that the resolution of the image is not enough, and the edges and details of the image are blurred, which makes it d...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to improve the deep learning ability of the model through the gan network, and solve the technical problem that the accuracy of the text detection network is low and the detection speed cannot be balanced

Images