Image processing method, device, medium and computing device

Abstract

Embodiments of the present invention provide an image processing method. The method includes: extracting image features of the image to be processed to obtain a first eigenvalue matrix; using a classification prediction model to process the first eigenvalue matrix, and determining the image to be processed relative to each of a plurality of predetermined angle categories The prediction confidence of the predetermined angle category and generate a prediction confidence set, wherein the predetermined angle category indicates the angle interval where the offset angle is located; according to the prediction confidence set, determine the offset angle of the image to be processed; and according to the set The offset angle is used to rotate the image to be processed. The method of the invention converts the problem of determining the offset angle of an image into an angle classification task, which can effectively reduce the computational complexity and improve the accuracy of the determined offset angle. In addition, the embodiments of the present invention also provide an image processing device, a medium, and a computing device.

Description

technical field [0001] Embodiments of the present invention relate to the field of image processing, and more specifically, embodiments of the present invention relate to an image processing method, device, medium, and computing device. Background technique [0002] This section is intended to provide a background or context for implementations of the invention that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] In work and life, it is often necessary to recognize and extract the text in the image to edit the extracted text; or, when the image is recognized and processed, the recognition of the text in the image is also essential. [0004] Generally, an optical character recognition (optical Character Recognition, OCR) method is often used when recognizing text in an image. However, the angle of the text in the image has a great influence on the accuracy of the OCR method to recognize the text. Us...

AI Technical Summary

Problems solved by technology

In the prior art, steps such as mathematical modeling, correction of distortion function parameters, calculation of reverse projection coordinates, and image restoration are often required when correcting images, each of which requires the use of complex algorithms

Therefore, when there are a large number of images to be corrected, the above method will make the execution efficiency of the image correction task inefficient

Images