Image processing method and device, computer-readable storage medium, and electronic equipment

Abstract

The embodiment of the invention provides an image processing method and device, a computer-readable storage medium, and electronic equipment. The method comprises the following steps: acquiring a to-be-detected original image; encoding the to-be-detected original image, and generating a target feature map of the to-be-detected original image; obtaining a first target decoding vector matched with the target feature map according to a positive sample original image, wherein the positive sample original image is an image without abnormal regions; decoding the first target decoding vector to obtain a to-be-detected generated image of the to-be-detected original image. According to the technical scheme provided by the embodiment of the invention, a to-be-decoded decoding vector of a to-be-detected original image is obtained through a positive sample original image without abnormal regions, so that the to-be-detected original image can be reconstructed more accurately, and the abnormal regions of the to-be-detected original image can be prevented from being reconstructed.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular, to an image processing method, an image processing device, a computer-readable storage medium, and electronic equipment. Background technique [0002] In fields such as medical treatment and security inspection, digital X-ray imaging technology (abbreviated as DR (digital radiography, digital X-ray photography) imaging) has a very wide range of applications. In the customs clearance inspection of vehicles at land and sea ports, DR imaging can clearly present the internal structure of the vehicle, thus becoming one of the main auxiliary inspection technologies. Inspection personnel can identify abnormal entrainment in vehicles by observing DR images, but this manual inspection method will cause problems such as inefficiency and waste of resources. [0003] Detecting abnormal entrainment in vehicles can be achieved by traditional subtraction techniques, which use the ...

AI Technical Summary

Problems solved by technology

However, the trained neural network model in the related art can sometimes better reconstruct the abnormal area of ​​the original input image, so that when the trained neural network model is applied to the application scenario of abnormal area detection (such as the above-mentioned identification of vehicles When the abnormal entrainment in the DR image), it may cause the problem that the abnormal area in the original input image is missed.

Images