Image detection, repair method and image detection, repair apparatus

Abstract

The invention provides an image bad point detecting method, comprising: performing the buffer memory on at least three continuous images including an origin image, at least a former image and at least a latter image; determining the pixel point in the origin image respectively relative to the forward motion vector of the former image and the backward motion vector of the latter image; determining the pixel point in the origin image respectively relative to the forward motion compensation point of the former image and relative to the backward motion compensation point of the latter image; performing the bad point detection on the pixel point in the origin image according to the forward motion compensation point and the backward motion compensation point. The method considers the characteristic of the image gray scale and the motion vector on the time and the space, obtains the motion compensation point in the former image and the latter image corresponding to the pixel in the origin image according to the motion vector, thereby increasing the detection precision of the bad point or the bad ring, improving the reparative accuracy of the bad point or the bad ring in the image.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image detection and restoration method and an image detection and restoration device. Background technique [0002] With the continuous development of digital image technology, various digital image processing or camera products have been widely popularized. At the same time, people's requirements for image quality are getting higher and higher, so it is necessary to analyze, process and process images so that they can meet visual, psychological and other requirements, which is called image processing. Image restoration is an important part of image processing. It has a wide range of applications. It can repair damaged paintings, photos, restore details lost in streaming media, such as repairing bad pixels or bad blocks in images, etc. [0003] The following is a brief introduction to the technology of detecting and repairing bad pixels and bad blocks in images in th...

AI Technical Summary

Problems solved by technology

[0008] The disadvantage of the existing technology is: the method of referring to the previous and subsequent frame images in the above-mentioned prior art does not consider the influence of motion on the image, that is to say, the pixel point A in the current frame image 1 (x 1 ,y 1 ), has already moved to pixel point B in the next frame of image 2 (x 2 ,y 2 ), and at this time the existing technology also refers to the pixel point A in the next frame of image 2 (x 1 ,y 1 ) to determine pixel point A 1 (x 1 ,y 1 ) is a bad point, which causes detection errors and affects the accuracy of image repair

Images