Image processing method

Abstract

The embodiment of the invention discloses an image processing method. The image processing method comprises the steps that a grey level histogram of non-sky-area pixels in a dark channel image of an initial image is determined; whether the initial image needs to be defogged or not is judged according to the grey level histogram; when the initial image needs to be defogged, the initial image is defogged; or, when the initial image does not need to be defogged, the initial image is not defogged. By means of the image processing method, whether the image needs to be defogged or not can be accurately judged, the number of occupied resources of a processor is small, the image processing time can be shortened, and the electricity quantity of an electronic device is saved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image processing method. Background technique [0002] When the captured image is foggy, the features such as the contrast and color of the object in the image will be unclear, which will interfere with the information to be expressed in the image. The existing technology proposes a method for image defogging, which selects a pixel point corresponding to each pixel value in the scale neighborhood Ω(x) to analyze the dark channel prior information, and then estimates the fog concentration and transmittance through the dark channel prior information , and finally dehaze the image according to the fog concentration and transmittance. [0003] When analyzing the dark channel information in the prior art, it is required that the corresponding scale neighborhood Ω(x) randomly selected contains dark pixels. When the image contains bright pixel areas exceeding the ar...

AI Technical Summary

Problems solved by technology

[0003] When analyzing the dark channel information in the prior art, it is required that the corresponding scale neighborhood Ω(x) randomly selected contains dark pixels. When the image contains bright pixel areas exceeding the area of ​​the corresponding scale neighborhood Ω(x), the image will be judged as It is a foggy image, and in practical applications, the bright pixel area exceeding the area of ​​the corresponding scale neighborhood Ω(x) can often be a scene such as the sky. When the image contains a large area of ​​the sky, the existing technology Not only can it not be recognized that the image is a haze-free image, but also dehazing the image based on wrong parameters will reduce the image effect, and even damage the image due to excessive defogging of the haze-free area in the image; in addition, the existing technology based on dark Estimating the concentration and transmittance of fog with channel prior information requires a huge amount of calculation, which takes up a lot of CPU, memory, bus and other processor resources. When processing a large amount of image data such as video data, there will be a freeze phenomenon, and it will seriously consume terminal power.

Images