Grayscale image enhancement method based on retina mechanism

Abstract

The invention belongs to the technical filed of computer vision and especially relates to brightness enhancement and edge enhancement of a grayscale image. The method specifically comprises the following steps: estimating global brightness and determining algorithm self-adaption parameters, generating a brightness mapping graph of the images and carrying out calculation to obtain a brightness enhancement image and carrying out edge enhancement processing. The method is characterized by, to begin with, estimating the self-adaption parameters according to the brightness distribution conditions of global dark areas; then, carrying out global brightness enhancement processing on the images and obtaining the modulation mapping graph of the whole picture through a modulation function, and carrying out calculation to obtain brightness enhancement result; and finally, realizing edge enhancement based on a dimension-self-adaptive Gaussian difference model, the model dimension being influenced by contrast ratio, and therefore, bright areas can be enhanced with finer texture information, and the dark areas can be enhanced with larger contour information. The method can enhance overall brightness and contrast of the grayscale images effectively, and the self-adaption characteristic can play a very good effect on edge enhancement of the bright and dark areas.

Description

technical field [0001] The invention belongs to the technical field of computer vision, in particular to brightness enhancement and edge enhancement of grayscale images. Background technique [0002] The information in grayscale images is mainly in terms of brightness. The large-scale brightness areas in these images determine the content information of objects, while the information of lines and points is an important boundary to distinguish between different objects. Therefore, effectively enhancing the brightness of images with low overall brightness plays an important role in target recognition and so on. [0003] At present, the more classic brightness enhancement methods include traditional global processing operators such as gamma transformation, local operators based on local templates, and the improvement of the prototype of the Retinex method based on the human retina mechanism proposed by Edwin.H.Land in 1963. Among the above methods: the global processing operat...

AI Technical Summary

Problems solved by technology

Among the above methods: the global processing operator has the same mapping function for the entire image, but the enhancement effect on the dark area is not good; the local processing operator is easy to cause the reversal of the light and dark boundary; the Retinex method needs to perform large-scale filtering on the target image, It is easy to cause image blurring, and excessive bleaching of bright areas causes loss of image information

[0004] In the traditional edge extraction method, the fixed-size Gaussian difference model is used to extract the edge information in the image, but the size applicable to different brightness areas in the image is different, and the fixed-size Gaussian difference model cannot achieve the optimal effect. Detail textures do not respond strongly enough, and larger outlines in dark areas are not recognized effectively

Images