CN-122023218-A - Texture feature-oriented self-adaptive image enhancement method and system

Abstract

The invention discloses an image self-adaptive enhancement method and system based on texture feature analysis. The method comprises the steps of S1, obtaining an image to be processed, extracting a texture feature area in the image, S2, analyzing the grain fineness of the image based on the texture feature area, S3, constructing an adaptive enhancement function according to the grain fineness, S4, carrying out feature enhancement on the image by utilizing the adaptive enhancement function, and outputting the enhanced image. According to the method, the problems of poor image enhancement adaptability and detail loss in the prior art are solved through texture fine granularity analysis and contrast difference calculation, and the definition and contrast of the image are improved.

Inventors

• CHEN NANQING

Assignees

• 陈楠清

Dates

Publication Date

20260512

Application Date

20260131

Claims (6)

1. 1. An image self-adaptive enhancement method based on texture feature analysis is characterized by comprising the following steps: acquiring an image to be processed, and extracting texture features of a key interest area in the image to be processed; Performing frequency domain conversion on the texture features, and analyzing to obtain high-frequency texture fine granularity and low-frequency texture fine granularity; Calculating local contrast difference data and global contrast difference data based on the high-frequency texture fine granularity and the low-frequency texture fine granularity; Constructing a self-adaptive image enhancement function according to the local contrast difference data and the global contrast difference data; And carrying out image characteristic enhancement on the key interest area by utilizing the self-adaptive image enhancement function to generate an enhanced image.
2. 2. The method of claim 1, wherein the high frequency grain size is calculated by a gradient operator and the low frequency grain size is calculated by an image mean.
3. 3. The method of claim 1, wherein the local contrast difference data is obtained by calculating pixel range in a local region and the global contrast difference data is obtained by calculating pixel distribution difference in a global region.
4. 4. The method of claim 1, wherein the adaptive image enhancement function is a nonlinear transformation function whose parameters are dynamically adjusted based on texture fine granularity and contrast difference data.
5. 5. An image adaptive enhancement system based on texture feature analysis, comprising: The image acquisition module is used for acquiring an image to be processed; the feature extraction module is used for extracting texture features in the image; the analysis module is used for analyzing the grain fineness and contrast difference; and the enhancement module is used for enhancing the image according to the analysis result.
6. 6. The system according to claim 5, wherein the system is implemented in the form of an electronic device comprising a memory and a processor, the processor implementing the method according to any of claims 1-4 when executing a program in the memory.

Description

Texture feature-oriented self-adaptive image enhancement method and system Technical Field The present invention relates to the field of image processing technologies, and in particular, to an image enhancement method and system. Background In the prior art, the image enhancement method often adopts unified enhancement parameters, so that the region with rich textures is over-enhanced, and the region with simple textures is not enhanced enough. The traditional image enhancement algorithm such as histogram equalization and Retinex algorithm can not adaptively adjust the enhancement parameters according to different texture characteristics, and is easy to cause image detail loss or noise amplification. Disclosure of Invention The invention aims to provide an image enhancement method and an image enhancement system capable of adaptively adjusting enhancement parameters according to different texture characteristics, so as to solve the problems of poor image enhancement adaptability and detail loss in the prior art. Technical proposal The invention provides an image self-adaptive enhancement method based on texture feature analysis, which is characterized by comprising the following steps of: acquiring an image to be processed, and extracting texture features of a key interest area in the image to be processed; Performing frequency domain conversion on the texture features, and analyzing to obtain high-frequency texture fine granularity and low-frequency texture fine granularity; Calculating local contrast difference data and global contrast difference data based on the high-frequency texture fine granularity and the low-frequency texture fine granularity; Constructing a self-adaptive image enhancement function according to the local contrast difference data and the global contrast difference data; And carrying out image characteristic enhancement on the key interest area by utilizing the self-adaptive image enhancement function to generate an enhanced image. Advantageous effects The invention realizes the self-adaptive adjustment of image enhancement through grain fine grain analysis and contrast difference calculation, and has the following beneficial effects: the enhancement parameters can be automatically adjusted according to different texture characteristics, and the adaptability of the enhancement effect is improved Effectively preserve image details and avoid over-enhancement or under-enhancement problems Improving definition and contrast of image and improving visual effect Drawings FIG. 1 is a system architecture diagram of an embodiment of the present invention; FIG. 2 is a network architecture diagram of an embodiment of the present invention; FIG. 3 is a flow chart of a method according to an embodiment of the present invention; FIG. 4 is a graph showing the comparison of effects of the embodiment of the present invention. Detailed Description Examples As shown in fig. 1, the image adaptive enhancement system of the present invention includes: An image acquisition module for acquiring an image to be processed The feature extraction module is used for extracting texture features in the image An analysis module for analyzing the grain fineness and contrast difference The enhancement module is used for enhancing the image according to the analysis result As shown in fig. 2, the network structure includes a convolution layer, a pooling layer, a feature analysis layer, and an enhancement layer. As shown in fig. 3, the method flow includes: image preprocessing and feature extraction Texture fine grain analysis Contrast difference calculation Adaptive function construction Image feature enhancement As shown in FIG. 4, compared with the traditional method, the method can better reserve details in the area with rich textures, and can properly enhance the contrast in the area with simple textures. Examples In specific implementation, the following technical parameters may be adopted: High-frequency texture fine granularity calculation formula: hf=Σgx |+|Gy| Low frequency texture fine granularity calculation formula lf=Σi (x, y) Local contrast difference lcd=max (I) -min (I) Global contrast difference gcd=mean (I) -mean (I) Wherein Gx and Gy are gradients of the image in x and y directions, respectively, and I (x, y) is an image pixel value.