Texture feature-oriented adaptive image enhancement method and system

Abstract

The invention discloses an image adaptive enhancement method and system based on texture feature analysis. The method comprises the following steps: S1, acquiring a to-be-processed image, and extracting a texture feature region in the image; s2, based on the texture feature region, analyzing the texture fine granularity of the image; s3, constructing an adaptive enhancement function according to the texture fine granularity; and S4, performing feature enhancement on the image by using the adaptive enhancement function, and outputting the enhanced image. Through texture fine-grained analysis and contrast difference calculation, the problems of poor image enhancement adaptability and detail loss in the prior art are solved, and the definition and the contrast of the image are improved.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to an image enhancement method and system. Background Technology

[0002] In existing technologies, image enhancement methods often use uniform enhancement parameters, resulting in over-enhancement of texture-rich areas and under-enhancement of areas with simple textures. Traditional image enhancement algorithms, such as histogram equalization and Retinex algorithm, cannot adaptively adjust enhancement parameters according to different texture features, which can easily lead to loss of image details or amplification of noise. Summary of the Invention

[0003] The purpose of this invention is to provide an image enhancement method and system that can adaptively adjust enhancement parameters according to different texture features, so as to solve the problems of poor adaptability and loss of detail in the existing image enhancement technology. Technical solution

[0004] This invention provides an image adaptive enhancement method based on texture feature analysis, characterized by the following steps: Acquire the image to be processed and extract the texture features of key regions of interest in the image to be processed; The texture features are subjected to frequency domain transformation, and the high-frequency texture fine-grainedness and low-frequency texture fine-grainedness are obtained through analysis. Based on the high-frequency texture fine-grainedness and low-frequency texture fine-grainedness, local contrast difference data and global contrast difference data are calculated; Based on the local contrast difference data and the global contrast difference data, an adaptive image enhancement function is constructed; The adaptive image enhancement function is used to enhance the image features of the key interest region to generate an enhanced image. Beneficial effects

[0005] This invention achieves adaptive adjustment of image enhancement through fine-grained texture analysis and contrast difference calculation, and has the following beneficial effects: It can automatically adjust enhancement parameters based on different texture features, improving the adaptability of the enhancement effect. Effectively preserves image details and avoids over-enhancement or under-enhancement issues. Improve image clarity and contrast, enhancing visual appeal. Attached Figure Description

[0006] Figure 1 This is a system architecture diagram of an embodiment of the present invention; Figure 2 This is a network structure diagram of an embodiment of the present invention; Figure 3This is a flowchart of a method according to an embodiment of the present invention; Figure 4 These are comparison diagrams showing the effects of embodiments of the present invention. Detailed Implementation Example

[0007] like Figure 1 As shown, the image adaptive enhancement system of the present invention includes: Image acquisition module: used to acquire images to be processed. Feature extraction module: used to extract texture features from images. Analysis module: Used to analyze texture fineness and contrast differences. Enhancement module: Used to enhance images based on analysis results. like Figure 2 As shown, the network structure includes convolutional layers, pooling layers, feature analysis layers, and enhancement layers.

[0008] like Figure 3 As shown, the method flow includes: Image preprocessing and feature extraction Fine-grained texture analysis Contrast difference calculation Adaptive function construction Image feature enhancement like Figure 4 As shown, compared with traditional methods, the method of the present invention can better preserve details in areas with rich textures and appropriately enhance contrast in areas with simple textures. Example

[0009] In practical implementation, the following technical parameters can be adopted: Formula for calculating fine-grained high-frequency texture: HF = Σ|Gx| + |Gy| Formula for calculating fine-grained low-frequency texture: LF = ΣI(x,y) Local contrast difference: LCD = max(I) - min(I) Global contrast difference: GCD = mean(I) - median(I) Where Gx and Gy are the gradients of the image in the x and y directions, respectively, and I(x,y) is the pixel value of the image.

Claims

1. An image adaptive enhancement method based on texture feature analysis, characterized in that, Includes the following steps: Acquire the image to be processed and extract the texture features of key regions of interest in the image to be processed; The texture features are subjected to frequency domain transformation, and the high-frequency texture fine-grainedness and low-frequency texture fine-grainedness are obtained through analysis. Based on the high-frequency texture fine-grainedness and low-frequency texture fine-grainedness, local contrast difference data and global contrast difference data are calculated; Based on the local contrast difference data and the global contrast difference data, an adaptive image enhancement function is constructed; The adaptive image enhancement function is used to enhance the image features of the key interest region to generate an enhanced image.

2. The method according to claim 1, characterized in that, The fine-grained high-frequency texture is calculated using a gradient operator, and the fine-grained low-frequency texture is calculated using the image mean.

3. The method according to claim 1, characterized in that, The local contrast difference data is obtained by calculating the pixel range within a local area, and the global contrast difference data is obtained by calculating the pixel distribution difference within a global area.

4. The method according to claim 1, characterized in that, The adaptive image enhancement function is a non-linear transformation function whose parameters are dynamically adjusted based on texture fineness and contrast difference data.

5. An image adaptive enhancement system based on texture feature analysis, characterized in that, include: The image acquisition module is used to acquire the image to be processed. The feature extraction module is used to extract texture features from images; The analysis module is used to analyze texture fineness and contrast differences; The enhancement module is used to enhance images based on the analysis results.

6. The system according to claim 5, characterized in that, The system is implemented as an electronic device, including a memory and a processor, wherein when the processor executes a program in the memory, it implements the method as described in any one of claims 1-4.

Images