Image Contrast Enhancement via Gray Value Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional image enhancement methods, such as histogram equalization, often result in overly bright images and fail to accurately maintain brightness, especially when dealing with external light interference, which affects the processing of specific image regions.
Innovation Solution
The method involves dividing an input image into sub-images based on gray value distribution ranges, performing histogram equalization and singular value decomposition on each sub-image, and merging the results to produce an output image with enhanced contrast and maintained brightness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional histogram equalization algorithm is used to enhance image contrast, then contrast of the image is improved, but the overall brightness of the image becomes too bright and cannot be accurately maintained
Solution Approach 1:
The patent divides the input image into multiple sub-images based on different gray value distribution ranges. Each sub-image is processed independently through histogram equalization, allowing contrast enhancement in specific gray value regions without affecting the overall image brightness. This segmentation approach resolves the contradiction by applying contrast enhancement locally rather than globally.
Solution Approach 2:
The patent applies different processing strategies to different regions of the image based on their gray value characteristics. By performing histogram equalization on sub-images with different gray value distributions and then merging them with appropriate weighting, the method achieves local contrast enhancement while maintaining global brightness balance, thus resolving the brightness overshoot problem of traditional global histogram equalization.
2Manufacturing precision
If traditional histogram equalization is applied to the entire image, then contrast enhancement is achieved, but processing of specific regions with different gray value distributions is not accurate
Solution Approach 1:
The patent segments the image into multiple sub-images according to different gray value distribution ranges. Each sub-image represents a specific region in the gray value space and can be processed independently. This segmentation enables accurate contrast enhancement for each region while maintaining adaptability to different gray value distributions throughout the image.
Solution Approach 2:
The patent changes the processing parameters (gray value distribution ranges) to adapt to different regions of the image. By defining multiple sub-images with different gray value ranges and applying histogram equalization separately to each, the method achieves both accurate contrast enhancement and adaptability to various regional characteristics.
Data Source
AI summary
The present disclosure provides a method for enhancing image contrast, including: dividing an input image into a plurality of input sub-images, each of the plurality of input sub-images corresponding to a gray value distribution range, the gray value distribution ranges of the respective input sub-images being different from each other, and each input sub-image comprising all pixels, among pixels of the input image, whose gray values are within the gray value distribution range of the input sub-image; performing an equalization processing on each of the plurality of input sub-images, and obtaining a plurality of output sub-images corresponding to the plurality of input sub-images, respectively, based on a result of the equalization processing; and merging the plurality of output sub-images to obtain an output image corresponding to the input image. The present disclosure further provides a device for enhancing image contrast, a display apparatus, and a computer-readable storage medium.