Scholarlink

<p>Color balance and contrast are improved over a range of detail levels in an image by employing multi-scale color correction and contrast stretching, which maximizes visual quality. Images are made more visually appealing by this approach, which improves clarity and detail. In this manuscript, Advanced Image Enhancement through Multi-scale Color correction and Contrast Stretching (IEMCCS) using Leaf in Wind Optimization (LiWO) are discussed. The Low-Light (LOL) dataset and the MIT-Adobe 5K dataset are the source of the input image. The Tyrannosaurus (T-Rex) Optimization Algorithm (TROA) is used to optimize the loss function parameters. Meanwhile, the LiWO method aims to maximize image detail and clarity by focusing on various techniques to improve contrast and overall visual quality. The Image Decomposition with Illumination Correction Noise Removal (IDICNR) network is designed to separate reflectance and illumination components. It is optimized to minimize artifacts through inter-consistency, smoothness, and reconstruction losses, while also adjusting illumination for uniformity using histogram-equalized images. TROA is used for training, while contrast-limited Adaptive Histogram Equalization (AHE) is used to enhance local contrast. For better image quality, Leaf further optimizes contrast. The suggested model has a PSNR value of 29.9, an SSIM of 1.00, a DE of 5.86, and a PCQI of 2.09, which outperforms the existing models' performance. These improvements demonstrate the effectiveness of integrating multiple techniques for enhanced image quality. This outcome confirms that the approach achieves superior metrics compared with other methods.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Advanced Image Enhancement Through Multi-scale Color Correction and Contrast Stretching Using Leaf in Wind Optimization

  • 期刊论文

  • 发表日期：

    2025年12月29日

查看全文
  • Senthil Anand Narayanasamy,
  • Rajkumar Kulandaivel

摘要

Color balance and contrast are improved over a range of detail levels in an image by employing multi-scale color correction and contrast stretching, which maximizes visual quality. Images are made more visually appealing by this approach, which improves clarity and detail. In this manuscript, Advanced Image Enhancement through Multi-scale Color correction and Contrast Stretching (IEMCCS) using Leaf in Wind Optimization (LiWO) are discussed. The Low-Light (LOL) dataset and the MIT-Adobe 5K dataset are the source of the input image. The Tyrannosaurus (T-Rex) Optimization Algorithm (TROA) is used to optimize the loss function parameters. Meanwhile, the LiWO method aims to maximize image detail and clarity by focusing on various techniques to improve contrast and overall visual quality. The Image Decomposition with Illumination Correction Noise Removal (IDICNR) network is designed to separate reflectance and illumination components. It is optimized to minimize artifacts through inter-consistency, smoothness, and reconstruction losses, while also adjusting illumination for uniformity using histogram-equalized images. TROA is used for training, while contrast-limited Adaptive Histogram Equalization (AHE) is used to enhance local contrast. For better image quality, Leaf further optimizes contrast. The suggested model has a PSNR value of 29.9, an SSIM of 1.00, a DE of 5.86, and a PCQI of 2.09, which outperforms the existing models' performance. These improvements demonstrate the effectiveness of integrating multiple techniques for enhanced image quality. This outcome confirms that the approach achieves superior metrics compared with other methods.