Scholarlink

<p>In recent years, image contrast enhancement has become a critical area of research. It is driven by the need to improve visual quality in various applications, which include medical imaging, remote sensing, and video surveillance. However, contrast enhancement is one of the fields where there is a need for constant solutions since many present technologies provide suboptimal results. This research introduces a novel approach, the Snow Geese Knowledge-Based Differential Evolution algorithm, designed to enhance image contrast while mitigating common challenges such as noise amplification and over-enhancement. The proposed algorithm is evaluated using several publicly available datasets, like CIFAR-10, CIFAR-100, Caltech101, Caltech256, and segmenting buildings in satellite images, with performance metrics such as edge preservation, entropy, and gray-level distribution being analyzed. The results (average peak-to-signal–noise-ratio is 83.85&#xa0;dB, average entropy is 7.17 bits, and average mean square error rate is 0.0025&#xa0;dB) demonstrate significant improvements over existing methods, particularly in terms of maintaining image details while enhancing contrast. This research contributes to the field of image processing by providing a robust and efficient algorithm for contrast enhancement, with potential applications in various domains requiring high-quality image analysis.</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

An Effective Image Contrast Stretching Enhancement Using Novel Snow Geese Knowledge-Based Differential Evolution Algorithm

  • 期刊论文

  • 发表日期：

    2026年1月19日

查看全文
  • B. Vishnupriya,
  • B. Vinoth Kumar

摘要

In recent years, image contrast enhancement has become a critical area of research. It is driven by the need to improve visual quality in various applications, which include medical imaging, remote sensing, and video surveillance. However, contrast enhancement is one of the fields where there is a need for constant solutions since many present technologies provide suboptimal results. This research introduces a novel approach, the Snow Geese Knowledge-Based Differential Evolution algorithm, designed to enhance image contrast while mitigating common challenges such as noise amplification and over-enhancement. The proposed algorithm is evaluated using several publicly available datasets, like CIFAR-10, CIFAR-100, Caltech101, Caltech256, and segmenting buildings in satellite images, with performance metrics such as edge preservation, entropy, and gray-level distribution being analyzed. The results (average peak-to-signal–noise-ratio is 83.85 dB, average entropy is 7.17 bits, and average mean square error rate is 0.0025 dB) demonstrate significant improvements over existing methods, particularly in terms of maintaining image details while enhancing contrast. This research contributes to the field of image processing by providing a robust and efficient algorithm for contrast enhancement, with potential applications in various domains requiring high-quality image analysis.