Scholarlink

<p>The destruction of seas and oceans due to human activities is one of the biggest problems facing the world’s oceans. Solving this problem requires a better understanding of the dangers to marine life. Photographing the underwater environment can be challenging due to the absorption and scattering of light, but it is crucial to the success of the work. In this work, a combination of fruit fly optimization and bee colony optimization (ABC + FOA) is used to improve ocean photography. To achieve this, we use convolution technology to reduce noise and increase the clarity of the image. The proposed method improves the peak-to-noise ratio (PSNR) and reduces the mean square error (MSE). This approach helps scientists and conservationists better understand the state of seas and oceans and develop strategies to protect them. Additionally, the improved images can aid underwater exploration, mapping, and resource management. The results show that the proposed approach attains the highest average PSNR (63.14) and the lowest MSE (7.91) thus surpassing existing studies in terms of ocean photography.</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

Enhancing underwater image quality with artificial bee colony and fruit fly optimization

  • 期刊论文

  • 发表日期：

    2025年10月4日

查看全文
  • Varun Malik,
  • Ruchi Mittal,
  • Vikram Singh,
  • Komal Parashar,
  • Praney Madan,
  • Aryan Jandwani,
  • Rehmat Jandwani

摘要

The destruction of seas and oceans due to human activities is one of the biggest problems facing the world’s oceans. Solving this problem requires a better understanding of the dangers to marine life. Photographing the underwater environment can be challenging due to the absorption and scattering of light, but it is crucial to the success of the work. In this work, a combination of fruit fly optimization and bee colony optimization (ABC + FOA) is used to improve ocean photography. To achieve this, we use convolution technology to reduce noise and increase the clarity of the image. The proposed method improves the peak-to-noise ratio (PSNR) and reduces the mean square error (MSE). This approach helps scientists and conservationists better understand the state of seas and oceans and develop strategies to protect them. Additionally, the improved images can aid underwater exploration, mapping, and resource management. The results show that the proposed approach attains the highest average PSNR (63.14) and the lowest MSE (7.91) thus surpassing existing studies in terms of ocean photography.