Scholarlink

<p>In the field of image processing, haze is a type of atmospheric scattering that reduces contrast and clarity&#xa0;of images, frequently masking small details and far-off objects. It is mostly caused by microscopic airborne particles like smoke, dust, and water droplets that scatter incoming light. The scattered light, producing a hazy image, diminishes the direct light that reaches the camera sensor. Many image processing methods have been presened to solve this problem and lessen the impacts of haze. Usually, these methods work by determining how much haze is there in an image, and then using this information to get the image back to its assumed previous quality. In this work, we present the proposed Modified Contrast Enhancement and Exposure Fusion (MCEEF) technique. The MCEEF dehazing technique falls under the umbrella of enhancement-based dehazing techniques. In this technique, hazy frames or images undergo sharpening through a Smoothing-Sharpening Image Filter (SSIF) designed to accentuate the disparity between the haze and objects in images. Subsequently, Gamma Correction (GC)&#xa0;and Color Preserving Adaptive Histogram Equalization (CP-AHE) enhance the sharpened hazy images by augmenting their contrast. Dehazed images are then obtained by fusing the results of the CP-AHE- and GC-enhanced images. The MCEEF dehazing technique is aided with enhanced hazy images or frames as input for the dehazing process. Moreover, essential enhancement tools precede the MCEEF dehazing technique. These tools include homomorphic processing and Contrast Limited Adaptive Histogram Equalization (CLAHE), which are instrumental in controlling the dynamic range before the dehazing phase. In the proposed approach, a hazy image or frame is initially subjected to homomorphic processing, followed by the application of CLAHE, and finally, the MCEEF dehazing technique is employed. To demonstrate the effectiveness of the proposed approach, we apply it on both visible and Near Infrared (NIR) frames. We compare the results&#xa0;of&#xa0;the MCEEF dehazing with and without enhancement. Real hazy images from different datasets serve as additional benchmarks for evaluating the performance of the proposed approach alongside other different dehazing techniques. The results affirm the superiority of the proposed approach, particularly in the context of visible videos, with various evaluation metrics, including Peak Signal-to-Noise Ratios (PSNRs), correlation&#xa0;values, entropies, histograms, and spectral entropies of dehazed frames.</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

Enhanced Modified Contrast Enhancement and Exposure Fusion: a visionary dehazing approach for clarity in hazy imagery

  • 期刊论文

  • 发表日期：

    2025年3月11日

查看全文
  • Abeer Ayoub,
  • Walid El-Shafai,
  • Fathi E. Abd El-Samie,
  • Ehab K. I. Hamad,
  • El-Sayed M. EL-Rabaie

摘要

In the field of image processing, haze is a type of atmospheric scattering that reduces contrast and clarity of images, frequently masking small details and far-off objects. It is mostly caused by microscopic airborne particles like smoke, dust, and water droplets that scatter incoming light. The scattered light, producing a hazy image, diminishes the direct light that reaches the camera sensor. Many image processing methods have been presened to solve this problem and lessen the impacts of haze. Usually, these methods work by determining how much haze is there in an image, and then using this information to get the image back to its assumed previous quality. In this work, we present the proposed Modified Contrast Enhancement and Exposure Fusion (MCEEF) technique. The MCEEF dehazing technique falls under the umbrella of enhancement-based dehazing techniques. In this technique, hazy frames or images undergo sharpening through a Smoothing-Sharpening Image Filter (SSIF) designed to accentuate the disparity between the haze and objects in images. Subsequently, Gamma Correction (GC) and Color Preserving Adaptive Histogram Equalization (CP-AHE) enhance the sharpened hazy images by augmenting their contrast. Dehazed images are then obtained by fusing the results of the CP-AHE- and GC-enhanced images. The MCEEF dehazing technique is aided with enhanced hazy images or frames as input for the dehazing process. Moreover, essential enhancement tools precede the MCEEF dehazing technique. These tools include homomorphic processing and Contrast Limited Adaptive Histogram Equalization (CLAHE), which are instrumental in controlling the dynamic range before the dehazing phase. In the proposed approach, a hazy image or frame is initially subjected to homomorphic processing, followed by the application of CLAHE, and finally, the MCEEF dehazing technique is employed. To demonstrate the effectiveness of the proposed approach, we apply it on both visible and Near Infrared (NIR) frames. We compare the results of the MCEEF dehazing with and without enhancement. Real hazy images from different datasets serve as additional benchmarks for evaluating the performance of the proposed approach alongside other different dehazing techniques. The results affirm the superiority of the proposed approach, particularly in the context of visible videos, with various evaluation metrics, including Peak Signal-to-Noise Ratios (PSNRs), correlation values, entropies, histograms, and spectral entropies of dehazed frames.