• Sanika Patankar
• Vinayak Sawandkar

This paper proposes a model for the enhancement of underwater images and is further the images are classified into 2 classes of fish and trash. It involves improving the quality of images using NUCE (Natural-based underwater image color enhancement). NUCE is a four-step strategy process involving color cast neutralization on underwater images, a fusion of dual-intensity images, and then an unsharp masking algorithm to sharpen the high frequencies. YOLO is used to classify objects into 2 categories: fish and trash. The paper covers a variety of enhancement techniques to get results with very high accuracy. The model gives satisfying results with high precision and accuracy.

Neutralization, masking, equalization, YOLO, classifiers. Machine learning

"Underwater Image Enhancement and Object Detection", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.m691-m696, May-2024, Available :http://www.jetir.org/papers/JETIR2405C93.pdf

"Underwater Image Enhancement and Object Detection", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppm691-m696, May-2024, Available at : http://www.jetir.org/papers/JETIR2405C93.pdf