Underwater Image Enhancement for Instance Segmentation using Deep Learning Models

• Published in: Journal of Applied Sciences and Environmental Management Vol. 27; no. 2; pp. 243 - 247
• Main Authors: Bello, R. W., Oluigbo, C. U., Peanock, I. G., Moradeyo, O. M.
• Format: Journal Article
• Language: English
• Published: Joint Coordination Centre of the World Bank assisted National Agricultural Research Programme (NARP) 28.02.2023
• Subjects: convolutional neural networks; deep learning; image enhancement; underwater image
• ISSN: 1119-8362; 2659-1499; 2659-1502; 2659-1502; 2659-1499
• DOI: 10.4314/jasem.v27i2.9

Underwater instance segmentation greatly depends on color-blended underwater images. In this work, a combination of Generalized Color Fourier Descriptor (GCFD), Convolutional Neural Network (CNN) and Mask Region-based Convolutional Neural Network (Mask R-CNN) models were employed to generate a mask for each bounding-boxed Region of Interest (ROI) to obtain enhanced individual underwater segmented images from their complex background accurately. By this image enhancement approach, individual underwater instances are segmented from their complex background accurately. The Patch-based Contrast Quality Index (PCQI) evaluation of our proposed image enhancement method (GCFD) after conducting experiment on the employed datasets shows performance accuracy of 1.1336, which is higher than the 1.1126 performance accuracy achieved by the Contrast-enhancement Algorithm (CA).