Alam, Md. AshrafulRahman, WashikurMahmud, TausifArnob, Khondker ShahedChowdhury, Sadnima Amin2025-08-172025-08-1720242024-10ID 21301029ID 21301345ID 21301028ID 21301260http://hdl.handle.net/10361/26550Cataloged from PDF version of thesis.Includes bibliographical references (pages 43-45).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2024.Object detection underwater is particularly difficult because of issues such as low illumination, illumination changes, and the scarcity of labeled underwater images. To overcome these issues, this paper introduces a new type of hybrid image enhancement method (Wav-DUC). The method incorporates the strengths of CLAHE, DCP, DWT, Unsharp Masking, and Bilateral filtering. While adopting the advantages of these techniques, the proposed method improves image quality under the various conditions of marine environments. The enhancement is done in such a way that the enhancement methods are selectively used above a predetermined threshold so as to enhance the image, resulting in an optimum result. testing the model with benchmark dataset [2], we achieved a PSNR score of 21.78 and an SSIM score of 0.8535. Also, the method has an average execution time of 64.78ms on Raspberry Pi 3. This proves the robustness and faster response time of the algorithm, making it suitable for edge devices.45 pagesenBRAC University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.UnderwaterRaspberry piUnsharp maskingTransfer learningBilateral filteringMarine biology.Machine learning.Artificial intelligence.Computer vision.Thesis