• Version
• Download 8
• File Size 769.67 KB
• File Count 1
• Create Date 15 May 2023
• Last Updated 15 May 2023

UNDERWATER IMAGE ENHANCEMENT USING CURRENT CONVOLUTIONAL NEURAL NETWORK

JOSEPH JOSHUA C, SUHITHA P, NADISH M

BACHELOR OF ENGINEERING

ELECTRICAL AND ELECTRONICS ENGINEERING

Dr. MAHALINGAM COLLEGE OF ENGINEERING AND TECHNOLOGY

POLLACHI - 642003

ABSTRACT

Due to the increased development of marine resources in recent years, underwater picture improvement has received a lot of attention. Many underwater image improvement techniques based on CNNs have been presented in recent years, taking advantage of the powerful representation capabilities of CNNs. The RGB colour space configuration used by almost all of these algorithms, however, is unresponsive to aspects of the image like brightness and saturation. To solve this issue, we suggested the Underwater Picture Enhancement Convolution Neural Network, which combines both RGB and HSV colour spaces into a single CNN utilizing the image dehaze methodology.