UNDERWATER IMAGE ENCHANCEMENT USING MACHINE LEARNING THROUGH EMBEDDED SYSTEM
The visibility of underwater images captured is degraded because of the presence of water, haze, fog and so on. Various atmospheric phenomena results in poor visibility which in turn results in the degradation of computer vision applications. To overcome such problems, various visibility restoration techniques are employed that are used to play a vital role in many computer vision applications that operate in various weather conditions. However, removing haze from a single image with a complex structure and color distortion is a difficult task for visibility restoration techniques. In this paper, a novel visibility restoration approach for images captured in under water images and featuring variable scenes is proposed. When the fish is detected, the device simulates the vibrating motor to vibrate. Such that fisherman can easily detect the presence of fish.