Blur Classification and Estimation of Motion Blur Parameters Using OLR

The atmospheric conditions impair the quality of underwater pictures. Motion blur induced by the imaging device or the movement of the object is one of the most significant issues in underwater images. With the Artificial Intelligence and Robotics industries skyrocketing and dominating the market lately, researchers have utilized these technologies to explore and research beyond and beneath the surface of the earth and one of them being underwater image analysis and processing. But the process of underwater imaging is very complex with a lot of challenges ahead needed to be tackled. Parameters of the blurred picture must be determined to fix this in post-processing. As a result, the characteristics estimate the point spread function based on the image's spectrum. After measuring the angle and length of motion blurred pictures, the Optimized Linear Regression (OLR) approach is used to increase the parameter estimation accuracy. The data was first gathered and analyzed in real-time settings in Chennai. For underwater pictures, the suggested OLR approach outperforms the current traditional Cepstral, Hough, and Radon transform estimation methods.