M.K. Sundareshan and R. Inampudi (USA)
Image Processing, Super-resolution, Neural Networks, Region of Interest Extraction
Computational complexity is a major impediment to the real-time implementation of image restoration and super-resolution algorithms. Although very powerful restoration algorithms have been developed within the last few years utilizing sophisticated mathematical machinery (based on statistical optimization and convex set theory), these algorithms are typically iterative in nature and require enough number of iterations to be executed in order to achieve desired levels of resolution gains in practice. Consequently, development of novel methods that facilitate real-time implementation of image restoration and super-resolution algorithms is of significant practical interest. Design of a pre-processing filter that extracts the Region of Interest (ROI) for reducing the size of the image to be subjected to super resolution processing will be described in this paper and the use of Hough transform and neural network methods for this objective will be outlined. The restoration and super-resolution performance of the overall image processing sequence will be quantitatively evaluated by integrating the ROI extraction scheme with a powerful iterative image restoration procedure.
Important Links:
Go Back
