A kernel regression based resolution enhancement technique for low resolution video

Super-resolution enhancement is the technique of increasing spatial resolution of an image from the image itself or from several noisy images of the same scene but with additional information such as motion. This paper presents a kernel regression approach to reconstruct a high resolution image from several low resolution video frames. In many applications including cell phone and webcam the imaging sensors capture low resolution images due to low cost sensors or physical limitation of the hardware. So, the proposed resolution enhancement technique could be used as an inexpensive software alternative. The performance of the proposed algorithm is evaluated with several grayscale and color video streams and found successful when compared to other state of the art techniques.