Super-resolution of face image extracted from a video sequence

This paper describes a technique to obtain a high resolution image from a given video sequence. The images obtained from inexpensive cameras are generally of low-quality and low-resolution and feeding those images to facial analysis systems generate undesirable outputs. The approach is to implement learning-based super-resolution algorithm on the low-resolution images to obtain high-resolution output. All the images extracted from the video are not useable in super-resolution algorithm. Therefore face quality assessment using facial feature extraction is utilized to discard the unwanted face images. Based on the quality score, it summarizes the input video sequence into a single best quality frontal face image. The employed super-resolution algorithm is applied on the best image resulting in an improved and enhanced high-quality, high-resolution image.