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.

[1]  Roger Y. Tsai,et al.  Multiframe image restoration and registration , 1984 .

[2]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[3]  Liangpei Zhang,et al.  A super-resolution reconstruction algorithm for surveillance images , 2010, Signal Process..

[4]  Robert L. Stevenson,et al.  Extraction of high-resolution frames from video sequences , 1996, IEEE Trans. Image Process..

[5]  Michal Irani,et al.  Improving resolution by image registration , 1991, CVGIP Graph. Model. Image Process..

[6]  Yizhen Huang,et al.  Super-resolution using neural networks based on the optimal recovery theory , 2006, 2006 16th IEEE Signal Processing Society Workshop on Machine Learning for Signal Processing.

[7]  Vivek Bannore,et al.  Iterative-Interpolation Super-Resolution Image Reconstruction - A Computationally Efficient Technique , 2009, Studies in Computational Intelligence.

[8]  Roberto Cipolla,et al.  A manifold approach to face recognition from low quality video across illumination and pose using implicit super-resolution , 2007, ICCV 2007.

[9]  N. K. Bose,et al.  High resolution image formation from low resolution frames using Delaunay triangulation , 2002, IEEE Trans. Image Process..

[10]  Yücel Altunbasak,et al.  Artifact reduction for set theoretic super resolution image reconstruction with edge adaptive constraints and higher-order interpolants , 2001, IEEE Trans. Image Process..

[11]  James L. Crowley,et al.  Head Pose Estimation on Low Resolution Images , 2006, CLEAR.

[12]  Christopher M. Bishop,et al.  Bayesian Image Super-Resolution , 2002, NIPS.

[13]  Thomas B. Moeslund,et al.  Face Quality Assessment System in Video Sequences , 2008, BIOID.

[14]  Moon Gi Kang,et al.  Super-resolution image reconstruction , 2010, 2010 International Conference on Computer Application and System Modeling (ICCASM 2010).

[15]  Thomas S. Huang,et al.  Image super-resolution as sparse representation of raw image patches , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Mohan M. Trivedi,et al.  Head Pose Estimation in Computer Vision: A Survey , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Takeo Kanade,et al.  Hallucinating faces , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[18]  Francisco de Borja Rodríguez Ortiz,et al.  A two-step neural-network based algorithm for fast image super-resolution , 2007, Image Vis. Comput..

[19]  Hong Chang,et al.  Super-resolution through neighbor embedding , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[20]  Xuelong Li,et al.  A multi-frame image super-resolution method , 2010, Signal Process..