In this paper we propose a zoom based technique to super resolve static scene using observation captured at different camera zoom factor. We capture a static scene at different camera zoom and obtain super resolved image of entire scene at resolution of most zoom observation. Minimum absolute error criteria is used to model image features such as edges, corners etc. We utilize the fact that the local geometry of these features in the low resolution image is similar to their corresponding high resolution version. Missing high frequency details of low resolution observation are learnt in the form of discrete cosine transform coefficient from high resolution training images in the database. The experiments are conducted on real world scene and results are compared with standard interpolation techniques.

1. Sung Cheol Park, Min Kyu Park, and Moon Gi Kang, "Super-Resolution Image Reconstruction: A Technical Overview", IEEE Signal Processing Magazine, pp. 21-36, May 2003.
2. R. Y. Tsai and T. S. Huang, "Multiframe image restoration and registration," Advances in Computer Vision and Image Processing, pp. 317-339, 1984.
3. R. C. Hardie, K. J. Barnard, and E. E. Armstrong, "Joint map registration and high-resolution image estimation using a sequence of undersampled images," IEEE Trans. Image Process. , vol. 6, pp. 1621–1633, 1997.
4. M. Elad and A. Feuer, "Restoration of a single super-resolution image from several blurred, noisy and undersampled measured images," IEEE Trans. Image Process, vol. 6, pp. 1646–1658, 1997.
5. H. Shen, L. Zhang, B. Huang, and P. Li, "A MAP approach for joint motion estimation, segmentation, and super resolution," IEEE Trans. Image Process. , vol. 16, pp. 479–490, 2007.
6. K. V. Suresh, G. M. Kumar, and A. N. Rajagopalan, "Superresolution of license plates in real traffic videos," IEEE Trans. Intell. Transport. Syst. , vol. 8, no. 2, pp. 321–331, Feb. 2007.
7. W. T. Freeman, T. R. Jones and E. C. Pasztor, 'Example-based super-resolution", IEEE Computer Graphics and Applications, pp. 56-65, 2002.
8. P. P. Gajjar and M. V. Joshi, "New Learning Based Super-Resolution: Use of DWT and IGMRF Prior" in IEEE transaction on image processing, vol. 19, no 5, May 2010, pp. 1201-1213.
9. P. V. Pithadia, P. P. Gajjar, J. G. Dave, "Super Resolution using DCT based Learning with LBP as Feature Model", in IEEE International conference on Computing, Communication & Networking Technologies (ICCC NT 2012).
10. H. Yue, J. Yang, X. Sun, F. Wu, "SIFT-Based Image Super-Resolution" in IEEE 2013, pp. 2896-2899.
11. M. V. Joshi, S. Chaudhuri, and R. Panuganti, "A Learning-Based Method for Image Super-Resolution From Zoomed Observations" in IEEE transactions on system, man, and cybernetics-part B: cybernetics, Vol. 35, NO. 3, JUNE 2005, pp. 527-537.
12. S. Dabbaghchian, M. P. Ghaemmaghami and Ali Aghagolzadeh, "Feature extraction using discrete cosine transform and discrimination power analysis with a face recognition technology",Journal of Pattern Recognition, 2010, pp. 1431-1440.
13. Nuno Roma and Leonel Sousa, "A tutorial overview on the properties of the discrete cosine transform for encoded image and video processing", Journal of Signal Processing, 2011, pp. 2443-2464.
14. Wei Zhang and Wai-Kuen Cham, "Hallucinating Face in the DCT Domain", IEEE Transactions on Image Processing, 2011, pp. 2769-2779.

Learning Based Method Discrete Cosine Transforms (dct) Minimum Absolute Error Criteria And Super Resolution.