Introduction to Image Super-resolution
Super-resolution, the process of obtaining one or more high-resolution images from one or more low resolution observations [1], has been a very attractive research topic over the last two decades. It has found practical applications in many real-world problems in different fields, from satellite [2] and aerial imaging to medical image processing, to facial image analysis, text image analysis, sign and number plates reading, and biometrics recognition [3-4], to name a few. This has resulted in many research papers, each developing a new super-resolution algorithm for a specific purpose [5-6]. In this seminar, we will introduce you some of these state-of-the-art works by grouping them in a broad taxonomy. We also will see some applications of state-of-the-art super resolution for surveillance videos.
1. Milanfar, Peyman, ed. Super-resolution imaging. CRC press, 2010.
2. Rasti, Pejman, et al. "Wavelet transform based new interpolation technique for satellite image resolution enhancement." ICARES, 2014 IEEE International Conference on. IEEE, 2014.
3. Rasti, Pejman, et al. "Convolutional Neural Network Super Resolution for Face Recognition in Surveillance Monitoring." AMDO. Springer International Publishing, 2016.
4. Uiboupin, T., Rasti, P., Anbarjafari, G., & Demirel, H. (2016, May). Facial image super resolution using sparse representation for improving face recognition in surveillance monitoring. In 2016 24th Signal Processing and Communication Application Conference (SIU) (pp. 437-440). IEEE.
5. Rasti, Pejman, et al. “New Two-Dimensional Sampling Kernel based Resolution Enhancement”, Signal Processing: Image Communication 2016 (under revision)
6. Rasti, Pejman, et al. “Improved Patch-based Super-Resolution”, IEEE Transactions on Image Processing 2016 (under review).