Self-Learning Super-Resolution Using Convolutional Principal Component Analysis and Random Matching
- 24 September 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 21 (5) , 1108-1121
Abstract
Self-learning super-resolution (SLSR) algorithms have the advantage of being independent of an external training database. This paper proposes a self-learning super-resolution algorithm that uses convolutional principal component analysis (CPCA) and random matching. The technologies of CPCA and random matching greatly improve the efficiency of self-learning. There are two main steps in this algorithm: forming the training and testing the data sets and patch matching. In the data set forming step, we propose the CPCA to extract the lowdimensional features of the data set. The CPCA uses a convolutional method to quickly extract the PCA features of each image patch in every training and testing image. In the patch matching step, we propose a two-step random oscillation accompanied with propagation to accelerate the matching process. This patch matching method avoids exhaustive searching by utilizing the local similarity prior of natural images. The two-step random oscillation first performs a coarse patch matching using the variance feature and then performs a detailed matching using the PCA feature, which is useful to find reliable matching patches. The propagation strategy enables patches to propagate the good matching patches to their neighbors. The experimental results demonstrate that the proposed algorithm has a substantially lower time cost than that of many existing self-learning algorithms, leading to better reconstruction quality.Keywords
Funding Information
- National Natural Science Foundation of China (61601362, 41874173, 61571361, 61671377, 41504115)
- New Star Team of Xi’an University of Posts and Telecommunications (xyt2016-01)
This publication has 56 references indexed in Scilit:
- Super-resolution: a comprehensive surveyMachine Vision and Applications, 2014
- Single image super-resolution via subspace projection and neighbor embeddingNeurocomputing, 2014
- A Statistical Prediction Model Based on Sparse Representations for Single Image Super-ResolutionIEEE Transactions on Image Processing, 2014
- Nonlinear neighbor embedding for single image super-resolution via kernel mappingSignal Processing, 2014
- Single Image Super-Resolution With Multiscale Similarity LearningIEEE Transactions on Neural Networks and Learning Systems, 2013
- On Single Image Scale-Up Using Sparse-Representations2012
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- A new three-step search algorithm for block motion estimationIEEE Transactions on Circuits and Systems for Video Technology, 1994
- Improving resolution by image registrationCVGIP: Graphical Models and Image Processing, 1991
- Cubic splines for image interpolation and digital filteringIEEE Transactions on Acoustics, Speech, and Signal Processing, 1978