Image resolution enhancement via image restoration using neural network

Image super-resolution aims to obtain a high-quality image at a resolution that is higher than that of the original coarse one. This paper presents a new neural network-based method for image super-resolution. In this technique, the super-resolution is considered as an inverse problem. An observation model that closely follows the physical image acquisition process is established to solve the problem. Based on this model, a cost function is created and minimized by a Hopfield neural network to produce high-resolution images from the corresponding low-resolution ones. Not like some other single frame super-resolution techniques, this technique takes into consideration point spread function blurring as well as additive noise and therefore generates high-resolution images with more preserved or restored image details. Experimental results demonstrate that the high-resolution images obtained by this technique have a very high quality in terms of PSNR and visually look more pleasant.

[1]  A. Murat Tekalp,et al.  Digital Video Processing , 1995 .

[2]  Edward A. Watson,et al.  High-Resolution Image Reconstruction from a Sequence of Rotated and Translated Frames and its Application to an Infrared Imaging System , 1998 .

[3]  Lei Zhang,et al.  An edge-guided image interpolation algorithm via directional filtering and data fusion , 2006, IEEE Transactions on Image Processing.

[4]  Aggelos K. Katsaggelos,et al.  Image restoration using a modified Hopfield network , 1992, IEEE Trans. Image Process..

[5]  Philip J. Bones,et al.  Statistical interpolation of sampled images , 2001 .

[6]  J. Paik,et al.  Regularized Interative Image Interpolation and its application to Spatially Scalable Coding , 1998, International 1998 Conference on Consumer Electronics.

[7]  Nirmal K. Bose,et al.  Recursive reconstruction of high resolution image from noisy undersampled multiframes , 1990, IEEE Trans. Acoust. Speech Signal Process..

[8]  Shuangteng Zhang,et al.  Image Resolution Enhancement Using a Hopfield Neural Network , 2007, Fourth International Conference on Information Technology (ITNG'07).

[9]  Robert L. Stevenson,et al.  A Bayesian approach to image expansion for improved definitio , 1994, IEEE Trans. Image Process..

[10]  Samir I. Shaheen,et al.  Adaptive resampling algorithm for image zooming , 1997 .

[11]  Hsieh Hou,et al.  Cubic splines for image interpolation and digital filtering , 1978 .

[12]  A. Murat Tekalp,et al.  Maximum likelihood image and blur identification: a unifying , 1990 .

[13]  Mei-Juan Chen,et al.  A fast edge-oriented algorithm for image interpolation , 2005, Image Vis. Comput..

[14]  Xiangjun Zhang,et al.  Image Interpolation by Adaptive 2-D Autoregressive Modeling and Soft-Decision Estimation , 2008, IEEE Transactions on Image Processing.

[15]  Dimitris Anastassiou,et al.  Subpixel edge localization and the interpolation of still images , 1995, IEEE Trans. Image Process..

[16]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[17]  Man-ni Duan,et al.  A layered SR restoration algorithm based on hopfield neural network , 2006, 2006 8th international Conference on Signal Processing.

[18]  Michael Elad,et al.  Super-Resolution Without Explicit Subpixel Motion Estimation , 2009, IEEE Transactions on Image Processing.

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

[20]  B. K. Jenkins,et al.  Image restoration using a neural network , 1988, IEEE Trans. Acoust. Speech Signal Process..

[21]  Giovanni Ramponi,et al.  Warped distance for space-variant linear image interpolation , 1999, IEEE Trans. Image Process..

[22]  Jia-Guu Leu.  Image enlargement based on a step edge model , 2000, Pattern Recognit..

[23]  Liming Zhang,et al.  New image super-resolution scheme based on residual error restoration by neural networks , 2003 .

[24]  R. Keys.  Cubic convolution interpolation for digital image processing , 1981 .

[25]  Sebastiano Battiato,et al.  A locally adaptive zooming algorithm for digital images , 2002, Image Vis. Comput..

[26]  B. Gunturk,et al.  Multiframe resolution-enhancement methods for compressed video , 2002, IEEE Signal Processing Letters.

[27]  A. Murat Tekalp,et al.  Maximum likelihood parametric blur identification based on a continuous spatial domain model , 1992, IEEE Trans. Image Process..

[28]  José Carlos Príncipe,et al.  Super-resolution of images based on local correlations , 1999, IEEE Trans. Neural Networks.