Classified image interpolation using neural networks

An improved classified image interpolation algorithm is presented. The algorithm obtains high-resolution pixels by filtering with parameters that are optimal for the selected class. By applying the highly flexible neural network model in the proposed algorithms, classified image data is extended into a nonlinear model in each class while enhancing the sharpness and edge characteristic. Meantime the interpolation performance is improved and computer complexity is reduced. Besides emulation, the technology has been applied to the visual presenter with low-resolution image sensor. Results demonstrate that the new algorithm improves substantially the subjective and objective quality of the interpolated images over original interpolation algorithms, and meets the requirements of real time image processing.

[1]  S. Carrato,et al.  Neural network-based image segmentation for image interpolation , 1995, Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing.

[2]  Ahmed M. Darwish,et al.  Adaptive resampling algorithm for image zooming , 1996, Electronic Imaging.

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

[4]  Jan P. Allebach,et al.  Optimal image scaling using pixel classification , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

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

[6]  G. de Haan,et al.  Towards an Overview of Spatial Up-conversion Techniques. , 2002 .

[7]  Brian E. Cooper,et al.  Adaptive image interpolation using a multilayer neural network , 2001, IS&T/SPIE Electronic Imaging.

[8]  Nathalie Plaziac.  Image interpolation using neural networks , 1999, IEEE Trans. Image Process..

[9]  Hao Hu,et al.  Image interpolation using classification-based neural networks , 2004, IEEE International Symposium on Consumer Electronics, 2004.

[10]  Kwanghoon Sohn,et al.  Interpolation using neural networks for digital still cameras , 2000, IEEE Trans. Consumer Electron..

[11]  R. Fletcher.  Practical Methods of Optimization , 1988 .

[12]  Mohammad A. Karim,et al.  High-fidelity image interpolation using radial basis function neural networks , 1995, Proceedings of the IEEE 1995 National Aerospace and Electronics Conference. NAECON 1995.

[13]  S.A. Martucci.  Image resizing in the discrete cosine transform domain , 1995, Proceedings., International Conference on Image Processing.

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