论文信息 - Using a Neural Network to Generate a FIR Filter to Improves Digital Images Using a Discrete Convolution Operation

Using a Neural Network to Generate a FIR Filter to Improves Digital Images Using a Discrete Convolution Operation

The aim of the article is to show correction possibilities of digital images, achieved by image acquisition tools built on low class CCD matrices, such as their quality were close to images achieved by high class tools. For this purpose the authors used the linear filter with 3x3 mask, which were generated with neural network. Digital images were compared using the quality metrics such as MSE, NMSE and Q.

Grzegorz Mikolajczak | Jakub Peksinski | J. Pęksiński | G. Mikolajczak

[1] Thrasyvoulos N. Pappas,et al. Perceptual criteria for image quality evaluation , 2005 .

[2] Martin J. Wainwright,et al. Image denoising using scale mixtures of Gaussians in the wavelet domain , 2003, IEEE Trans. Image Process..

[3] Charles M. Rader,et al. Digital processing of signals , 1983 .

[4] M. Bellanger. Digital processing of signals (2nd ed) , 1989 .

[5] Alexander I. Galushkin,et al. Neural Network Theory , 2007 .

[6] Alan C. Bovik,et al. Image information and visual quality , 2006, IEEE Trans. Image Process..

[7] William K. Pratt,et al. Digital Image Processing: PIKS Inside , 2001 .

[8] R. Kanhirodan,et al. Design of a FIR Filter for Image Restoration using Principal Component Neural Networks , 2006, 2006 IEEE International Conference on Industrial Technology.

[9] Emile Fiesler,et al. Neural Network Initialization , 1995, IWANN.

[10] Alan C. Bovik,et al. Mean squared error: Love it or leave it? A new look at Signal Fidelity Measures , 2009, IEEE Signal Processing Magazine.

[11] A. Bovik,et al. A universal image quality index , 2002, IEEE Signal Processing Letters.

[12] Maurice G. Bellanger,et al. Digital processing of signals: Theory and practice , 1984 .

[13] Alan C. Bovik,et al. Handbook of Image and Video Processing (Communications, Networking and Multimedia) , 2005 .