Digital Image Processing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Blind Source Separation with Wavelet Based ICA Technique Using Kurtosis


Affiliations
1 Engineering Department, Nuclear Research Center, Atomic Energy Authority, Egypt
2 Department of Electronics and Electrical Communications, Menoufia University, Menouf, Egypt
3 Nuclear Research Center, Atomic Energy Authority, Egypt
     

   Subscribe/Renew Journal


This paper deals with the problem of blind separation of digital images from mixtures. A method to solve this problem is blind source separation (BSS) using independent component analysis (ICA). It proposes a wavelet based ICA method using Kurtosis for blind image source separation. In this method, the observations are transformed into an adequate representation using wavelet packets decomposition and Kurtosis criterion. The simulation results of performance measures show a considerable improvement when compared to FastICA. The Peak Signal-to-Noise Ratio (PSNR), Signal-to-Noise Ratio (SNR), Root Mean Square Error (RMSE) and and Segmental Signal-to-Noise Ratio (SNRseg) are used to evaluate the quality of the separated images.

Keywords

Blind Source Separation (BSS), ICA, Kurtosis.
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 235

PDF Views: 1




  • Blind Source Separation with Wavelet Based ICA Technique Using Kurtosis

Abstract Views: 235  |  PDF Views: 1

Authors

Mohammed Y. Abbass
Engineering Department, Nuclear Research Center, Atomic Energy Authority, Egypt
Safey A. Abdelwahab
Engineering Department, Nuclear Research Center, Atomic Energy Authority, Egypt
Salah M. Diab
Department of Electronics and Electrical Communications, Menoufia University, Menouf, Egypt
Bassiony M. Salam
Department of Electronics and Electrical Communications, Menoufia University, Menouf, Egypt
El-Sayed M. El-Rabaie
Department of Electronics and Electrical Communications, Menoufia University, Menouf, Egypt
Fathi E. Abd El-Samie
Department of Electronics and Electrical Communications, Menoufia University, Menouf, Egypt
Said S. Haggag
Nuclear Research Center, Atomic Energy Authority, Egypt

Abstract


This paper deals with the problem of blind separation of digital images from mixtures. A method to solve this problem is blind source separation (BSS) using independent component analysis (ICA). It proposes a wavelet based ICA method using Kurtosis for blind image source separation. In this method, the observations are transformed into an adequate representation using wavelet packets decomposition and Kurtosis criterion. The simulation results of performance measures show a considerable improvement when compared to FastICA. The Peak Signal-to-Noise Ratio (PSNR), Signal-to-Noise Ratio (SNR), Root Mean Square Error (RMSE) and and Segmental Signal-to-Noise Ratio (SNRseg) are used to evaluate the quality of the separated images.

Keywords


Blind Source Separation (BSS), ICA, Kurtosis.