Blind Images Separation Based on Sparse Independent Component Analysis

2013 ◽  
Vol 846-847 ◽  
pp. 929-933
Author(s):  
Jing Hui Wang ◽  
Yuan Chao Zhao ◽  
Dong Sheng Chen
Keyword(s):  
Independent Component Analysis ◽  
Time Scale ◽  
Quadratic Function ◽  
Component Analysis ◽  
Independent Component ◽  
Experimental Results ◽  
Frequency Function ◽  
Scale Function ◽  
Time Frequency

In this paper, a novel sparse component multi-resolution independent component analysis is presented. This method separates mixed images based on quadratic function of sparse component coefficient. The quadratic function can be interpreted as the time-frequency function or time-scale function. The performance of the algorithm is evaluated by using noisy mixed images data. Experimental results show that the method is feasible.

Quadratic Independent Component Analysis Based on Sparse Component

2013 ◽  
Vol 442 ◽  
pp. 562-567
Author(s):  
Jing Hui Wang ◽  
Shu Gang Tang
Keyword(s):  
Independent Component Analysis ◽  
Computing Time ◽  
Quadratic Function ◽  
Component Analysis ◽  
Independent Component ◽  
Frequency Function ◽  
Experimental Result ◽  
Scale Function ◽  
Blind Separation ◽  
Time Frequency

In this paper, a novel signal blind separation using adaptive multi-resolution independent component analysis based on sparse component is presented. This method separates mixed signal based on quadratic function and sparse representation. The quadratic function can be interpreted as the time-frequency function or time-scale function, or other. The sparse expression is the original signal through the dictionary to get their coefficients. Most of the coefficients is very small, close to zero, can greatly save separate computing time. At the same time this method can filter out the noise. The argorithm extends the separate technology from time-frequency domain to sparse mutil-resolution domain. The experimental result showed the method can be effective separation of mixed signals. And it shows that the method is feasible.

Image Blind Separation Based on Adaptive Multi-Resolution Independent Component Analysis

2012 ◽  
Vol 586 ◽  
pp. 365-369
Author(s):  
Jing Hui Wang ◽  
Shu Gang Tang
Keyword(s):  
Independent Component Analysis ◽  
Quadratic Function ◽  
Component Analysis ◽  
Independent Component ◽  
Frequency Resolution ◽  
Frequency Function ◽  
Experimental Result ◽  
Blind Separation ◽  
Time Frequency ◽  
Dimensional Domain

In this paper, a novel image blind separation using adaptive multi-resolution independent component analysis is presented.This method separates mixed images based on quadratic function. The quadratic function can be interpreted as the time-frequency function or time-scale function, or other. According to the signal characteristics, we can choose the frequency resolution or scale resolution. The argorithm extends the separate technology from one dimensional domain to two dimensional domain,and it’s implement by adaptive procedure. The experimental result showed the method can be effective separation of mixed images. And it shows that the method is feasible.

Palm Vein Recognition Based on Independent Component Analysis

2013 ◽  
Vol 333-335 ◽  
pp. 1106-1109
Author(s):  
Wei Wu
Keyword(s):  
Pattern Recognition ◽  
Independent Component Analysis ◽  
Euclidean Distance ◽  
Recognition Performance ◽  
Component Analysis ◽  
Independent Component ◽  
Experimental Results ◽  
Vein Pattern ◽  
Vein Recognition ◽  
Palm Vein

Palm vein pattern recognition is one of the newest biometric techniques researched today. This paper proposes project the palm vein image matrix based on independent component analysis directly, then calculates the Euclidean distance of the projection matrix, seeks the nearest distance for classification. The experiment has been done in a self-build palm vein database. Experimental results show that the algorithm of independent component analysis is suitable for palm vein recognition and the recognition performance is practical.

Separation and Reproduction of Mixed Images Using 2-D Complex Wavelet Transform

2010 ◽  
Vol 36 ◽  
pp. 466-475
Author(s):  
Tsutomu Matsuura ◽  
Amirul Faiz ◽  
Kouji Kiryu
Keyword(s):  
Image Processing ◽  
Wavelet Transform ◽  
Independent Component Analysis ◽  
Component Analysis ◽  
Independent Component ◽  
Complex Wavelet Transform ◽  
Time Frequency ◽  
Frequency Information ◽  
Complex Wavelet ◽  
Complex Valued

The differences method between 1-D wavelet transform and 2-D wavelet transform in image processing is discussed. Both proposed method uses the quotient of complex valued time-frequency information of observed signals to detect the number of sources. No less number of observed signals than the detected number of sources is needed to separate sources. The assumption on sources is quite general independence in the time-frequency plane, which is different from that of independent component analysis. Using the same given Algorithm and parameters for both method, the result on separated images are compared.

Sign in / Sign up

Export Citation Format

Share Document