A Multichannel Canonical Correlation Analysis Feature Extraction with Application to Buried Underwater Target Classification

Multichannel canonical correlation analysis (MCCA) is used in this paper for feature extraction from multiple sonar returns off of buried underwater objects using data collected by the new generation buried object scanning sonar (BOSS) system. Comparisons are made between the classification results of features extracted by the proposed algorithm and those extracted by the two-channel canonical correlation analysis (CCA) algorithm. This study compares different feature extraction and classification algorithms, and the results are presented in terms of confusion matrices. The results show that MCCA yields higher correct classification rates than CCA while reducing the classifier's structural complexity.

[1]  M.R. Azimi-Sadjadi,et al.  Buried underwater target classification using the new BOSS and canonical correlation decomposition feature extraction , 2005, Proceedings of OCEANS 2005 MTS/IEEE.

[2]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[3]  Gómez,et al.  Multi-set multi-temporal canonical analysis of psoriasis images-DTU Orbit (06/10/2019) , 2002 .

[4]  G. Quentin,et al.  Synthetic aperture processing of buried object scanning sonar data , 2005, Proceedings of OCEANS 2005 MTS/IEEE.

[5]  Allan Aasbjerg Nielsen,et al.  Multiset canonical correlations analysis and multispectral, truly multitemporal remote sensing data , 2002, IEEE Trans. Image Process..

[6]  S. G. Schock,et al.  Buried object scanning sonar for AUVs , 2003, Oceans 2003. Celebrating the Past ... Teaming Toward the Future (IEEE Cat. No.03CH37492).

[7]  Mahmood R. Azimi-Sadjadi,et al.  A network for recursive extraction of canonical coordinates , 2003, Neural Networks.

[8]  Qiang Huang,et al.  Underwater target classification using wavelet packets and neural networks , 2000, IEEE Trans. Neural Networks Learn. Syst..

[9]  Mahmood R. Azimi-Sadjadi,et al.  Multi-aspect target discrimination using hidden Markov models and neural networks , 2005, IEEE Transactions on Neural Networks.

[10]  M.R. Azimi-Sadjadi,et al.  Underwater target classification using canonical correlations , 2003, Oceans 2003. Celebrating the Past ... Teaming Toward the Future (IEEE Cat. No.03CH37492).