Abstract | ||
---|---|---|
We present a new feature extraction method, which called the complete two-dimensional principal component analysis (Complete 2DPCA), for image registration. Complete 2DPCA is based on 2D image matrices. Two image covariance matrices are constructed directly using the original image matrix and their eigenvectors are derived for image feature extraction. In the 2D image registration scheme, we propose complete 2DPCA to extract features from the image sets, and these features are input vectors of feedforward neural networks (FNN). Neural network outputs are registration parameters with respect to reference and observed image sets. Comparative experiments are performed between complete 2DPCA based method and other feature based methods. The results show that the proposed method has an encouraging performance. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/ICSMC.2008.4811252 | SMC |
Keywords | Field | DocType |
feature extraction method,complete 2dpca,feature extraction,feedforward neural networks,image registration,principal component analysis,geometric transformation,covariance matrix,image features,artificial neural networks,feedforward neural network,polynomials,eigenvectors,neural network,data mining | Feature detection (computer vision),Computer science,Artificial intelligence,Kanade–Lucas–Tomasi feature tracker,Computer vision,Feedforward neural network,Pattern recognition,Image texture,Feature (computer vision),Feature extraction,Machine learning,Principal component analysis,Image registration | Conference |
Volume | Issue | ISSN |
null | null | 1062-922X E-ISBN : 978-1-4244-2384-2 |
ISBN | Citations | PageRank |
978-1-4244-2384-2 | 0 | 0.34 |
References | Authors | |
8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Anbang Xu | 1 | 351 | 30.52 |
Xinyu Chen | 2 | 29 | 7.43 |
Ping Guo | 3 | 601 | 85.05 |