A CNN based Hybrid approach towards automatic image registration

• Autorzy: Arun P. V. , Katiyar S. K.

Warianty tytułu

PL

Hybrydowe podejście do automatycznej rejestracji obrazu z wykorzystaniem komórkowych sieci neuronowych

• Języki publikacji: EN

Abstrakty

EN

Image registration is a key component of various image processing operations which involve the analysis of different image data sets. Automatic image registration domains have witnessed the application of many intelligent methodologies over the past decade; however inability to properly model object shape as well as contextual information had limited the attainable accuracy. In this paper, we propose a framework for accurate feature shape modeling and adaptive resampling using advanced techniques such as Vector Machines, Cellular Neural Network (CNN), SIFT, coreset, and Cellular Automata. CNN has found to be effective in improving feature matching as well as resampling stages of registration and complexity of the approach has been considerably reduced using corset optimization The salient features of this work are cellular neural network approach based SIFT feature point optimisation, adaptive resampling and intelligent object modelling. Developed methodology has been compared with contemporary methods using different statistical measures. Investigations over various satellite images revealed that considerable success was achieved with the approach. System has dynamically used spectral and spatial information for representing contextual knowledge using CNN-prolog approach. Methodology also illustrated to be effective in providing intelligent interpretation and adaptive resampling.

PL

Rejestracja obrazu jest kluczowym składnikiem różnych operacji jego przetwarzania. W ostatnich latach do automatycznej rejestracji obrazu wykorzystuje się metody sztucznej inteligencji, których największą wadą, obniżającą dokładność uzyskanych wyników jest brak możliwości dobrego wymodelowania kształtu i informacji kontekstowych. W niniejszej pracy zaproponowano zasady dokładnego modelowania kształtu oraz adaptacyjnego resamplingu z wykorzystaniem zaawansowanych technik, takich jak Vector Machines (VM), komórkowa sieć neuronowa (CNN), przesiewanie (SIFT), Coreset i automaty komórkowe. Stwierdzono, że za pomocą CNN można skutecznie poprawiać dopasowanie obiektów obrazowych oraz resampling kolejnych kroków rejestracji, zaś zastosowanie optymalizacji metodą Coreset znacznie redukuje złożoność podejścia. Zasadniczym przedmiotem pracy są: optymalizacja punktów metodą SIFT oparta na podejściu CNN, adaptacyjny resampling oraz inteligentne modelowanie obiektów. Opracowana metoda została porównana ze współcześnie stosowanymi metodami wykorzystującymi różne miary statystyczne. Badania nad różnymi obrazami satelitarnymi wykazały, że stosując opracowane podejście osiągnięto bardzo dobre wyniki. System stosując podejście CNN-prolog dynamicznie wykorzystuje informacje spektralne i przestrzenne dla reprezentacji wiedzy kontekstowej. Metoda okazała się również skuteczna w dostarczaniu inteligentnych interpretacji i w adaptacyjnym resamplingu.

Słowa kluczowe

EN

cellular neural network (CNN); image analysis; image registration; resampling; remote sensing

PL

teledetekcja; metody resamplingu; sieć neuronowa komórkowa; analiza obrazu; rejestracja obrazu

• Wydawca: Komitet Geodezji PAN
• Czasopismo: Geodesy and Cartography
• Rocznik: 2013
• Tom: Vol. 62, no. 1
• Strony: 33--49
• Opis fizyczny: Bibliogr. 40 poz., rys., tab.

Twórcy

autor

Arun P. V.

• National Institute of Technology Madhya Pradesh, India

autor

Katiyar S. K.

• Maulana Azad National Institute of Technology- Bhopal Department of Civil Engineering, Bhopal Madhya Pradesh, India

Bibliografia

• Agarwal, P. K., Aronov B. & Sharir M. (2001). Exact and approximation algorithms for minimum-width cylindrical shells. Discrete Computational Geometry, 26(3), 307-320. DOI: 10.1007/s00454-001-0039-6.
• Australian Geoscience portal. (2013, March). Retrived January 2013 from http://www.ga.gov.au/.
• Badoiu, M, Har-Peled S. & Indyk P. (2003). Approximate clustering via corsets. In Proceedings of 34th Annual ACM Symposium, Theory of Computation, 19-21 May 2002 (pp. 250-257). Montréal, Québec, Canada: ACM.
• Camann, K., Thomas A. & Ellis J. (2010). Resampling considerations for registering remotely sensed images. In Proceedings of the IEEE SoutheastCon 2010 (SoutheastCon), 18-21 March 2010 (pp. 159-162). Charlotte, North Carolina, USA: Institute of Electrical and Electronics Engineers (IEEE). DOI: 10.1109/SECON.2010.5453899.
• Chang, T. & Kuo C. J. (1993). Texture analysis and classification with tree-structured wavelet transform. IEEE Transactions on Image Processing, 2(4), 429-441. DOI: 10.1109/83.242353.
• Chow, C. K., Tat Tsui H. & Lee T. (2004). Surface Registration using a dynamic genetic algorithm. Journal of Pattern Recognition, 37(1), 105-117. DOI: 10.1016/S0031-3203(03)00222-X.
• Cvejic, N., Cangarajah C N. & Bull D. R. (2006). Image fusion metric based on mutual information and Tsallis entropy. Electronic Letters, 42(11), 626-627. DOI: 10.1049/el:20060693.
• Gouveia, A. R., Metz C., Freire L. & Klein S. (2012). 3D-2D image registration by nonlinear regression. In 9th IEEE International Symposium on Biomedical Imaging (ISBI), 02-05 May 2012 (pp. 1343-1346), Barcelona, Spain: Institute of Electrical and Electronics Engineers (IEEE).
• Grodecki, J. Dial G. & Lutes, J. (2004). Mathematical model for 3D feature extraction from multiple satellite images described by RPCs. In ASPRS Annual Conference, 23-28 May 2004 (pp. 1091-1098). Denver, Colorado, USA: American Society for Photogrammetry and Remote Sensing.
• Hong, G. & Zhang Y. (2008). Wavelet based technique for image registration techniques for high resolution satellite imagery. Computers and Geosciences, 34, 1708-1720.
• Hosseini, R. S. & Homayouni S. (2009). A SVMS-based hyper spectral data classification algorithm in a similarity space. In Workshop on Hyper spectral Image and Signal Processing: Evolution in Remote Sensing- WHISPERS ‘09, 26-28th August 2001 (pp. 1-4). Grenoble, France: Institute of Electrical and Electronics Engineers (IEEE). DOI: 10.1109/WHISPERS.2009.5288980.
• Jacq, J-J. & Roux Ch. (1995). Registration of 3-D images by genetic optimization. Pattern RecognitionLetters, 16(12), 823-841. DOI: 10.1016/0167-8655(95)00051-H.
• Jian, B. & Vemuri B. C. (2005). A robust algorithm for point set image registration using mixture of gausians. In Tenth IEEE International Conference on computer Vision, Vol.2, 7-20 October 2005 (pp. 1246-1251). Beijing, China: IEEE Computer Society.
• Klein, S. (2007). Evaluation of Optimization Methods for Nonrigid Medical Image Registration Using Mutual Information and B Splines. IEEE Transactions on Image Processing, 16(12), pp.2797-2890. DOI: 10.1109/TIP.2007.909412.
• Knops, Z. F., Maintz J., Viergever M. & Pluim J. (2004). Registration using segment intensity remapping and mutual information. MICCAI 2004, Lecture Notes in Computer Science, vol. 3216, 805-812.
• Kumar S. & Hebert, M. (2003). Discriminative random fields: a discriminative framework for contextual interaction in classification. In Proceedings of Ninth IEEE International Conference on Computer Vision, 2(4), 13-16 October 2003 (pp.1150-1157). Nice, France: Institute of Electrical and Electronics Engineers (IEEE).
• Lee, C., Schmidt M. & Greiner R. (2005). Support vector random fields for spatial classification. In 9th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD), 3-7 October 2005 (pp. 196). Porto, Portugal: Artificial Intelligence and Computer Science Laboratory.
• Lindi, J. Q. (2004). A Review of Techniques for Extracting Linear Features from Imagery. PhotogrammetricEngineering & Remote Sensing, 70(12), 1383-1392.
• Liu, J. & Wu H. (2012). A New Image Registration Method Based on Frame and Gray Information. In International Conference on Computer Distributed Control and Intelligent Enviromental Monitoring CDCIEM, 5-6 March 2012 (pp. 48-51). Zhangjiajie, Hunan, China: Institute of Electrical and Electronics Engineers (IEEE).
• Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91-110. DOI: 10.1109/TMI.2012.2212718.
• Malviya, A. & Bhirud S.G. (2009). Wavelet based image registration using mutual information. Emerging Trends in Electronic and Photonic Devices & Systems. In ELECTRO ‘09 International Conference, 22-24 Aug 2009 (pp. 241-244). Mumbai, India: Institute of Electrical and Electronics Engineers (IEEE).
• Mercier, G. & Lennon M., (2003). Support Vector Machines for Hyperspectral Image Classification with Spectral-based kernels. IIEEE-Transactions of Geo Science and Remote Sensing, 45(3), 123-130.
• Mitchell, M., Crutchfield J. P. & Das R. (1996). Evolving Cellular Automata with Genetic Algorithms: A Review of Recent Work. In First International Conference on Evolutionary Computation and Its Applications (EvCA’96), 1(1), 20-22 May 1996 (pp.120-130). Nayoya Japan: Nayoya University.
• Mnih, V. & Hinton, G. (2010). Learning to detect roads in high-resolution aerial images. In 11th European Conference on Computer Vision (ECCV), vol. 10(1), 5-15 September 2010 (pp.120-130). Heraclion, Crete, Greece: Foundation for Research and Technology-Hellas (FORTH).
• Mohanalin, J. & Kalra P. K. (2009). Mutual Information based Rigid Medical Image registration using Normalized Tsallis entropy and Type II fuzzy index. International Journal of Computer Theory andEngineering, 1(2), 173-178.
• Orovas, C. & Austin J. (2000). A cellular system for pattern recognition using associative neural networks. Lecture Notes in Computer Science 1778, 372-386. DOI: 10.1007/10719871_26.
• Pluim, J. P.W., Maintz J. B. A. & Viergever M. A. (2000). Image registration by maximization of combined mutual information and gradient information. IEEE Transactions of Medical Imaging, vol. 19(8), 809-814.
• Porway, J., Wang K., Yao B. & Zhu S. C. (2008). A hierarchical and contextual model for aerial image understanding. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 49(7), 155-160. DOI:10.1007/s11263-009-0306-1.
• Schnitzspan, P., Mario F. & Bernt S. (2008). Hierarchical Support Vector Random Fields: Joint Training to Combine Local and Global Features. Computer Vision - ECCV 2008. In 10th European Conference on Computer Vision, Proceedings, Part II. 12-18 October 2008 (pp. 527-540). Marseille, France: Springer.
• Sikdar, B. K., Paul K., Biswas G. P., Yang C., Bopanna V., Mukherjee S. & Chaudhuri P. P. (2000). Theory and Application of GF(2P) Cellular Automata as On-Chip Test Pattern Generator. In Proceedings of 13th Int. Conf. on VLSI Design, 3-7 January 2000 (pp. 556-561). Bangalore, India: Institute of Electrical and Electronics Engineers (IEEE).
• Srivastava, A. N. (2004). Mixture Density Mercer Kernels: A Method to Learn Kernels Directly from Data. In SIAM Data Mining Conference, 22-24 April 2004 (369-378). Lake Buena Vista, Florida, USA: Florida University.
• Sunil, R. R., Dennis D. T., Eric K. & Charles G. O. (2004). Comparing Spectral and Object Based Approaches for Classification and Transportation Feature Extraction from High Resolution Multispectral Imagery. In ASPRS Annual Conference Proceedings, 15-24 May 2004. Denver, Colorado, USA: The American Society for Photogrammetry and. Remote Sensing (ASPRS).
• Trinder, J. & Li H. (2003). Semi-automatic feature extraction by snakes. Automatic Extraction of Man-Made Objects from Aerial and Space Images, 25(1), 95-104. DOI: 10.1007/978-3-0348-9242-1_10.
• Vapnik, V. N. (1998). Statistical Learning Theory. New York: Wiley Publishers Inc.
• Viola, P. A. (1997). Alignment by maximization of mutual information. International Journal ofComputer Vision, 24(2), 137-154.
• Wang, H., Yang Y., Ma S. & Guo C. (2009). Automatic Object Extraction Based on Fuzzy Mask. In Intelligent Systems and Applications, ISA International Workshop on, vol.23(2), 23-23 May 2009 (pp. 1352-1355). Wuhan, China: Institute of Electrical and Electronics Engineers IEEE.
• Yuan, J., Wang D., Wu B., Yan L. & Li R. (2009). Automatic Road Extraction from Satellite Imagery Using LEGION Networks. In IJCNN’09 Proceedings of the 2009 international joint conference on Neural Networks, 14-19 June 2009 (pp. 188-193). NJ, USA: IEEE Press Piscataway.
• Zagorchev, L. & Goshtasby A. (2006). A comparative study of transformation functions for nonrigid image registration, IEEE Transactions on Image Processing, 15(3), 529-538. DOI: 10.1109/ TIP.2005.863114.
• Zitová, B. & Flusser J. (2003). Image registration methods: a survey. Image Vision Computation, 21 (11), 977-1000.
• Zsolt, J. (2006). Using a genetic algorithm to register an uncelebrated image pair to a 3D surface model, Engineering Applications of Artificial Intelligence, 19(1), 269-276.