Show simple item record

dc.contributor.advisorDeng, Da
dc.contributor.authorZhang, Jianhuaen_NZ
dc.date.available2011-04-07T03:12:56Z
dc.date.copyright2005-02-28en_NZ
dc.identifier.citationZhang, J. (2005, February 28). An approach for intelligent image collection navigation and semantic analysis (Dissertation, Master of Science). Retrieved from http://hdl.handle.net/10523/1321en
dc.identifier.urihttp://hdl.handle.net/10523/1321
dc.description.abstractWith the growing use of multimedia such as images and videos in industries as well as in our daily life, image retrieval has become a vital technology for users to consume the valuable multimedia resources effectively and efficiently. For example it is not easy to browse or search a large image collection. Content-based image retrieval has achieved limited success in multimedia asset management and rapid information retrieval based on low-level visual features. However, humans normally access multimedia assets by semantic concepts. There is a significant semantic gap existing between low-level visual features processed by machines and semantic concepts interpreted by humans. It is generally understood that the problem of image retrieval is still far from being solved. As indicated by literatures, image semantic analysis and visualisation are well known research areas to overcome this gap and to enhance the capability of content-based image retrieval systems. This thesis proposes an approach for intelligent image collection navigation and semantic analysis to bridge the gap between visual features and semantics. Some of MPEG-7 colour and texture descriptors based on global and local visual features are selected as multiple representations of images, as they have been intensively and successfully evaluated in many of image retrieval experiments. Taking a pattern classification approach for image semantic analysis, two types of classifiers are designed according to the different characteristics of global and local visual features to classify images into the predefined classes. Combination classifications are investigated in this study. Leave-one-out cross-validation is employed to evaluate their performances using different visual features and combination schemes. In order to increase the impact of the classifiers with high precisions in the final classification decision, the precision-based combination rule that weights each classifier based on its precision in the combination of the results is proposed. For the visualisation of image collections, an intelligent image collection navigation system is developed by joining the SOM-based image visualisation based on visual feature spaces together with semantic concepts extracted from semantic analysis. Experiments show that the proposed approach is successful in improving the accuracy of indoor and outdoor scenes classification and revealing image collection structure both in the visual feature spaces and on the semantics level. With further works on this study the system is able to assist users to develop automatic interpretations to the image collection and navigate and access images of interests much more easily.en_NZ
dc.subjectimage retrievalen_NZ
dc.subjectmultimediaen_NZ
dc.subjectintelligent image collection navigationen_NZ
dc.subjectsemantic analysisen_NZ
dc.subjectpattern classification approach,en_NZ
dc.subject.lcshT Technology (General)en_NZ
dc.subject.lcshQ Science (General)en_NZ
dc.titleAn approach for intelligent image collection navigation and semantic analysisen_NZ
dc.typeDissertationen_NZ
dc.description.versionUnpublisheden_NZ
otago.date.accession2007-02-19en_NZ
otago.schoolInformation Scienceen_NZ
thesis.degree.disciplineInformation Scienceen_NZ
thesis.degree.nameMaster of Science
thesis.degree.grantorUniversity of Otagoen_NZ
thesis.degree.levelMasters Dissertationsen_NZ
otago.interloanyesen_NZ
otago.openaccessAbstract Only
dc.identifier.eprints547en_NZ
otago.school.eprintsInformation Scienceen_NZ
dc.description.referencesA.Vailaya, M, A, T. Figueiredo, et al. (2001). "Image classification for content-based indexing." Image Processing, IEEE Transactions 10(1): 117-130. Barnard, K. and F. Forsyth (2001), Learning the Semantics of Words and Picture, IEEE International Conference on Computer Vision II. Burger, C. J. C. (1998). "A Tutorial on Support Vector Machines for Pattern Recognition." Data Ming and Knowledge Discovery (2): 121-167. Carson, C., S. Belongie, et al. (2002), "Blobworld: Image segmentation using Expectation-Maximization and its application to image querying," IEEE Trans on PAMI 24(8): 1024-1038, Casteli, V. and L. D, Bergman, Eds, (2002), Image Databases Search and Retrieval of Digital Imagery, John Wiley & Sons. Corridoni, J, M., A. D, Bimbo, et al. (1999). "Image Retrieval by Colour Semantics," Multimedia System Vol 7(3): 175-183, Deng, D. (2004). Content-based Comparison of Image Collection via Distance Measuring of Self-organised maps image retrieval, Proceedings of IEEE MMM 2004, Brisbane, Australia, Deng, D,, I, Koprinska, et al. (1999). RICBIS: New Zealand Repository for intelligent Connectionist-Based Information Systems, Proceedings of ICONIP international workshop, Dunedin, New Zealand. Deng, D. and J. Zhang (2004), Visualisation and comparison of Image Collections based on Self-organization Maps, The Australasian Workshop on Data Mining and Web Intelligence, Dunedin, New Zealand, Deng, Y, and B. S. Manjunath (2001), "Unsupervised segmentation of colour-texture regions in images and video." IEEE trans on PAMI: 800-810, Deng, Y., B. S, Manjunath, et al, (2001). "An Efficient Colour Representation for Image Retrieval," IEEE trans on Image Processing 10(1): 140-147, Eakins, J. P, and M, E. Graham (1999), Content-based Image Retrieval, A report to the ESC Technology Applications Programme, Institute for Image Data Research, Northumbria University, Feng, H. and T.-S. Chua (2004). A Learnin g h for annotation Large On-Line Image Collection. Proc of the 10th International Conf on Multi-Media Modelling, Brisbane, Australia. Hamerly, G, and C. Elkan (2002). Alternatives to the k-means algorithm that find better clustering. Proceedings of the eleventh international conference on Information and knowledge management, McLean, Virginia, USA, Hand, D, J, (2003), Intelligent Data Analysis, Springer. Heesch, D, and S. Ruger (2004). K-NN networks for content-based image retrieval, Proceedings of the 26th European Conference on Information Retrieval, ECIR, Sunderland, UK. Huang, J,, S, R, Kumar, et al. (1997). "Image Indexing using colour correlograms." IEEE Computer Society Conference on CVPR: 762-768, Kittler, J,, M. Halef, et al, (1998), "On Combination Classifiers." IEEE Trans on PAMI Vol. 20(No. 3): 226-238. Kohonen, T,, J, Hynnien, et al, (1995). The Self-Organising Map Program Package (SOM_PAK), SOM Programming Team of the Helsinki University of Technology. Kovalev, V. and M, Petrou (1996). "Multimedimensional Co-occurrence Matrices for Object Recognition and Matching." Graphical Models and Image Processing 58(3): 187-197. Laaksonen, J., M, Koskela, et al, (2001), " Self-Organising Maps as a relevance feedback technique in content-based image retrieval." Pattern Analysis & Applications 4, No. 2-3: 140-152. Laaksonen, J., M. Koskela, et al, (2002). "PicSOM – self-organising image retrieval with MPEG-7 content descriptors," IEEE Transactions on Neural Networks: Special Issue on Intelligent Multimedia Processing 13(4): 841-853. Lampinen, J. (1992). On clustering properties of hierarchical self-organising maps, Artificial Neural Networks 2, North-Holland, Amsterdam, Netherlands, Li, J. and J. Z. Wang (2003), "Automatic Linguistic Indexing of Pictures by a Statistical Modelling Approach," IEEE Trans on PAMI 25(9): 1075-1088, Limpien, J, (1992), On Clustering properties of hierachical self-organizing maps. Artificial Neural Networks 2, North-Holland, Amsterdam, Netherlands. Luo, J. and A. Savakis (2001). Indoor vs. outdoor classification of consumer photographs using low-level and semantic features. Int. Conf. Image Proc. ICIP'01, Thessaloniki, Greece. Ma, W. Y. and B, S, Manjunath (1997). Edge Flow: A Framework of Boundary Detection and Image Segmentation, Proceedings of the IEEE International Conference on CVPR, Puetro, Rico, Manjunath, B, S., J.-R. Ohm, et al, (2001), "Colour and Texture Descriptors," IEEE Trans on Circuits and Systems for Video Technology 11(6): 703-715. Martines, J. M. (2003). MPEG-7 Overview V.9, ISO/IEC JTC1/SC29/WG11 N5525. J, M, Martines, Pattaya. MPEG-7 (2003). MPEG-7 eXperimentation Model (XM), Institute for Integrated Systems, MUNICH UNIVERSITY OF TECHNOLOGY, Germany, Narasimhalu, A, D, (1996), "Multimedia Database," Multimedia System 4: 226-249. Park, D. K., Y. S, Jeon, et al. (2000). Efficient Use of Local Ede histo gram ram Descriptor. Pro. ACM Workshop Standards, Interoperability, and Practice, Los Angeles, CA, Pecenovic, Z,, M. N. Do, et al. (2000), Integrated Browsing and Searching of Large Image Collections, Int, Conf. Visual Information Systems, Rauber, A. and D, Merki (1999). "The SOMLib Digital Library System." Ro, Y. M,, M. Kim, et al, (2001), "MPEG-7 Homogeneous Texture Descriptor," ETRI 23(2): 41-51. Smeulders, A, W, M., W, Marcel, et al, (2000). "Content-based Image Retrieval of the end of the early years." IEEE Trans on PAMI 22(12): 1349-1380. Smith, G. and E, Jordaan (2002), Improved SVM regression using mixtures of kernels. International Joint Conference on Neural Networks (IJCNN), Hawaii, USA, Smith, J, R. and S.-F. Chang (1996), Tools and Techniques for Colour Image Retrieval, IS&T/SPIE, San Jose, CA, Sonka, M., V. Hlavac, et al. (1998), Image Processing Analysis and Machine Vision, PWS Publishing. Soysal, M. and A. A. Alatan (2003). Combining MPEG-7 Based Visual Experts For Reaching Semantics. VLBV03, Madrid, Stricker, M, and M. Orengo (1995), "Similarity of Colour Images." SPIE, Szummer, M. and R. W. Picard (1998). Indoor-Outdoor Image Classification. Cambridge, MA, USA, M,I.T Media Laboratory, T.Kohonen (1997), Self-organizing maps, Springer-Verlag. Tax, D. M. J., M. v, Breukelen, et al. (2000). "Combinaing multiple classifiers by average or by multiplying?" Pattern Recognition 33: 1475-1485. Vesanto, J. (1999), "SOM-Based Data Visualisation Methods." Intelligent Data Analysis journal. Wang, J. Z., J. Li, et al. (2001), "SIMPLicity: Semantics-Sensitive Integrated Matching for Picture Libraries," IEEE Trans on PAMI 23(9): 947-963. Wang, L, and B, S. Manjunath (2003). A Semantic Representation for Image Retrieval, IEEE International Conference on ICIP, Barcelona Spain,en_NZ
 Find in your library

Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item is not available in full-text via OUR Archive.

If you would like to read this item, please apply for an inter-library loan from the University of Otago via your local library.

If you are the author of this item, please contact us if you wish to discuss making the full text publicly available.

This item appears in the following Collection(s)

Show simple item record