ABSTRACT
To enable automatic multi-level image annotation, we have addressed two inter-related important issues:(1)more effective framework for image content representation and feature extraction to characterize the middle-level semantics of image contents;(2)new framework for hierarchical probabilistic image concept reasoning and detection. To address the first issue salient objects are used as the semantic building blocks to characterize the middle-level semantics of image contents effectively while reducing the image analysis cost significantly. We have proposed three approaches to designing the detection functions for automatic salient object detection,and automatic function selection is also supported to find the "right "assumptions of the principal visual properties for the corresponding salient object classes. To address the second issue wehaveproposed a novel framework to incorporate the concept ontology to achieve hierarchical probabilistic image concept reasoning for multi-level image annotation. The concept ontology for a large-scale public image database called Label Me is semi-automatically derived from the available image labels by using WordNet The image concepts at the first level of the concept ontology are used to characterize the most specific semantics of image contents with the smallest variations, and their correspondences with the semantic building blocks (i.e.,salient objects)are well-de fined and can be modeled accurately by using Bayesian networks. In addition,the predictions of the appearances of the higher-level image concepts with large variations are adopted by the underlying concept ontology or by combining the available predictions of the appearances of their children concepts through hierarchical Bayesian networks.Our experiments on a large public dataset have shown that our framework for hierarchical probabilistic image concept reasoning is scalable to diverse image contents (i.e.,large amount of salient object classes)with large within-category variations.
- Y. Rui, T. S. Huang, and S.-F. Chang, "Image Retrieval:Current Techniques,Promising Directions and Open Issues", Journal of Visual Communication and Image Representation Vol.10, pp.39--62, 1999.Google ScholarDigital Library
- F. Monay, D. Gatica-Perez,"On image auto-annotation with latent space models", ACM Multimedia, pp.275--278, 2003. Google ScholarDigital Library
- A. W. M. Smeulders, M. Worring, S. Santini, A. Gupta and R. Jain,"Content-based image retrieval at the end of the early years", IEEE Trans. on PAMI vol. 22, pp.1349--1380, 2000. Google ScholarDigital Library
- R. Zhao, W. I. Grosky, "Negotiating the semantic gap: from feature maps to semantic landscapes", Pattern Recognition vol.35, no.3, pp.593--600, 2002.Google ScholarCross Ref
- X. He, W.-Y. Ma, O. King, M. Li and H. J. Zhang, "Learning and inferring a semantic space from user 's relevance feedback", ACM Multimedia,2002. Google ScholarDigital Library
- R. Lienhart and A. Hartmann," Classifying images on the web automatically", Journal of Electronic Imaging vol. 11, no.4, pp. 445--454, 2002.Google ScholarCross Ref
- C. Carson, S. Belongie, H. Greenspan, J. Malik, "Blobworld: Image segmentation using expectation-maximization and its application to image querying ", IEEE Trans. PAMI 2002. Google ScholarDigital Library
- Y. Gong," Advancing Content-Based Image Retrieval by Exploiting Image Color and Region Features ", Multimedia Systems vol.7, no.6, pp.449--457, 1999. Google ScholarDigital Library
- K. Vu, K. A. Hua, W. Tavanapong, "Image Retrieval Basedon Regions of Interest", IEEE Trans. TKDE vol.15, no.4, pp. 1045--1049, 2003. Google ScholarDigital Library
- J. Z. Wang, J. Li and G. Wiederhold, "SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture Libraries", IEEE Trans. on PAMI vol.23, no.9, pp. 947--963, 2001. Google ScholarDigital Library
- J. R. Smith and C.-S. Li,"Image classification and querying using composite region template ", Journal of CVIU 1999. Google ScholarDigital Library
- J. Fan, Y. Gao, H. Luo, "Multi-level annotation of natural scenes using dominant image components and semantic image concepts", ACM Multimedia, 2004. Google ScholarDigital Library
- A. B. Benitez, S.-F. Chang, "Image classi fication using multimedia knowledge networks", ICIP, pp.613--616, 2003.Google ScholarCross Ref
- A. B. Benitez, J. R. Smith, S.-F. Chang,"MediaNet: A multimedia information network for knowledge representation", SPIE, vol. 4210, 2000.Google Scholar
- S.-F. Chang, J. R. Smith, M. Beigi, A. B. Benitez, "Visual information retrieval from large distributed on-line repositories", Comm. of the ACM vol.40, no. 12, pp.63--71, 1997. Google ScholarDigital Library
- Y. A. Aslandogan, C. T. Yu, "Evaluating strategies and systems for content based indexing of person images on the Web", ACM Multimedia, 2000. Google ScholarDigital Library
- J. Huang, S. Kumar, R. Zabih, "An automatic hierarchical image classi fication scheme", ACM multimedia, 1998. Google ScholarDigital Library
- A. G. Hauptmann,"Towards a large scale concept ontology for broadcast video", CIVR, 2004.Google ScholarCross Ref
- A. Natsev, M. R. Naphade, J. R. Smith, "Semantic representation: search and mining of multimedia content", KDD, pp.641--646, 2004. Google ScholarDigital Library
- J. Li and J. Z. Wang,"Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach", IEEE Trans. on PAMI vol.25, no.9, pp. 1075--1088, 2003. Google ScholarDigital Library
- K. Barnard and D. Forsyth,"Learning the semantics of words and pictures", Proc. ICCV, pp.408--415, 2001.Google ScholarCross Ref
- N. Vasconcelos, "Image indexing with mixture hierarchies", IEEE CVPR, 2001.Google ScholarCross Ref
- J. Fan, H. Luo, Y. Gao, M.-S. Hacid, "Mining image databases on semantics via statistical learning", ACM SIGKDD, 2005. Google ScholarDigital Library
- F. Monay, D. Gatica-Perez, "PLSA-based image auto-annotation:constraining the latent space", ACM Multimedia, pp. 348--351, 2004. Google ScholarDigital Library
- N. Serrano, A. E. Savakis, J. Luo, "Improved scene classification using efficient low-level features and semantic cues ",Pattern Recognition vol.37, no.9, pp.1773--1784, 2004.Google ScholarCross Ref
- R. Jin, A. G. Hauptmann, "Using a probabilistic source model for comparing images", ICIP, pp.941--944, 2002.Google Scholar
- A. Vailaya, M. Figueiredo, A. K. Jain, H. J. Zhang, "Image classification for content-based indexing ", IEEE Trans. on Image Processing vol.10, pp. 117--130, 2001. Google ScholarDigital Library
- C. Fellbaum, WordNet: An Electronic Lexical Database MIT Press, 1998.Google Scholar
- D. Lowe,"Distinctive image features fromscale-invariant keypoints ", International Journal of Computer Vision 2004. Google ScholarDigital Library
- L. Fei-Fei, R. Fergus, P. Perona, "A Bayesian approach to unsupervised One-Shot learning of Object categories", IEEE ICCV, 2003. Google ScholarDigital Library
- M. Sanderson, B. Croft, "Deriving concept hierarchies from text ", ACM SIGIR, 1999. Google ScholarDigital Library
- D. J. Lawrie, B. Croft, "Generating hierarchical summaries for web searches", ACM SIGIR, 2003. Google ScholarDigital Library
- K. Toutanova, F. Chen, K. Popat, T. Hofmann, "Text Classification in a Hierarchical Mixture Model for Small Training Sets", ACM CIKM, 2001. Google ScholarDigital Library
- S. Dumais, H. Chen, "Hierarchical classification of Web content", ACM SIGIR, 2000. Google ScholarDigital Library
- D. Comaniciu, Peter Meer, "Mean Shift: A robust approach toward feature space analysis", IEEE Trans. on PAMI vol.24, no.5, 2002. Google ScholarDigital Library
- Y. Freund, R. E. Schapire, "Experiments with a new boosting algorithm", Proc. ICML, pp. 148--156, 1996.Google Scholar
- A. Torralba, K. Murphy, W. Freeman, "Sharing features: effcient boosting procedures for multiclass object detection", CVPR, 2004. Google ScholarDigital Library
- P. Viola, M. Jones, "Robust real-time face detection", Intl. J. ComputerVision vol. 57, no. 2, 2004. Google ScholarDigital Library
- J. C. Platt, "Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods", in Adavances in Large Margin Classifiers MIT Press, 1999.Google Scholar
- Y. Gao, J. Fan, "Semantic Image Classification with Hierarchical Feature Subset Selection", ACM SIGMM International Workshop on Multimedia Information Retrieval, November 10--11, 2005, Singapore. Google ScholarDigital Library
- Y. Gao, J. Fan, H. Luo, X. Xue, R. Jain, "Automatic image annotation by incorporating feature hierarchy and boosting to scale up SVM classi fiers", ACM Multimedia, 2006. Google ScholarDigital Library
- D. Heckerman, D. Geiger, D. Chickering, "Learning Bayesian networks: The combination of knowkedge and statistical data", Machine Learning vol.20, 1995. Google ScholarDigital Library
Index Terms
- Incorporating concept ontology to enable probabilistic concept reasoning for multi-level image annotation
Recommendations
High-level concept annotation using ontology and probabilistic inference
ICIMCS '09: Proceedings of the First International Conference on Internet Multimedia Computing and ServiceImage annotation is a significant step towards semantic based image retrieval. Ontology is a popular approach for semantic representation and has been intensively studied for multimedia analysis. However, relations among concepts are seldom used to ...
Automatic image annotation by using concept-sensitive salient objects for image content representation
SIGIR '04: Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrievalMulti-level annotation of images is a promising solution to enable more effective semantic image retrieval by using various keywords at different semantic levels. In this paper, we propose a multi-level approach to annotate the semantics of natural ...
New approach for hierarchical classifier training and multi-level image annotation
MMM'08: Proceedings of the 14th international conference on Advances in multimedia modelingIn this paper, we have proposed a novel algorithm to achieve automatic multi-level image annotation by incorporating concept ontology and multitask learning for hierarchical image classifier training. To achieve more reliable image classifier training ...
Comments