Scene Classification Using Cascaded Probabilistic Latent Semantic Analysis

Anahtar Kelimeler:

Sahne Sınıflandırılması, Uzaysal Piramit

Scene Classification Using Cascaded Probabilistic Latent Semantic Analysis

In this paper we propose a novel approach of image representation for weakly supervised scene classification that mainly combine two popular methods in the literature: Bag-of-Words (BoW) modeling and probabilistic Latent Semantic Analysis (pLSA) modeling. The new image representation scheme called Cascaded pLSA performs pLSA in a hierarchical sense after the BoW representation based on SIFT features is extracted. We associate location information with the conventional BoW/pLSA algorithm by subdividing each image into sub-regions iteratively at different resolution levels and implementing a pLSA model for each sub-region individually. Finally, an image is represented by concatenated topic distributions of each sub-region. The performance of our method is compared with the most successful methods in the literature using the same dataset. In the experiments, it has been seen that the proposed method outperforms the others in that particular dataset.sınıflandırması sağlayan ve literatürde son zamanlarda sıkça başvurulan Görsel Kelimeler Kümesi ve Olasılıksal Gizli Anlam Analizi yöntemlerinin birleştirildiği yeni bir yaklaşım önerilmektedir. Betimlemede Olasılıksal Gizli Anlam Analizi algoritmasının hiyerarşik bir yapıda imgeye uygulanmaktadır. SIFT özniteliklerine dayalı Görsel Kelimeler Kümesinin elde edilmesini müteakip, Olasılıksal Gizli Anlam Analizi modellemesinin piramit basamaklandırma şeklinde tüm alt bölgelere ayrı ayrı uygulanır. Tüm sevilerden elde edilen gizli tema dağılımı birleştirilerek imge betimlemesi gerçekleştirilir. Önerilen yöntemin performansı, aynı veri seti kullanılarak eşit şartlarda literatürde mevcut en başarılı diğer yöntemler ile karşılaştırılmış; ve önerilen yöntemin diğerlerinden daha iyi neticeler elde ettiği görülmüştür

Keywords:

-,

PDF

___

Fei-Fei L. and Perona P. “A Bayesian Hierarchical Model for Learning Natural Scene Categories,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 524-531, 2005. [2] Lazebnik S., Schmid C. and Ponce J. “Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition , vol. 2, pp. 2169-2178, 2006.
Sivic J., Russell B.C., Efros A., Zisserman A. and Freeman W. “Discovering Objects and Their Location in Images,” IEEE ICCV, vol. 1, pp. 370-377, 2005.
Oliva A. and Torralba A. “Modeling the Shape of the Scene: A Holistic Reprasentation of the Spatial Envelope,” Int’l J. Computer Vision, vol. 42, no. 3, pp. 145-175, 2001.
Vogel J. and Schiele B. “Semantic Modeling of Natural Scenes for Content-Based Image Retrieval,” Int’l J. Computer Vision, vol. 72, no. 2, pp. 133-157, 2007.
Deng J., Dong W., Socher R., Li L., Li K. and Fei-Fei L. “ImageNet: A Large-scale Hierarchical Image Database,” CVPR, http://www.image-net.org, 2009.
Vogel J. and Schiele B. “Natural Scene Retrieval Based on a Semantic Modeling Step,” Int’l Conf. Image and Video Retrieval, vol. 3155, 207-215, 2004.
Luo J., Singhal, A. and Zhu W. “Natural Object Detection in Outdoor Scenes Based on Probabilistic Spatial Context Models," Proc. IEEE Int’l. Conf. on Multimedia and Expo, 2003. [9] Boutell M., Choudhury A., Luo J. and Brown M.C. “Using Semantic Features for Scene Classification: How Good do They Need to Be?,” IEEE Int’l Conf. Multimedia and Expo, pp. 785-788, 2006.
Quelhas P., Monay F., Odobez J.M., Perez, D. and Tuytelaars, T. “A Thousand Words in a Scene," IEEE Trans. on pattern Analysis and Machine Intelligence, vol. 29, no. 9, 2007. [11] Hofmann T. “Probabilistic Latent Semantic Indexing,” Proc. SIGIR Conf. Research and Development in Information Retrieval, 1998.
Lowe D. “Distinctive Image Features from Scale Invariant Keypoints,” Int’l J. Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.
Bosch A., Zisserman A. and Munoz X. “Scene Classification Using a Hybrid Generative/Discriminative Approach,” IEEE Transections on Pattern Analysis and Machine Intelligence, vol. 30, no. 4, 2008.
Jiang J., Ngo C.W. and Yang J. “Towards Optimal Bag-of-Features for Object Categorization and Semantic Video Retrieval,” ACM Int’l Conf. Image and Video Retrieval (CIVR), 2007.
Mikolajczyk K. and Schmid C. “A Performance Evaluation of Local Descriptors,” IEEE Pattern Analysis and Machine Intelligence, vol. 27(10), pp. 1615-1630, 2005.
Hofmann T. “Unsupervised Learning by Probabilistic Latent Semantic Analysis,” Machine Learning, vol. 41, no. 2, pp. 177-196, 2001.
Dempster A.P., Laird N.M. and Rubin D.B. “Maximum Likelihood from Incomplete data via the EM Algorithm,” J. Royal Statist. Soc. B., vol. 39, pp. 1-38, 1977.
Rakotomamonjy A. “SVM and Kernel Methods Matlab Toolbox,” http://asi.insa- rouen.fr/enseignants/~arakotom/toolbox/index.html, 2008.