Abstract
The automatic recognition of the contents of a scene is an important issue in the computer vision field. Though considerable progress has been made, the complexity of scenes remains an important challenge to computer vision research. Most of the previous scene recognition models are based on the so-called “bag of visual words” method, which uses some clustering method to quantize the numerous local region descriptors into a codebook. The size of the codebook and the selection of initial clustering center have great influence on the performance. Furthermore, the big size of the codebook has high computational cost and memory consumption. To overcome these drawbacks, we present an unsupervised natural scene recognition approach that is not based on the “bag of visual words” method. This approach works by creating multiple resolution images and partitioning them into sub-regions at different scales. The descriptors of all sub-regions in the same resolution image are directly concatenated for support vector machine (SVM) classifiers. To represent images more effectively, we present a new visual descriptor: weighted histograms of gradient orientation (WHGO). We evaluate our approach on three data sets: the 8 scene categories of Oliva et al., the 13 scene categories of Fei-Fei et al. and the 15 scene categories of Lazebnik et al. Experiments show that the WHGO descriptor outperforms the classical scale invariant feature transform (SIFT) descriptor in natural scene recognition, and our approach achieves good performances with respect to the state of the art methods.
Similar content being viewed by others
References
Torralba A. Contextual priming for object detection. International Journal of Computer Vision, 2003, 53(2): 169–191
Vogel J, Schiele B. Semantic modeling of natural scenes for content-based image retrieval. International Journal of Computer Vision, 2007, 72(2): 133–157
Kivinen J J, Sudderth E B, Jordan M I. Learning multi-scale representations of natural scenes using Dirichlet processes. In: Proceedings of the 11th International Conference on Computer Vision. 2007, 1–8
Liu J, Shah M. Scene modeling using co-clustering. In: Proceedings of the 11th International Conference on Computer Vision. 2007, 1–7
Rasiwasia N, Vasconcelos N. Scene classification with low-dimensional semantic spaces and weak supervision. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2008, 1–6
Smeulders A W, Worring M, Santini S, Gupta A, Jain R. Content-based image retrieval at the end of the early years. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(12): 1349–1380
Szummer M, Picard R. Indoor-outdoor image classification. In: Proceedings of IEEE International Workshop on Content-based Access of Image and Video Database. 1998, 42–51
Oliva A, Torralba A. Modeling the shape of the scene: a holistic representation of the spatial envelope. International Journal of Computer Vision, 2001, 42(3): 145–175
Mikolajczyk K, Schmid C. Scale and affine invariant interest point detectors. International Journal of Computer Vision, 2004, 60(1): 63–86
Lowe D. Distinctive image features from scale-invariant key-points. International Journal of Computer Vision, 2004, 60(2): 91–110
Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 2(4): 509–522
Lazebnik S, Schmid C, Ponce J. A Sparse texture representation using affine-invariant regions. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2003, 2: 319–324
Bosch A, Zisserman A, Munoz X. Scene classification via pLSA. In: Proceedings of the 9th European Conference on Computer Vision. 2006, 517–530
Bosch A, Zisserman A, Muñoz X. Scene classification using a hybrid generative/discriminative approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(4): 712–727
Fei-Fei L, Perona P. A Bayesian hierarchical model for learning natural scene categories. In: Proceedings of IEEE Computer Society International Conference on Computer Vision and Pattern Recognition. 2005, 2: 524–531
Lazebnik S, Schmid C, Ponce J. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of IEEE Computer Society International Conference on Computer Vision and Pattern Recognition. 2006, 2169–2178
Ulrich I, Nourbakhsh I R. Appearance-based place recognition for topological localization. In: Proceedings of IEEE International Conference on Robotics and Automation. 2006, 2: 1023–1029
Pronobis A, Caputo B, Jensfelt P. A discriminative approach to robust visual place recognition. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. 2006, 7
Mikolajczyk K, Schmid C. Performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615–1630
Chang C C, Lin C J. LIBSVM: a library for support vector machines, 2001. Software available at: http://www.csie.ntu.edu.tw/~cjlin/libsvm
Zhang J, Marszalek M, Lazebnik S, Schmid C. Local features and kernels for classification of texture and object categories: a comprehensive study. International Journal of Computer Vision, 2007, 73(2): 213–238
Gehler P, Nowozin S. On feature combination for multiclass object classification. In: Proceedings of IEEE 12th International Conference on Computer Vision. 2009, 221–228
Author information
Authors and Affiliations
Corresponding author
Additional information
Li ZHOU was born in Hunan, China, in 1982. He received the B.Sc. and M.Sc. degrees from Dalian Navy Academy, China, in 2004 and 2006, respectively. He is currently working toward the doctoral degree in the National University of Defense Technology. His research interests include computer/biological vision, visual navigation, and machine learning.
Dewen HU was born in Hunan, China, in 1963. He received the B.Sc. and M.Sc. degrees from Xi’an Jiaotong University, China, in 1983 and 1986, respectively. From 1986, he was with the National University of Defense Technology. From October 1995 to October 1996, he was a Visiting Scholar with the University of Sheffield, UK. He got his Ph.D degree from the National University of Defense Technology in 1999. He was promoted Professor in 1996. His research interests include image processing, system identification and control, neural networks, and cognitive science. He is an action editor of Neural Networks.
Zongtan ZHOU was born in Henan, China, in 1969. He received the B.Sc., M.Sc. and Ph.D degrees from the National University of Defense Technology, China, in 1990, 1994 and 1998, respectively. From February 2010 to February 2011, He was a Visiting Scholar with the Eberhard Karls Universitt Tübingen. He was promoted Professor in 2007. His research interests include image/signal processing, computer/biological vision, neural networks, cognitive neuroscience and brain-computer interface.
Zhaowen ZHUANG was born in Fujian, China, in 1958. He received the B.Sc. and M.Sc. degrees from the National University of Defense Technology, China, in 1981 and 1984, and the Ph.D degree from Beijing Institute of Technology at Beijing in 1989, respectively, both in electronic engineering. He worked in Purdue University as Senior Visiting Scholar to conduct radar signal processing in 1999. He is now a Professor in the National University of Defense Technology and performs research on radar target recognition, artificial intelligence and signal processing in satellite navigation.
About this article
Cite this article
Zhou, L., Hu, D., Zhou, Z. et al. Natural scene recognition using weighted histograms of gradient orientation descriptor. Front. Electr. Electron. Eng. China 6, 318–327 (2011). https://doi.org/10.1007/s11460-011-0140-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11460-011-0140-4