Abstract
Image classifications the basis to solve visual tracking, image segmentation, scenes understanding and other complex visual tasks. Bag of words(Bow) model is initially applied in text classification area, introduced in image proceeding and recognition on account of its simple and effective. This paper follows the standard bag-of-words pipeline, but substitutes original SIFT descriptor with DSP-SIFT(domain-size pooling sift). Then, taking account of the truth that an DSP-SIFT was developed for gray images which limits its performance with regard to some colored objects, we present to add CN(color-name) descriptor to collect the color information to form visual words of image. The experimental results over fifteen scene categories and Caltech 101 datasets indicate that our method can achieve very promising performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Fei Fei L, Perona P (2004) A bayesian hierarchical model forlearning natural scene cate-gories. In Proceedings of IEEE CVPR
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis
Dosovitskiy A, Tobias J (2014) Unsupervised feature learning by augmenting single images. arXiv:1405.5769
Fischer P, Dosovitskiy A (2014) Thomas, Brox.: Descriptor matching with convolutional neural networks: a comparison to sift. arXiv:1405.5769
Dong J, Soatto S (2015) Domain-size pooling in local descriptors DSP-SIFT. In: Proceedings of IEEE CVPR
Van J, De Weijer Cordelia (2009) Schmid: learning color names for real-world applications. IEEE Trans Imag Process 18(7):1512–1523
Khan R, Van de Weijer J (2013) Damien muselet discriminative color descriptors. In: Proceedings of IEEE CVPR
Ke Y, Sukthankar R (2004) PCA-SIFT: A more distinctive representation for local image descriptors. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Bay H, Tuytelaars T (2008) Speeded Up Robust Features. In: Computer vision and image understanding (CVIU), vol 110, pp 346–359
Brown M, Lowe D (2002) Invariant features from interest point groups. BMVC
Mikolajczyk K, Schmid C (2005) A performance evaluation of local descriptors. IEEE Transactions on PAMI, vol 27 p 10
Alaa E, Hakim A, Farag AA (2006) CSIFT: A SIFT descriptor with color invariant characteristics. In: Proceedings of IEEE CVPR
Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of fe atures: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of IEEE CVPR. 2169C2178
Maji S, Dosovitskiy A, Malik J (2008) Classification using intersection kernel support vector machines is efficient. In: Proceedings of IEEE CVPR
Dong J, Karianakis N, Davis D (2014) Multi-view feature engineering and learning. In: Proceedings of IEEE CVPR
Vedaldi A, Fulkerson B (2010) Vlfeat: an open and portable library of computer vision algorithms. In: ACM multimedia
Dhillon IS, Mallela S, Kumar RV (2003) A divisive information-theoretic feature clustering algorithm for text classification. J Mach Learn Res
Vazquez E, Joost V, Weijer D (2011) Describing reflectances for color segmentation robust to shadows, highlights, and textures. In: IEEE Transactions on Pattern Analysis and Machine Intelligence
Feifei Li, Fergus R, Perona P (2004) Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: Proceedings of IEEE CVPR
Oliva A, Torralba A (2001) Modeling the shape of the scene: a holistic representation of the spatial envelope. Int J Comput Vis
Zhang C, Liu J, Tian Q (2011) Image classification by non-negative sparse coding, low-rank and sparse decomposition. In: Proceedings of IEEE CVPR
Gao J, Yang J, Li M (2015) A novel feature extraction method for scene recognition based on centered convolutional restricted boltzmann machines. arXiv:150607257
Acknowledgments
This work is partly supported by the National Natural Science Foundation of China under Grant no. 61201362, 61273282 and 81471770, Graduate students of science and technology fund under no. ykj-2004–11205.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing Switzerland
About this paper
Cite this paper
Zhang, G., Yang, J., Zhang, S., Yang, F. (2017). Image Classification Based on Modified BOW Model. In: Balas, V., Jain, L., Zhao, X. (eds) Information Technology and Intelligent Transportation Systems. Advances in Intelligent Systems and Computing, vol 455. Springer, Cham. https://doi.org/10.1007/978-3-319-38771-0_33
Download citation
DOI: https://doi.org/10.1007/978-3-319-38771-0_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-38769-7
Online ISBN: 978-3-319-38771-0
eBook Packages: EngineeringEngineering (R0)