Abstract
Scene classification is an important task for computer vision, and Convolutional Neural Networks, a model of deep learning, is widely used for object classification. However, they rely on pooling and large fully connected layers to combine information from spatially disparate regions; these operations can throw away useful fine-grained information, and in natural scenes, there are many useless information which will increase computation cost. In this paper, mid-level discriminative patches are utilized to pre-process the full images. The proposed method which combines mid-level discriminative patches for preprocessing with CNN for feature extraction improved the efficiency of computation and are more suitable for classifying scenes. Firstly, full images are divided into discriminative parts. Then utilize these patches to go through CNN for feature extraction. Finally, a support vector machine will be used to classify the scenes. Experimental evaluations using MIT 67 indoor dataset performs well and proved that proposed method can be applied to scene classification.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dalal N, Triggs B (2015) Histograms of oriented gradients for human detection. In: CVPR
Lowe DG (2003) Distinctive image features from scale-invariant keypoints
Csurka G, Dance C, Fan L, Willamowski J, Bray C (2004) Visual categorization with bags of keypoints. In: ECCV workshop
Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: CVPR
Perronnin F, Sanchez J, Mensink T (2010) Improving the fisher kernel for large-scale image classification. In: ECCV
Pandey M, Lazebnik S (2011) Scene recognition and weakly supervised object localization with deformable part-based models. In: ICCV
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Gong Y, Wang L, Guo R, Lazebnik S (2014) Multi-scale orderless pooling of deep convo-lutional activation features. In: ECCV
Zhou B, Lapedriza A, Xiao J, Torralba A, Oliva A (2014) Learning deep features for scene recognition using places database. In: NIPS
Doersch C, Gupta A, Efros A (2013) Mid-level visual element discovery as discriminative mode seeking. In: NIPS
Dixit M, Chen S (2015) Scene classification with semantic fisher vectors. In: CVPR
Liu L, Shen C, van den Hengel A (2015) The treasure beneath convolutional layers: cross-convolutional-layer pooling for image classification. In: CVPR
He K, Zhang X, Ren S, Sun J (2014) Spatial pyramid pooling in deep convolutional net-works for visual recognition. In: ECCV
Dai J, He K, Sun J (2015) Convolutional feature masking for joint object and stuff segmentation. In: CVPR
Ciresan DC, Giusti A, Gambardella LM, Schmidhuber J (2012) Deep neural networks segment neuronal membranes in electron microscopy images. In: NIPS, pp 2852–2860
Farabet C, Couprie C, Najman L, LeCun Y (2013) Learning hierarchical features for scene labeling. IEEE transactions on pattern analysis and machine intelligence
Hariharan B, Arbelaez P, Girshick R, Malik J (2014) Simultaneous detection and segmentation. In: european conference on computer vision (ECCV)
Pinheiro PH (2014) Recurrent convolutional neural networks for scene labelling. In: ICML
Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y (2014) Overfeat: integrated recognition, localization and detection using convolutional networks. In: ICLR
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR
Shen W, Wang X, Wang Y (2015) DeepContour: a deep convolutional feature learned by positive-sharing loss for contour detection. In: CVPR
Uijlings JRR, Ferrari V (2015) Situational object boundary detection. In: CVPR
Albaradei S, Wang Y (2014) Learning mid-level features from object hierarchy for image classification. In: WACV
Zhao R, Ouyang W, Wang X (2014) Learning mid-level filters for person reidentification. In: IEEE conference on computer vision and pattern recognition
Singh S, Gupta A, Efros AA (2013) Representing videos using mid-level discriminative patches. In: CVPR
Boureau Y-L, Bach F, LeCun Y, Ponce J (2010) Learning mid-level features for recognition. In: CVPR
Quattoni A, Torralba A (2009) Recognizing indoor scenes. In: CVPR
Li L.-J, Su H, Fei-Fei L, Xing EP (2010) Object bank: a high-level image representation for scene classification and semantic feature sparsification. In: NIPS
Singh S, Gupta A, Efros AA (2012) Unsupervised discovery of mid-level discriminative patches. In: ECCV
Lin D, Lu C, Liao R, Jia J (2014) Learning important spatial pooling regions for scene classification. In: IEEE conference on computer vision and pattern recognition
Cheng G, Han J, Guo L, Liu T (2015) Learning coarse-to-fine sparselets for efficient object detection and scene classification. In: CVPR
Sivic J, Zisserman A (2003) Video Google: a text retrieval approach to object matching in videos. In: ICCV
Kim G, Torralba A (2009) Unsupervised detection of regions of interest using iterative link analysis. In: NIPS
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
Yang, F., Yang, J., Wang, Y., Zhang, G. (2017). A Novel Method for Scene Classification Feeding Mid-Level Image Patch to Convolutional Neural Networks. 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_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-38771-0_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-38769-7
Online ISBN: 978-3-319-38771-0
eBook Packages: EngineeringEngineering (R0)