Abstract
In the context of object and scene recognition, state-of-the-art performances are obtained with visual Bag-of-Words (BoW) models of mid-level representations computed from dense sampled local descriptors (e.g., Scale-Invariant Feature Transform (SIFT)). Several methods to combine low-level features and to set mid-level parameters have been evaluated recently for image classification. In this chapter, we study in detail the different components of the BoW model in the context of image classification. Particularly, we focus on the coding and pooling steps and investigate the impact of the main parameters of the BoW pipeline. We show that an adequate combination of several low (sampling rate, multiscale) and mid-level (codebook size, normalization) parameters is decisive to reach good performances. Based on this analysis, we propose a merging scheme that exploits the specificities of edge-based descriptors. Low and high contrast regions are pooled separately and combined to provide a powerful representation of images. We study the impact on classification performance of the contrast threshold that determines whether a SIFT descriptor corresponds to a low contrast region or a high contrast region. Successful experiments are provided on the Caltech-101 and Scene-15 datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
Chatfield et al. [8] report that their re-implementation of Zhou et al. [51] performs 6 % below the published results. From personal communication with the authors of Zhou et al. [51], the results reported in Chatfield et al. [8] are representative of the method performances, without including non trivial modifications not discussed in the chapter.
- 3.
In the provided source codes for evaluation, the sampling is sometimes set to lower values: e.g., \(6\) pixels in http://www.ifp.illinois.edu/~jyang29/ScSPM.htm for Liu et al. [31] or http://users.cecs.anu.edu.au/~lingqiao/ for Liu et al. [31]. Compared to the value of \(8\) pixels, the performances decrease of about 1–2 %, making some reported results in published papers over-estimated.
- 4.
Note that from personal communication with the authors, we discover that the performances of 74 % in Liu et al. [31] in the Caltech-101 dataset have been obtained with a wrong evaluation metric. The level of performances that can be obtained with the setup depicted in Liu et al. [31] is about 70 % (see Sect. 2.5). However, the conclusion regarding the relative performances of LSC with respect to sparse coding remains valid.
- 5.
Available on Svetlana Lazebnik’s professional homepage: http://www.cs.illinois.edu/homes/slazebni/.
- 6.
Example VLFEAT [44] http://www.vlfeat.org/.
References
Avila S, Thome N, Cord M, Valle E, de Araujo A (2011) Bossa: extended bow formalism for image classification. In: Proceedings of the IEEE international conference on image processing (ICIP)
Bach FR, Lanckriet GR, Jordan MI (2004) Multiple kernel learning, conic duality, and the SMO algorithm. In: Proceedings of the twenty-first international conference on machine learning (ICML)
Bay H, Ess A, Tuytelaars T, van Gool L (2008) SURF: speeded Up robust features. Comput Vis Image Underst (CVIU) 110(3):346–359
Benois-Pineau J, Bugeau A, Karaman S, Mégret R (2012) Spatial and multi-resolution context in visual indexing. In: Visual Indexing and Retrieval, pp 41–63
Boureau Y-L, Bach, F, LeCun Y, Ponce J (2010) Learning mid-level features for recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Boureau Y-L, Le Roux N, Bach F, Ponce J, LeCun Y (2011) Ask the locals: multi-way local pooling for image recognition. In: Proceedings of the IEEE international conference on computer vision (ICCV)
Boureau Y-L, Ponce J, LeCun Y (2010) A theoretical analysis of feature pooling in vision algorithms. In: Proceedings of the international conference on machine learning (ICML)
Chatfield K, Lempitsky V, Vedaldi A, Zisserman A (2011) The devil is in the details: an evaluation of recent feature encoding methods. In: Proceedings of the British machine vision conference (BMVC)
Coates A, Ng A (2011) The importance of encoding versus training with sparse coding and vector quantization. In: Proceedings of the 28th international conference on machine learning (ICML)
Cord M, Cunningham P (2008) Machine learning techniques for multimedia: case studies on organization and retrieval. Machine learning techniques for multimedia, cognitive technologies. Springer, Heidelberg
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Duchenne O, Joulin A, Ponce J (2011) A graph-matching kernel for object categorization. In: Proceedings of the IEEE international conference on computer vision (ICCV)
Everingham M, Zisserman A, Williams C, Van Gool L (2007) The PASCAL visual obiect classes challenge 2007 (VOC2007) results. Technical Report, Pascal Challenge
Fan RE, Chang KW, Hsieh CJ, Wang XR, Lin CJ (2008) LIBLINEAR: a library for large linear classification. J Mach Learn Res (JMLR) 9:1871–1874
de Avila Fontes SE, Thome N, Cord M, Valle E, de Albuquerque Arajo A (2013) Pooling in image representation: The visual codeword point of view. Comp Vis Image Underst 117(5):453–465
Fei-fei L (2005) A bayesian hierarchical model for learning natural scene categories. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Fei-Fei L, 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 the IEEE conference on computer vision and pattern recognition (CVPR) workshop on GMBV
Feng J, Ni B, Tian Q, Yan S (2011) Geometric \(\ell _p\)-norm feature pooling for image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Gehler P, Nowozin S (2009) On feature combination for multiclass object classification. In: Proceedings of the IEEE international conference on computer vision (ICCV)
van Gemert J, Veenman C, Smeulders A, Geusebroek JM (2010) Visual word ambiguity. IEEE Trans Pattern Anal Mach Intell (TPAMI) 32(7):1271–1283
Goh H, Thome N, Cord M, Lim J-H (2012) Unsupervised and supervised visual codes with restricted Boltzmann machines. In: Proceedings of the European conference on computer vision (ECCV)
González-Díaz I, Buso V, Benois-Pineau J, Bourmaud G, Megret R (2013) Modeling instrumental activities of daily livinf in egocentric vision as sequences of active objects and context for Alzheimer disease research. In: ACM multimedia workshop on multimedia information indexing and retrieval for healthcare
Grauman K, Darrell T (2005) The pyramid match kernel: discriminative classification with sets of image features. In: Proceedings of the IEEE international conference on computer vision (ICCV)
Harris S, Stephens M (1988) A combined corner and edge detector. In: Proceedings of the 4th Alvey vision conference, pp 147–151
Jégou H, Douze M, Schmid C, Pérez P (2010) Aggregating local descriptors into a compact image representation. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Karaman S, Benois-Pineau J, Mgret R, Bugeau A (2012) Multi-layer local graph words for object recognition. In: Proceedings of the international conference on multimedia modeling
Kavukcuoglu K, Sermanet P, Boureau Y-L, Gregor K, Mathieu M, LeCun Y (2010) Learning convolutional feature hierachies for visual recognition. In: Proceedings of advances in neural information processing systems (NIPS), pp 1090–1098
Krizhevsky A, Sutskever I, Hinton G (2012) Imagenet classification with deep convolutional neural networks. In: Proceedings of advances in neural information processing systems (NIPS), pp. 1106–1114
Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Liu L, Wang L, Liu X (2011) In defense of soft-assignment coding. In: Proceedings of the IEEE international conference on computer vision (ICCV)
Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis (IJCV) 60:91–110
Mikolajczyk K, Schmid C (2004) Scale and affine invariant interest point detectors. Int J Comput Vis (IJCV) 60(1):63–86
Mironica I, Uijlings J, Rostamzadeh N, Ionescu B, Sebe N (2013) Time matters! capturing variation in time in video using fisher kernels. In: Proceedings of the 21st ACM international conference on multimedia
Perronnin F, Dance CR (2007) Fisher kernels on visual vocabularies for image categorization. In: Proceedings of the IEEE Conference on computer vision and pattern recognition (CVPR)
Perronnin F, Sánchez J, Mensink T (2010) Improving the fisher kernel for large-scale image classification. In: Proceedings of the European conference on computer vision (ECCV)
Serre T, Wolf L, Bileschi S, Riesenhuber M, Poggio T (2007) Robust object recognition with cortex-like mechanisms. IEEE Trans Pattern Anal Mach Intell (TPAMI) 29:411–426
Sharma G, Jurie F, Schmid C (2012) Discriminative spatial saliency for image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Sivic J, Zisserman A (2003) Video google: a text retrieval approach to object matching in videos. In: Proceedings of the IEEE international conference on computer vision (ICCV)
Smith JR, Chang S-F (1997) VisualSEEk: a fully automated content-based image query system. In: Proceedings of the fourth ACM international conference on Multimedia, ACM, pp 87–98
Snoek C, Worring M, Hauptmann A (2006) Learning rich semantics from news video archives by style analysis. ACM Transa Multimedia Comput Commun Appl (TOMCCAP) 2(2):91–108
Thériault C, Thome N, Cord M (2013) Extended coding and pooling in the HMAX model. IEEE Trans Image Process 22(2):764–777
van de Sande KEA, Gevers T, Snoek CGM (2010) Evaluating color descriptors for object and scene recognition. IEEE Trans Pattern Anal Mach Intell (TPAMI) 32(9):1582–1596
Vedaldi A, Fulkerson B (2008) VLFeat: an open and portable library of computer vision algorithms. http://www.vlfeat.org/
Vedaldi A, Gulshan V, Varma M, Zisserman A (2009) Multiple kernels for object detection. In: Proceedings of the IEEE international conference on computer vision (ICCV)
Vedaldi A, Zisserman A (2011) Efficient additive kernels via explicit feature maps. IEEE Trans Pattern Anal Mach Intell (TPAMI) 34:480–492
Vig E, Dorr, M, Cox DD (2012) Space-variant descriptor sampling for action recognition based on saliency and eye movements. In: Proceedings of the European conference on computer vision (ECCV)
Wang J, Yang J, Yu K, Lv F, Huang T, Gong Y (2010) Locality-constrained linear coding for image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Yang J, Yu K, Gong Y, Huang T (2009) Linear spatial pyramid matching using sparse coding for image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Zhang H, Berg AC, Maire M, Malik J (2006) SVM-KNN: discriminative nearest neighbor classification for visual category recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Zhou X, Yu K, Zhang T, Huang TS (2010) Image classification using super-vector coding of local image descriptors. In: Proceedings of the european conference on computer vision (ECCV)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Law, M.T., Thome, N., Cord, M. (2014). Bag-of-Words Image Representation: Key Ideas and Further Insight. In: Ionescu, B., Benois-Pineau, J., Piatrik, T., Quénot, G. (eds) Fusion in Computer Vision. Advances in Computer Vision and Pattern Recognition. Springer, Cham. https://doi.org/10.1007/978-3-319-05696-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-05696-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-05695-1
Online ISBN: 978-3-319-05696-8
eBook Packages: Computer ScienceComputer Science (R0)