ABSTRACT
Feature representation plays a key role to the success of an image retrieval system. In this paper, a comparative study over the effectiveness of several features for content-based image search is presented. This study covers across several conventional features as well as convolutional neural networks (CNN) features, which are introduced recently into retrieval tasks. In particular, the evaluation is conducted when features are under the same encoding scheme. In addition, a hybrid feature representation that combines keypoint detector and CNN descriptor is proposed, in which the geometric invariances of keypoint feature and the distinctiveness of CNN feature are integrated. Experiments on popular evaluation benchmarks show that this hybrid feature achieves superior performance.
- A. Babenko, A. Slesarev, A. Chigorin, and V. Lempitsky. Neural codes for image retrieval. In ECCV, pages 584--599, Sep. 2014.Google ScholarCross Ref
- H. Bay, T. Tuytelaars, and L. V. Gool. SURF: Speeded up robust features. Computer Vision and Image Understanding, 110(3):346--359, 2008. Google ScholarDigital Library
- D. M. Chen, G. Baatz, and K. Koser. City-scale landmark identification on mobile devices. In CVPR, pages 737--744, 2011. Google ScholarDigital Library
- O. Chum, M. Perdoch, and J. Matas. Geometric min-hashing: Finding a (thick) needle in a haystack. In CVPR, pages 17--24, Jun. 2009.Google ScholarCross Ref
- Q. Danfeng, S. Gammeter, L. Bossard, T. Quack, and L. V. Gool. Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors. In CVPR, 2011. Google ScholarDigital Library
- J. Delhumeau, P.-H. Gosselin, H. Jégou, and P. Pérez. Revisiting the VLAD image representation. In ACM Multimedia, pages 653--656, 2013. Google ScholarDigital Library
- P. Fischer, A. Dosovitskiy, and T. Brox. Descriptor matching with convolutional neural networks: a comparison to SIFT. Eprint Arxiv, 2014.Google Scholar
- H. Jégou, M. Douze, and C. Schmid. Hamming embedding and weak geometric consistency for large scale image search. In ECCV, pages 304--317, Oct. 2008. Google ScholarDigital Library
- H. Jégou, M. Douze, and C. Schmid. Packing bag-of-features. In ICCV, pages 2357--2364, Sep. 2009.Google ScholarCross Ref
- H. Jégou, M. Douze, and C. Schmid. Product quantization for nearest neighbor search. Trans. PAMI, 33(1):117--128, Jan. 2011. Google ScholarDigital Library
- H. Jégou, M. Douze, C. Schmid, and P. Pérez. Aggregating local descriptors into a compact image representation. In CVPR, pages 3304--3311, Jun. 2010.Google ScholarCross Ref
- A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25(2):1097--1105, 2012. Google ScholarDigital Library
- J. Law-to, A. Joly, L. Joyeux, N. Boujemaa, O. Buisson, and V. Gouet-Brunet. Video and image copy detection demo. In CIVR, pages 97--100, 2007. Google ScholarDigital Library
- D. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 60(2):91--110, Nov. 2004. Google ScholarDigital Library
- E. Moxley, T. Mei, and B. S. Manjunath. Video annotation through search and graph reinforcement mining. IEEE Trans. on Multimedia, 12(3):183--193, Apr. 2010. Google ScholarDigital Library
- M. Paulin, M. Douze, Z. Harchaoui, and J. Mairal. Local convolutional features with unsupervised training for image retrieval. In ICCV, pages 91--99, 2015. Google ScholarDigital Library
- F. Perronnin and C. R. Dance. Fisher Kernels on visual vocabularies for image categorization. In CVPR, pages 1--8, Jun. 2007.Google ScholarCross Ref
- J. Philbin, O. Chum, M. Isard, J. Sivic, and A. Zisserman. Lost in quantization: Improving particular object retrieval in large scale image databases. In CVPR, pages 1--8, Jun. 2008.Google ScholarCross Ref
- A. S. Razavian, J. Sullivan, A. Maki, and S. Carlsson. Visual instance retrieval with deep convolutional networks. Cornell University Library, 2015. http://arxiv.org/abs/1412.6574.Google Scholar
- P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. Lecun. Overfeat: Integrated recognition, localization and detection using convolutional networks. Eprint Arxiv, 2013.Google Scholar
- J. Sivic and A. Zisserman. Video google: A text retrieval approach to object matching in videos. In ICCV, pages 1470--1477, 2003. Google ScholarDigital Library
- T. Tuytelaars and K. Mikolajczyk. Local Invariant Feature Detectors: A Survey. Now Publishers Inc., 2008. Google ScholarDigital Library
Index Terms
- A Comparative Study On Features for Similar Image Search
Recommendations
Image Retrieval Using Fused Deep Convolutional Features
This paper proposes an image retrieval using fused deep convolutional features to solve the semantic gap between low-level features and high-level semantic features of traditional contend-based image retrieval method. Firstly, the improved network ...
Rotation Invariant Curvelet Features for Region Based Image Retrieval
There have been much interest and a large amount of research on content based image retrieval (CBIR) in recent years due to the ever increasing number of digital images. Texture features play a key role in CBIR. Many texture features exist in literature,...
Deep convolutional features for image retrieval
Highlights- A comprehensive study that explores deep convolutional features for CBIR.
- The ...
AbstractNowadays, the use of Convolutional Neural Networks (CNNs) has led to tremendous achievements in several computer vision challenges. CNN-based image retrieval methods vary in complexity, growing capacity, and execution time. This work ...
Comments