Abstract
In this paper, we present a fast local feature extraction method, which is our contribution to ongoing MPEG standardization of compact descriptor for visual search (CDVS). To reduce time complexity of feature extraction, two-stage feature selection, which is based on the feature selection method of CDVS Test Model (TM), and partial gradient computation are introduced. The proposed method is examined on SIFT and compared to SIFT and SURF extractor with the previous feature selection method. In addition, the proposed method is compared to various feature extraction methods of the current CDVS TMĀ 11 in CDVS evaluation framework. Experimental results show that the proposed method significantly reduces the time complexity while maintaining the matching and retrieval performance of previous work. For its efficiency, the proposed method has been integrated into CDVS TM since \(107^{\text {th}}\) MPEG meeting. This method will be also useful for feature extraction on mobile devices, where the use of computational resource is limited.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
This figure was reproduced by the author with the permission of G. Francini et al.Ā [7] using the program and dataset which they provided during the MPEG meetings. Note that this figure is not just taken fromĀ [7], the larger datasetsĀ [4, 8, 17, 18] were used to obtain the results compared to that ofĀ [7].
References
Balestri, M., Francini, G., LepsĆøy, S., Lee, K.D., Na, S.I., Lee, S.J.: CDVS: ETRI and TIās response to CE1 - an invariant low memory implementation of the ALP detector with a simplified usage interface. In: 107th MPEG Meeting, M31987 (2014)
Ballocca, G., Mosca, A., Fiandrotti, A., Mattelliano, M.: CDVS: TM10 extraction evaluation on ARM architectures. In: 109th MPEG Meeting, M34086 (2014)
Bay, H., Ess, A., Tuytelaars, T., Van, G.L.: Speeded-up robust features (SURF). Comput. Vis. Image Underst. 110, 346ā359 (2008)
California Institute of Technology: Pasadena Buildings 2010 dataset. http://www.vision.caltech.edu/archive.html (accessed 2014)
Chen, J., Duan, L.Y., Huang, T., Gao, W., Kot, A.C., Balestri, M., Francini, G., LepsĆøy, S.: CDVS CE1: a low complexity detector ALP BFLoG. In: 108th MPEG Meeting, M33159 (2014)
Francini, G., Balestri, M., LepsĆøy, S.: CDVS: telecom Italiaās response to CE1 - interest point detection. In: 106th MPEG Meeting, M31369 (2013)
Francini, G., LepsĆøy, S., Balestri, M.: Selection of local features for visual search. Signal Process. Image Commun. 28, 311ā322 (2013)
Jegou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometric consistency for large scale image search. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 304ā317. Springer, Heidelberg (2008)
ISO/IEC JTC1/SC29/WG11: Evaluation framework for compact descriptors for visual search. In: 97th MPEG Meeting, N12202 (2011)
ISO/IEC JTC1/SC29/WG11: Study text of ISO/IEC DIS 15938ā13 compact descriptors for visual search. In: 109th MPEG Meeting, N14681 (2014)
ISO/IEC JTC1/SC29/WG11: Test Model 11: compact descriptors for visual search. In: 109th MPEG Meeting, N14682 (2014)
Lee, K.D., Na, S.I., Lee, S.J., Balestri, M., Francini, G., LepsĆøy, S.: CDVS: ETRI and TIās response to CE1 - a fast feature extraction based on ALP detector. In: 107th MPEG Meeting, M31991 (2014)
LepsĆøy, S., Francini, G., Cordara, G., de Gusmao, P.P.B.: Statistical modelling of outliers for fast visual search. In: IEEE International Conference on Multimedia and Expo (ICME), pp. 1ā6 (2011)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60, 91ā110 (2004)
Microsoft: Counters in Process performance object. http://msdn.microsoft.com/en-us/library/ms804621.aspx (accessed 2014)
OpenCV Library: http://opencv.org/ (accessed 2014)
Telecom Italia: 201 Books, InternetArchive and DistractorPairs dataset. http://pacific.tilab.com/ (accessed 2013)
University of Oxford: The Oxford Buildings Dataset. http://www.robots.ox.ac.uk/~vgg/data/oxbuildings/ (accessed 2014)
VLFeat Library. http://www.vlfeat.org/ (accessed 2014)
Acknowledgement
This work was supported by the ICT R& D program of MSIP/IITP. [2014(R2012030111), Development of The Smart Mobile Search Technology based on UVD(Unified Visual Descriptor)]
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Lee, K., Lee, S., Oh, WG. (2015). Accelerating Local Feature Extraction Using Two Stage Feature Selection and Partial Gradient Computation. In: Jawahar, C., Shan, S. (eds) Computer Vision - ACCV 2014 Workshops. ACCV 2014. Lecture Notes in Computer Science(), vol 9010. Springer, Cham. https://doi.org/10.1007/978-3-319-16634-6_27
Download citation
DOI: https://doi.org/10.1007/978-3-319-16634-6_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16633-9
Online ISBN: 978-3-319-16634-6
eBook Packages: Computer ScienceComputer Science (R0)