Abstract
Representing local image patches is a key step in many applications of computer vision, while fast and effective description methods are always required by real-time image processing. Motivated by the fact that quantization compresses information while preserving primary structures, in this paper, we propose to use vector quantization (VQ) on local patch descriptor building. Compared to conventional approaches that compress floating-point features with VQ, we produce local integer descriptors very fast directly based on simple quantization methods. Experimental results on a publicly available dataset show that the present method is efficient both to build and to match. It achieves comparable performance to some typical floating-point and binary descriptors such as SIFT and BRIEF, offering a novel solution to fast local image representation except for bit test created in BRIEF.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Alahi, A., Ortiz, R., Vandergheynst, P.: FREAK: fast retina keypoint. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 510–517. IEEE (2012)
Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006). https://doi.org/10.1007/11744023_32
Bjornson, E., Ottersten, B.: Post-user-selection quantization and estimation of correlated frobenius and spectral channel norms. In: IEEE 19th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC 2008), pp. 1–6. IEEE (2008)
Calonder, M., Lepetit, V., Strecha, C., Fua, P.: BRIEF: binary robust independent elementary features. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 778–792. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15561-1_56
Chandrasekhar, V., Takacs, G., Chen, D.M., Tsai, S.S., Reznik, Y., Grzeszczuk, R., Girod, B.: Compressed histogram of gradients: a low-bitrate descriptor. Int. J. Comput. Vis. 96(3), 384–399 (2012)
Gionis, A., Indyk, P., Motwani, R., et al.: Similarity search in high dimensions via hashing. In: VLDB, vol. 99, pp. 518–529 (1999)
Harris, C., Stephens, M.: A combined corner and edge detector. In: Alvey Vision Conference, Manchester, UK, vol. 15, p. 50 (1988)
Hua, G., Brown, M., Winder, S.: Discriminant embedding for local image descriptors. In: IEEE 11th International Conference on Computer Vision (ICCV 2007), pp. 1–8. IEEE (2007)
Huang, Z., Kang, W., Wu, Q., Chen, X.: A new descriptor resistant to affine transformation and monotonic intensity change. Comput. Vis. Image Underst. 120, 117–125 (2014)
Leutenegger, S., Chli, M., Siegwart, R.Y.: BRISK: binary robust invariant scalable keypoints. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 2548–2555. IEEE (2011)
Lowe, D.G.: Object recognition from local scale-invariant features. In: The proceedings of the seventh IEEE International Conference on Computer Vision, vol. 2, pp. 1150–1157. IEEE (1999)
Mair, E., Hager, G.D., Burschka, D., Suppa, M., Hirzinger, G.: Adaptive and generic corner detection based on the accelerated segment test. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 183–196. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15552-9_14
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1615–1630 (2005)
Ni, Z.S.: B-SIFT: a binary sift based local image feature descriptor. In: 2012 Fourth International Conference on Digital Home, pp. 117–121. IEEE (2012)
Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. Int. J. Comput. Vis. 42(3), 145–175 (2001)
Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to SIFT or SURF. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 2564–2571. IEEE (2011)
Singh, M., Parameswaran, V., Ramesh, V.: Order consistent change detection via fast statistical significance testing. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008), pp. 1–8. IEEE (2008)
Tian, T., Sethi, I., Ming, D., Zhang, Y., Ma, J.: LIPID: local image permutation interval descriptor. In: 2013 12th International Conference on Machine Learning and Applications (ICMLA), vol. 2, pp. 513–518. IEEE (2013)
Torralba, A., Fergus, R., Weiss, Y.: Small codes and large image databases for recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008), pp. 1–8. IEEE (2008)
Tuytelaars, T., Schmid, C.: Vector quantizing feature space with a regular lattice. In: IEEE 11th International Conference on Computer Vision (ICCV 2007), pp. 1–8. IEEE (2007)
Wang, C., Duan, L.Y., Wang, Y., Gao, W.: PQ-WGLOH: a bit-rate scalable local feature descriptor. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 941–944. IEEE (2012)
Ziegler, A., Christiansen, E., Kriegman, D., Belongie, S.J.: Locally uniform comparison image descriptor. In: Advances in Neural Information Processing Systems, pp. 1–9 (2012)
Acknowledgement
This work is supported by the National Natural Science Foundation of China under Grant 61672474 and 41701417, the Fundamental Research Funds for the Central Universities - China University of Geosciences (Wuhan), the Provincial Natural Science Foundation of Hubei Province of China under Grant 2016CFB278 and 2015CFB400, the China Postdoctoral Science Foundation under Grant 2016M602390, and the Open Research Project of Hubei Key Laboratory of Intelligent Geo-Information Processing (KLIGIP1608).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Tian, T., Yang, F., Zheng, K., Yao, H., Gao, Q. (2018). A Fast Local Image Descriptor Based on Patch Quantization. In: Zu, Q., Hu, B. (eds) Human Centered Computing. HCC 2017. Lecture Notes in Computer Science(), vol 10745. Springer, Cham. https://doi.org/10.1007/978-3-319-74521-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-74521-3_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-74520-6
Online ISBN: 978-3-319-74521-3
eBook Packages: Computer ScienceComputer Science (R0)