Abstract
Recently, a variety of smart devices have been introduced for entertainment or industrial purposes, and there have been a lot of needs for image matching applications exploiting a large number of images stored in those smart devices. Boundary image matching identifies similar boundary images using their corresponding time-series, and supporting the rotation invariance is crucial to provide more intuitive matching results not only in conventional computing devices but also in smart devices such as smartphones, smart pads, and smart cameras. Computing the rotation-invariant distance between image time-series, however, is a very time-consuming process since it requires a lot of Euclidean distance computations for all possible rotations. We here note that, for smart devices, a very efficient mechanism of computing rotation-invariant distances is required. For this purpose, in this paper we use a novel notion of envelope-based lower bound proposed by Keogh et al. (VLDB J 18:611–630, 2009) to reduce the number of distance computations dramatically. With the help of Keogh et al.’s prior work (Keogh in Proceedings of the 28th International Conference on Very Large Data Bases, 406–417, 2002; Keogh et al. in VLDB J 18:611–630, 2009), we first explain how to construct a single envelope from a query sequence and how to obtain a lower bound of the rotation-invariant distance using the envelope. We then explain that the single envelope lower bound can reduce a number of distance computations. This single envelope approach, however, may cause bad performance since it may incur a larger lower bound due to considering all possible rotated sequences in a single envelope. To solve this problem, we present a concept of rotation interval, and using the concept of multiple envelopes proposed by Keogh et al. (VLDB J 18:611–630, 2009) with these rotation intervals, we then generalize the envelope-based lower bound by exploiting multiple envelopes rather than a single envelope. We also propose equi-width and envelope-minimization divisions as the method of determining rotation intervals in the multi-envelope approach. We further present an advanced multi-step matching algorithm that progressively prunes search spaces by dividing the rotation interval in half. Experimental results show that our envelope-based solutions outperform naive solutions by one to three orders of magnitude. We believe that this performance improvement makes our algorithms very suitable for smart devices.
Similar content being viewed by others
Notes
Besides the range query of Definition 2, the \(k\)-nearest neighbor (\(k\)-NN) query is also widely used. However, we can evaluate \(k\)-NN queries using range queries because we can regard the distances for current \(k\) candidates as the tolerances of range queries. Thus, in this paper we focus on the range query whose inputs are a query sequence and the tolerance.
The concept of multiple envelopes was originally proposed by Keogh et al. [19], and in this paper we used their concept with slight modification for rotation intervals.
In Sect. 7, we determine \(m\) through extensive experiments. Finding a theoretical optimal \(m\) is another challenging issue since it varies by types of boundary images and lengths of sequences, and we leave this issue as a further study.
In RI-MS, we compute all possible query envelopes in advance and maintain them in main memory of smart devices. Without loss of generality, let us assume that the sequence length \(n\) is \(2^n\). Then, in RI-MS, the number of envelopes will be \((2^k - 1)\,(= 2^0 + 2^1 + \cdots + 2^{k-1})\). That is, the number of all envelopes becomes \((n-1)\), and if \(n < 2^k\), the number will be less than \((n-1)\). For each envelope, we maintain two sequences \(U\) and \(L\), each of which consists of \(n\) entries. Thus, we need to maintain total \(2n^2\) entries (=\(n\) envelopes \(\times \) \(2n\) entries) for a query sequence. For example, if the sequence length is \(360\) and each entry requires four bytes, we then require 1,036,800 bytes to store all the envelopes, which is \(<\)1 MB and is small enough to be maintained in main memory, even for smart devices with limited memory space. Therefore, we maintain all possible envelopes in main memory through the pre-computation, which is negligible in the overall matching performance since the usual environment contains a huge number of data sequences to be compared.
WEB_DATA can be publicly downloaded at http://cs.kangwon.ac.kr/~ysmoon/zips/web-data.zip.
References
Abbasi, S., Mokhtarian, F., Kittler, J.: Search for similar shapes in the SQUID system: shape queries using image databases. http://www.ee.surrey.ac.uk/CVSSP/demos/css/demo.html (2005)
Agrawal, R., Faloutsos, C., Swami, A.: Efficient similarity search in sequence databases. In: Proceedings of the 4th International Conference on Foundations of Data Organization and Algorithms, pp. 69–84. Chicago, Oct 1993
Boas, P.V.E., Kaas, R., Zulstra, E.: Design and implementation of an efficient priority queue. Theory Comput. Syst. 10(1), 99–127 (1997)
Boulos, M., Wheeler, S., Tavares, C., Jones, R.: How smartphones are changing the face of mobile and participatory healthcare: an overview with examples from eGAALYX. BioMed. Eng. Online 10(1), 24–38 (2011)
Bu, Y., Chen, L., Fu, A.W.-C., Liu, D.: Efficient anomaly monitoring over moving object trajectory streams. In: Proceedings of the 15th International Conference on Knowledge Discovery and Data Mining, pp. 159–168. ACM SIGKDD, Paris, June 2009
Chan, K.-P., Fu, A.W.-C., Yu, C.T.: Haar wavelets for efficient similarity search of time-series: with and without time warping. IEEE Trans. Knowl. Data Eng. 15(3), 686–705 (2003)
Cho, H.: Distributed multidimensional clustering based on spatial correlation in wireless sensor networks. Int. J. Comput. Syst. Sci. Eng. 26(4), 275–283 (2011)
Choi, Y., Tak, Y., Rho, S., Hwang, E.: Skin feature extraction and processing model for statistical skin age estimation. Multimed. Tools Appl. 64(2), 227–247 (2013)
Do, M.N.: Wavelet-based texture retrieval using generalized Gaussian density and Kullback–Leibler distance. IEEE Trans. Image Process. 11(2), 146–158 (2002)
Esling, P., Agon, C.: Time-series data mining. ACM Comput. Surv. 45(1), 1–34 (2013). (article 12)
Faloutsos, C., Ranganathan, M., Manolopoulos, Y.: Fast subsequence matching in time-series databases. In: Proceedings of International Conference on Management of Data, pp. 419–429. ACM SIGMOD, Minneapolis, May 1994
Gao, X., Qiu, B., Shen, J.J., Ng, T.-T., Shi, Y.Q.: A smart phone image database for single image recapture detection. In: Proceedings of the 9th Internationall Workshop on Digital Watermarking, pp. 90–104. Seoul, Oct 2011
Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 2nd edn. Prentice Hall, New Jersey (2002)
Han, W.-S., Lee, J., Moon, Y.-S., Jiang, H.: Ranked subsequence matching in time-series databases. In: Proceedings of the 33rd Internationall Conference on Very Large Data Bases, Vienna, pp. 423–434, Sept 2007
Han, W.-S., Lee, J., Moon, Y.-S., Hwang, S.-W., Yu, H.: A new approach for processing ranked subsequence matching based on ranked union. In: Proceedings of International Conference on Management of Data. ACM SIGMOD, Athens, June 2011
Kashyap, S., Lee, M.L., Hsu, W.: Similar subsequence search in time series databases. In: Proceedings of the 22nd International Conference on Database and Expert Systems Applicaitons, Toulouse, pp. 232–246, Aug 2011
Kekre, H.B., Thepade, S.D., Chaturvedi, R.N.: Block based information hiding using Cosine, Hartley, Walsh and Haar wavelets. Int. J. Adv. Comput. Res. 3(1), 1–6 (2013)
Keogh, E.J.: Exact indexing of dynamic time warping. In: Proceedings of the 28th International Conference on Very Large Data Bases, Hong Kong, pp. 406–417, Aug 2002
Keogh, E.J., Wei, L., Xi, X., Vlachos, M., Lee, S.-H., Protopapas, P.: Supporting exact indexing of arbitrarily rotated shapes and periodic time series under Euclidean and Warping distance measures. VLDB J. 18(3), 611–630 (2009)
Kim, B.-S., Moon, Y.-S., Kim, J.: Noise control boundary image matching using time-series moving average transform. In: Proceedings of the 19th International Conference on Database and Expert Systems Applications, Turin, pp. 362–375, Sept 2008
Kim, S.-P., Moon, Y.-S., Hong, S.-K.: An envelope-based approach to rotation-invariant boundary image matching. In: Proceedings of the 13th International Conference on Data Warehousing and Knowledge Discovery, Toulouse, pp. 382–393, Aug 2011
Kim, M., Whang, K.-Y., Moon, Y.-S.: Horizontal reduction: instance-level dimensionality reduction for similarity search in large document databases. In: Proceedings of the 28th IEEE International Conference on Data Engineering, Washington DC, pp. 1061–1072, April 2012
Kong, F., Tan, J.: DietCam: automatic dietary assessment with mobile camera phones. Pervas. Mobile Comput. 8(1), 147–163 (2012)
Lee, A.J.T., Lin, C.-W., Lo, W.-H., Chen, C.-C., Chen, J.-X.: A novel filtration method in biological sequence databases. Pattern Recognit. Lett. 28(4), 447–458 (2007)
Lee, A.J.T., Wu, H.W., Lee, T.-Y., Liu, Y.-H., Chen, K.-T.: Mining closed patterns in multi-sequence time-series databases. Data Knowl. Eng. 68(10), 1071–1090 (2009)
Lee, S., Rho, S., Park, J.: Multimedia contents adaptation by modality conversion with user preference in wireless network. J. Netw. Comput. Appl. 37(1), 1–8 (2014)
Lim, H.-S., Whang, K.-Y., Moon, Y.-S.: Similar sequence matching supporting variable-length and variable-tolerance continuous queries on time-series data stream. Inf. Sci. 178(6), 1461–1478 (2008)
Lin, C.-H., Lin, W.-C.: Image retrieval system based on adaptive color histogram and texture features. Comput. J. 54(7), 1136–1147 (2011)
Loh, W.-K., Park, Y.-H., Yoon, Y.-I.: Fast recognition of asian characters based on database methodologies. In: Proceedings of the 24th British National Conference on Databases, Glasgow, pp. 37–48, July 2007
Loh, W.-K., Moon, Y.-S., Srivastava, J.: Distortion-free predictive streaming time-series matching. Inf. Sci. 180(8), 1458–1476 (2010)
Moon, Y.-S., Whang, K.-Y., Han, W.-S.: General match: a subsequence matching method in time-series databases based on generalized windows. In: Proceedings of International Conference on Management of Data, pp. 382–393. ACM SIGMOD, Madison, June 2002
Moon, Y.-S., Kim, J.: Efficient moving average transform-based subsequence matching algorithms in time-series databases. Inf. Sci. 177(23), 5415–5431 (2007)
Moon, Y.-S., Kim, H.-S., Kim, S.-P., Bertino, E.: Publishing time-series data under preservation of privacy and distance orders. In: Proceedings of the 21th International Conference on Database and Expert Systems Application, Bilbao, pp. 17–31, Sept 2010
Moon, Y.-S., Kim, B.-S., Kim, M.S., Whang, K.-Y.: Scaling-invariant boundary image matching using time-series matching techniques. Data Knowl. Eng. 69(10), 1022–1042 (2010)
Nam, Y., Rho, S., Park, J.: Inference topology of distributed camera networks with multiple cameras. Multimed. Tools Appl. 67(1), 289–309 (2013)
Peng, P., Shou, L., Chen, K., Chen, G., Wu, S.: The knowing camera, recognizing places-of-interest in smartphone photos. In: Proceedings of the 36th International Conference on Research and Development in Information Retrieval, Dublin, pp. 969–972, July 2013
Pratt, W.K.: Digital Image Processing, 4th edn. Eastman Kodak Company, Rochester (2007)
Rasheed, F., Al-Shalalfa, M., Alhajj, R.: Efficient periodicity mining in time series databases using suffix trees. IEEE Trans. Knowl. Data Eng. 23(1), 79–94 (2011)
Scully, C.G., et al.: Physiological parameter monitoring from optical recordings with a mobile phone. IEEE Trans. Biomed. Eng. 59(2), 303–306 (2012)
Theoharatos, C.: A generic scheme for color image retrieval based on the multivariate Wald–Wolfowitz test. IEEE Trans. Knowl. Data Eng. 17(6), 808–819 (2005)
Vlachos, M., Vagena, Z., Yu, P.S., Athitsos, V.: Rotation invariant indexing of shapes and line drawings. In: Proceedings of ACM Conference on Information and Knowledge Management, Bremen, pp. 131–138, Oct 2005
Wang, Z., Chi, Z., Feng, D., Wang, Q.: Leaf image retrieval with shape features. In: Proceedings of the 4th International Conference on Advances in Visual Information Systems, Lyon, pp. 477–487, Nov 2000
Yang, X., Bai, X., Koknar-Tezel, S., Latecki, L.J.: Densifying distance spaces for shape and image retrieval. J. Math. Imaging Vis. 46(1), 12–28 (2013)
You, J., Park, S., Kim, I.: An efficient frequent melody indexing method to improve the performance of query-by-humming systems. J. Inf. Sci. 34(6), 777–798 (2008)
Zhang, D.Z., Lu, G.: Review of shape representation and description techniques. Pattern Recognit. 37(1), 1–19 (2003)
Zhou, H., Wang, R., Wang, C.: A novel extended local-binary-pattern operator for texture analysis. Inf. Sci. 178(22), 4314–4325 (2008)
Acknowledgments
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MEST) (NRF-2011-0013235).
Author information
Authors and Affiliations
Corresponding author
Additional information
The preliminary version of this paper was published in Proc. of the 13th Int’l Conf. on Data Warehousing and Knowledge Discovery (DaWaK 2011), Toulouse, France, pp. 382–393, Aug 2011, and its Korean version was published in The KIPS Transactions: Part D, Vol. 18-D, No. 1, pp. 9–22, Feb 2011.
Rights and permissions
About this article
Cite this article
Loh, WK., Kim, SP., Hong, SK. et al. Envelope-based boundary image matching for smart devices under arbitrary rotations. Multimedia Systems 21, 29–47 (2015). https://doi.org/10.1007/s00530-014-0386-9
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00530-014-0386-9