Abstract
Mobile systems such as PDAs and cell phones play an increasing role in handling visual contents such as images. Thousands of images can be stored in a mobile system with the advances in storage technology: this creates the need for better organization and retrieval of these images. Content Based Image Retrieval (CBIR) is a method to retrieve images based on their visual contents. In CBIR, images are compared by matching their numerical representations called features; CBIR is computation and memory intensive and consumes significant amounts of energy. This article examines energy conservation for CBIR on mobile systems. We present three improvements to save energy while performing the computation on the mobile system: selective loading, adaptive loading, and caching features in memory. Using these improvements adaptively reduces the features to be loaded into memory for each search. The reduction is achieved by estimating the difficulty of the search. If the images in the collection are dissimilar, fewer features are sufficient; less computation is performed and energy can be saved. We also consider the effect of consecutive user queries and show how features can be cached in memory to save energy. We implement a CBIR algorithm on an HP iPAQ hw6945 and show that these improvements can save energy and allow CBIR to scale up to 50,000 images on a mobile system. We further investigate if energy can be saved by migrating parts of the computation to a server, called computation offloading. We analyze the impact of the wireless bandwidth, server speed, number of indexed images, and the number of image queries on the energy consumption. Using our scheme, CBIR can be made energy efficient under all conditions.
- Ahmad, I. and Gabbouj, M. 2005. Compression and network effect on content-based image retrieval on java enabled mobile devices. In Proceedings of the Finnish Signal Processing Symposium. 35--38.Google Scholar
- Andrysiak, T. and Choras, M. 2005. Image retrieval based on hierarchical Gabor filters. Int. J. Appl. Math. Comput. Sci. 15, 4, 471--480.Google Scholar
- Balan, R. K., Satyanarayanan, M., Park, S., and Okoshi, T. 2003. Tactics-based remote execution for mobile computing. In Proceedings of the International Conference on Mobile Systems, Applications, and Services. 273--286. Google ScholarDigital Library
- Buford, J., Burg, B., Celebi, E., and Frankl, P. 2006. Sleeper: A power-conserving service discovery protocol. In Proceedings of the Annual International Conference on Mobile and Ubiquitous Systems Workshops. 1--9.Google Scholar
- Chen, D., Tsai, S., Chandrasekhar, V., Takacs, G., Singh, J., and Girod, B. 2009. Tree histogram coding for mobile image matching. In Proceedings of the Data Compression Conference. IEEE Computer Society, Washington, DC, 143--152. Google ScholarDigital Library
- Chen, G., Kang, B.-T., Kandemir, M., Vijaykrishnan, N., Irwin, M. J., and Chandramouli, R. 2004. Studying energy trade offs in offloading computation/compilation in java-enabled mobile devices. IEEE Trans. Parallel Distrib. Syst. 15, 9, 795--809. Google ScholarDigital Library
- Datta, R., Joshi, D., Li, J., and Wang, J. Z. 2008. Image retrieval: Ideas, influences, and trends of the new age. ACM Comput. Surv. 40, 2, 1--60. Google ScholarDigital Library
- Davidson, A., Anvik, J., and Nascimento, M. A. 2001. Parallel traversal of signature trees for fast CBIR. In Proceedings of the ACM Workshops on Multimedia: Multimedia Information Retrieval. 6--9. Google ScholarDigital Library
- Enser, P., Sandom, C., and Lewis, P. 2006. Surveying the reality of semantic image retrieval. In Visual Information and Information Systems. Springer, 177--188. Google ScholarDigital Library
- Forster, J. 2007. Reducing time and RAM requirements in content-based image retrieval using retrieval filtering. In Informatiktage. 143--146.Google Scholar
- French, J. C., Martin, W. N., and Watson, J. V. S. 2002. A qualitative examination of content-based image retrieval behavior using systematically modified test images. In Proceedings of the Midwest Symposium on Circuits and Systems. 655--658.Google Scholar
- Goldberger, J., Greenspan, H., and Dreyfuss, J. 2007. An optimal reduced representation of a moG with applications to medical image database classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1--6.Google Scholar
- Gunther, N. J. and Beretta, G. 2001. A benchmark for image retrieval using distributed systems over the Internet: BIRDS-I. In SPIE - Internet Imaging II. 252--267.Google Scholar
- Haruechaiyasak, C. and Damrongrat, C. 2010. Improving social tag-based image retrieval with CBIR technique. In The Role of Digital Libraries in a Time of Global Change. 212--215. Google ScholarDigital Library
- He, R., Liu, K., Xiong, N., and Zhu, Y. 2008. Garment image retrieval on the web with ubiquitous camera-phone. In Proceedings of the IEEE Asia-Pacific Services Computing Conference. 1584--1589. Google ScholarDigital Library
- Hong, Y.-J., Kumar, K., and Lu, Y.-H. 2009. Energy efficient content-based image retrieval for mobile systems. In Proceedings of the IEEE International Symposium on Circuits and Systems. 1673--1676.Google Scholar
- Jacobs, C. E., Finkelstein, A., and Salesin, D. H. 1995. Fast multiresolution image querying. In Proceedings of the International Conference on Computer Graphics and Interactive Techniques. 277--286. Google ScholarDigital Library
- Jia, M., Fan, X., Xie, X., Li, M., and Ma, W.-Y. 2006. Photo-to-Search: Using camera phones to inquire of the surrounding world. In Proceedings of the International Conference on Mobile Data Management. 46--51. Google ScholarDigital Library
- Kotoulas, L. and Andreadis, I. 2003. Colour histogram content-based image retrieval and hardware implementation. IEE Proc. Circ. Devices Syst. 150, 387--393.Google ScholarCross Ref
- Kumar, K. 2008. Energy conservation for content-based image retrieval on mobile devices. ECE Master’s thesis, Purdue University.Google Scholar
- Kumar, K. and Lu, Y. 2010. Cloud computing for mobile users: Can offloading computation save energy? Computer 43, 4, 51--56. Google ScholarDigital Library
- Kumar, K., Nimmagadda, Y., Hong, Y.-J., and Lu, Y.-H. 2008. Energy conservation by adaptive feature loading for mobile content-based image retrieval. In Proceedings of the International Symposium on Low Power Electronics and Design. 153--158. Google ScholarDigital Library
- Li, J. and Wang, J. 2003. Automatic linguistic indexing of pictures by a statistical modeling approach. IEEE Trans. Pattern Anal. Mach. Intel. 25, 9, 1075--1088. Google ScholarDigital Library
- Li, J., Wang, J., and Wiederhold, G. 2000. IRM: Integrated region matching for image retrieval. In Proceedings of the ACM International Conference on Multimedia. 147--156. Google ScholarDigital Library
- Li, Z., Wang, C., and Xu, R. 2001. Computation offloading to save energy on handheld Devices: A partition scheme. In Proceedings of the International Conference on Compilers, Architecture and Synthesis for Embedded Systems. 238--246. Google ScholarDigital Library
- Macii, A., Benini, L., and Poncino, M. 2002. Memory Design Techniques for Low Energy Embedded Systems. Kluwer Academic Publishers.Google Scholar
- Manjunath, B., Ohm, J., Vasudevan, V., and Yamada, A. 2002. Color and texture descriptors. IEEE Trans. Circ. Syst. Video Techn. 11, 6, 703--715. Google ScholarDigital Library
- Noda, M. and Sonobe, H. 2002. Cosmos: Convenient image retrieval system of flowers for mobile computing situations. In Proceedings of the International Conference on Information Systems and Databases. 25--30.Google Scholar
- Oliva, A. and Torralba, A. 2001. Modeling the shape of the scene: A holistic representation of the spatial envelope. Int. J. Comput. Vision 42, 3, 145--175. Google ScholarDigital Library
- Park, B., Lee, K., and Lee, S. 2008. Color-based image retrieval using perceptually modified Hausdorff distance. J. Image Video Process. 1--10. Google ScholarDigital Library
- Pavlidis, T. 2009. Why meaningful automatic tagging of images is very hard. In Proceedings of the International Conference on Multimedia and Expo. 1432--1435. Google ScholarDigital Library
- Prasad, B., Gupta, S., and Biswas, K. 2001. Color and shape index for region-based image retrieval. Visual Form 2001, 716--725. Google ScholarDigital Library
- Qian, G., Sural, S., Gu, Y., and Pramanik, S. 2004. Similarity between Euclidean and cosine angle distance for nearest neighbor queries. In Proceedings of the ACM Symposium on Applied Computing. 1232--1237. Google ScholarDigital Library
- Quig, B., Rosenberg, J., and Kolling, M. 2003. Supporting interactive invocation of remote services within an integrated programming environment. In Proceedings of the International Conference on Principles and Practice of Programming in Java. 195--200. Google ScholarDigital Library
- Robles, O., Bosque, J., Pastor, L., and Rodriguez, A. 2005. Performance analysis of a CBIR system on shared-memory systems and heterogeneous clusters. In Proceedings of the 7th International Workshop on Computer Architecture for Machine Perception. 309--314. Google ScholarDigital Library
- Rohs, M. and Gfeller, B. 2004. Using camera-equipped mobile phones for interacting with real-world objects. In Advances in Pervasive Computing. 265--271.Google Scholar
- Rong, P. and Pedram, M. 2003. Extending the lifetime of a network of battery-powered mobile devices by remote processing: A Markovian decision-based approach. In Proceedings of the Design Automation Conference. 906--911. Google ScholarDigital Library
- Rudinac, S., Zajic, G., Ucumlic, M., Rudinac, M., and Reljin, B. 2007. Comparison of CBIR systems with different number of feature vector components. In Proceedings of the 2nd International Workshop on Semantic Media Adaptation and Personalization, 199--204. Google ScholarDigital Library
- Sonobe, H., Takagi, S., and Yoshimoto, F. 2004. Mobile computing system for fish image retrieval. In Proceedings of the International Workshop on Advanced Image Technology. 33--37.Google Scholar
- Tian, Q., Sebe, N., Lew, M., Loupias, E., and Huang, T. 2001. Image retrieval using wavelet-based salient points. J. Electron. Imaging 10, 835--849.Google ScholarCross Ref
- Wang, C. and Li, Z. 2004a. A computation offloading scheme on handheld devices. J. Parallel Distrib. Comput. 64, 6, 740--746. Google ScholarDigital Library
- Wang, C. and Li, Z. 2004b. Parametric analysis for adaptive computation offloading. In Proceedings of the Conference on Programming Language Design and Implementation. 119--130. Google ScholarDigital Library
- Wolski, R., Gurun, S., Krintz, C., and Nurmi, D. 2008. Using bandwidth data to make computation offloading decisions. In Proceedings of the IEEE International Symposium on Parallel and Distributed Processing. 1--8.Google Scholar
- Wu, W. and Yang, J. 2008. Semi-supervised learning of object categories from paired local features. In Proceedings of the International Conference on Content-Based Image and Video Retrieval. 231--238. Google ScholarDigital Library
- Xian, C., Lu, Y.-H., and Li, Z. 2007. Adaptive computation offloading for energy conservation on battery-powered systems. In Proceedings of the International Conference on Parallel and Distributed Systems. 1--8. Google ScholarDigital Library
- Yang, J., Park, S., Seong, H., Byun, H., and Lim, Y. 2008a. A fast image retrieval system using index lookup table on mobile device. In Proceedings of the 19th International Conference on Pattern Recognition. 265--271.Google Scholar
- Yang, K., Qu, S., and Chen, H.-H. 2008b. On effective offloading services for resource-constrained mobile devices running heavier mobile internet applications. IEEE Commun. Mag. 46, 1, 56--63. Google ScholarDigital Library
- Yeh, T., Tollmar, K., and Darrell, T. 2004. Searching the Web with mobile images for location recognition. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 76--81. Google ScholarDigital Library
- Zhang, D. and Lu, G. 2003. Content-based shape retrieval using different shape descriptors: A comparative study. In Proceedings of the IEEE International Conference on Multimedia and Expo. 1139--1142.Google Scholar
- Zhang, H., Rahmani, R., Cholleti, S., and Goldman, S. 2006. Local image representations using pruned salient points with applications to CBIR. In Proceedings of the ACM International Conference on Multimedia. 287--296. Google ScholarDigital Library
- Zhu, C., Li, K., Lv, Q., Shang, L., and Dick, R. P. 2009. iScope: Personalized multi-modality image search for mobile devices. In Proceedings of the International Conference on Mobile Systems, Applications, and Services. 277--290. Google ScholarDigital Library
Index Terms
- Energy Conservation for Image Retrieval on Mobile Systems
Recommendations
Energy conservation by adaptive feature loading for mobile content-based image retrieval
ISLPED '08: Proceedings of the 2008 international symposium on Low Power Electronics & DesignWe present an adaptive loading scheme to save energy for content based image retrieval (CBIR) in a mobile system. In CBIR, images are represented and compared by high-dimensional vectors called features. Loading these features into memory and comparing ...
Tradeoff between energy savings and privacy protection in computation offloading
ISLPED '10: Proceedings of the 16th ACM/IEEE international symposium on Low power electronics and designOffloading can save energy on mobile systems for computation-intensive applications. The mobile systems send programs and data to grid-powered servers where computation is performed. Offloading, however, causes privacy concerns because sensitive data ...
Energy harvesting computation offloading game towards minimizing delay for mobile edge computing
AbstractMobile edge computing (MEC) has emerged for meeting the ever-increasing computation demands from mobile applications. Mobile users endowing with computation and energy harvesting (EH) capabilities, called EH devices, are desired in MEC ...
Highlights- An energy harvesting computation offloading game (EHCOG) for delay minimization in MEC is studied.
Comments