研究生: |
陳青緯 Ching-Wei Chen |
---|---|
論文名稱: |
基於MapReduce分散式運算架構的室內場景辨識系統 An Indoor Scene Recognition System Using MapReduce |
指導教授: |
項天瑞
Tien-Ruey Hsiang |
口試委員: |
鄧惟中
Wei-Chung Teng 李育杰 Yuh-Jye Lee 鮑興國 Hsing-Kuo Pao |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 資訊工程系 Department of Computer Science and Information Engineering |
論文出版年: | 2015 |
畢業學年度: | 103 |
語文別: | 中文 |
論文頁數: | 53 |
中文關鍵詞: | MapReduce 、影像檢索 、雲端計算 |
外文關鍵詞: | MapReduce, image retrieval, cloud computing |
相關次數: | 點閱:292 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
近年來由於雲端運算的興起,使得一般使用者也可以簡單的擁有大量的運算資源。再加上手持移動裝置的普及,使得影像資料累積的十分快速並呈現爆炸性的成長,連帶的讓影像辨識也出現各種不同的應用方式。
本論文提出了以MapReduce 為架構的二階段場景辨識系統。由於以往單機環境的限制,使得有限的資料庫影像底下可能無法涵蓋較完整的室內環境,容易讓辨識的準確率下降。因此,本論文在這個問題上提出了採用MapReduce 的分散式比對方法,藉由涵蓋完整的室內環境影像提高準確率,而衍生出來的龐大計算量便可以藉由平行運算的方式來分攤。
我們的方法進一步考慮到運算負載平衡的問題,降低在分散式架構中,容易因為節點間的運算時間不同,而導致系統產生延遲的情形。根據測試結果,我們的方法相較於一般未考慮負載平衡的方式,在相同實驗環境下能多提升30% 以上的效率,說明了在分散式架構下進行負載平衡能確實的減少系統等待時間。實驗最後再針對系統的運算時間和系統的效能進行分析和評估,其結果可以供其他採用MapReduce 架構的實驗做為參考。
With the rise of cloud computing in recent years, general users can easily access a large amount of computational resources. Besides, the popularization of mobile devices result in fast-accumulating a huge mass of image data, and also broaden the applications of image recognition.
In this thesis, we propose a two-phased indoor scene recognition system using MapReduce. In single-machine environment, the indoor environment is not complete with the limited database images, and making the recognition rates decrease.Therefore, we propose a distributed matching method using MapReduce.This method not only increases the recognition rates with the complete coverage of indoor environment images, but also deals with the massive calculation by parallel computing.
Our method further includes the computing load balancing function. In a distributed architecture, we shorten the system latency by decreasing the difference of computation times between different nodes. Comparing with the previous studies,our method is 30% higher in execution efficiency under the same experimental environment.The results show that the load balancing module can be really effective to reduce total waiting time in the distributed architecture. Finally, the experiment analyses the system execution time and efficiency between the number of Mappers and data size, which can provide the hints for other MapReduce programming model applications.
[1] M. S. Lew, N. Sebe, C. Djeraba, and R. Jain, “Content-based multimedia information retrieval: State of the art and challenges,” ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), vol. 2, no. 1, pp. 1–19, feb 2006.
[2] P. Hiremath and J. Pujari, “Content based image retrieval using color, texture and shape features,” in International Conference on Advanced Computing and Communications., Dec 2007, pp. 780–784.
[3] A. Ganar, C. Gode, and S. Jambhulkar, “Enhancement of image retrieval by using colour, texture and shape features,” in International Conference on Electronic Systems, Signal Processing and Computing Technologies (ICESC), Jan 2014, pp. 251–255.
[4] Q. Zhao, J. Yang, J. Yang, and H. Liu, “Stone images retrieval based on color histogram,” in International Conference on Image Analysis and Signal., April 2009, pp. 157–161.
[5] J. Han and K.-K. Ma, “Fuzzy color histogram and its use in color image retrieval,” IEEE Transactions on Image Processing, vol. 11, no. 8, pp. 944–952, Aug 2002.
[6] A. Rao, R. Srihari, and Z. Zhang, “Spatial color histograms for content-based image retrieval,” in 11th IEEE International Conference on Tools with Artificial Intelligence., 1999, pp. 183–186.
[7] S. Brandt, J. Laaksonen, and E. Oja, “Statistical shape features in contentbased image retrieval,” in 15th International Conference on Pattern Recognition., vol. 2, 2000, pp. 1062–1065.
[8] J. Pujari, S. Pushpalatha, and P. Desai, “Content-based image retrieval using color and shape descriptors,” in International Conference on Signal and Image Processing (ICSIP), Dec 2010, pp. 239–242. 40
[9] R. Haralick, K. Shanmugam, and I. Dinstein, “Textural features for image
classification,” IEEE Transactions on Systems, Man and Cybernetics, vol. SMC-3, no. 6, pp. 610–621, Nov 1973.
[10] G. Preethi and V. Sornagopal, “MRI image classification using GLCM texture features,” in International Conference on Green Computing Communication and Electrical Engineering (ICGCCEE)., March 2014, pp. 1–6.
[11] D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, vol. 60, no. 2, pp. 91–110, Nov. 2004.
[12] J.-M. Morel and G. Yu, “ASIFT: A new framework for fully affine invariant image comparison,” SIAM Journal on Imaging Sciences, vol. 2, no. 2, pp. 438–469, 2009.
[13] J. Dean and S. Ghemawat, “MapReduce: simplified data processing on large clusters,” Communications of the ACM, vol. 51, no. 1, pp. 107–113, Jan. 2008.
[14] B. Furht and A. Escalante, Handbook of Cloud Computing, 1st ed. Springer Publishing Company, Incorporated, 2010.
[15] T. Gunarathne, T.-L. Wu, J. Qiu, and G. Fox, “MapReduce in the clouds for science,” in IEEE SecondInternational Conference on Cloud Computing Technology and Science (CloudCom), Nov 2010, pp. 565–572.
[16] J. Dean and S. Ghemawat, “MapReduce: a flexible data processing tool,” Communications of the ACM, vol. 53, no. 1, pp. 72–77, Jan. 2010.
[17] Apache Hadoop. [Online]. Available: http://hadoop.apache.org/
[18] Amazon ElasticMapReduce. [Online]. Available: http://aws.amazon.com/elasticmapreduce/
[19] Google App Engine. [Online]. Available: https://appengine.google.com/
[20] Microsoft Azure. [Online]. Available: http://azure.microsoft.com/en-us/
[21] S. Ghemawat, H. Gobioff, and S.-T. Leung, “The Google file system,” ACM SIGOPS Operating Systems Review, vol. 37, no. 5, pp. 29–43, Oct. 2003.41
[22] K. Shvachko, H. Kuang, S. Radia, and R. Chansler, “The Hadoop Distributed File System,” in IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST), ser. MSST ’10. Washington, DC, USA: IEEE Computer Society, 2010, pp. 1–10.
[23] Amazon Web Services. [Online]. Available: http://aws.amazon.com/
[24] HDInsight - Hadoop big data solution. [Online]. Available: http://azure.microsoft.com/en-us/services/hdinsight/
[25] Plotting the whole internet. [Online]. Available: http://www.isi.edu/ant/address/whole_internet/index.html
[26] W. Y. Arms, M. Calimlim, and L. Walle, “Escience in practice: Lessons from the cornell web lab,” D-Lib Magazine, vol. 15, no. 5/6, 2009.
[27] Z. Yang, S. Kamata, and A. Ahrary, “NIR: Content based image retrieval on cloud computing,” in IEEE International Conference on Intelligent Computing and Intelligent Systems., vol. 3, Nov 2009, pp. 556–559.
[28] J. Zhang, X. Liu, J. Luo, and B. Lang, “DIRS: Distributed image retrieval system based on mapreduce,” in 5th International Conference on Pervasive Computing and Applications ., 2010, pp. 93–98.
[29] C. Sweeney, L. Liu, S. Arietta, and J. Lawrence, “HIPI: a hadoop image processing interface for image-based mapreduce tasks,” 2011.
[30] S. Jai-Andaloussi, A. Elabdouli, A. Chaffai, N. Madrane, and A. Sekkaki, “Medical content based image retrieval by using the hadoop framework,” in 20th International Conference on Telecommunications., May 2013, pp. 1–5.
[31] H. Kocakulak and T. Temizel, “A hadoop solution for ballistic image analysis and recognition,” in International Conference on High Performance Computing and Simulation ., 2011, pp. 836–842.
[32] R. Grace, R. Manimegalai, and S. Kumar, “Medical image retrieval system in grid using hadoop framework,” in International Conference on Computational Science and Computational Intelligence., vol. 1, March 2014, pp. 144–148.42
[33] L. Stein, “The case for cloud computing in genome informatics,” Genome Biology, vol. 11, no. 5, p. 207, 2010.
[34] M. C. Schatz, “BlastReduce: high performance short read mapping with
MapReduce,” 2008.
[35] M. H. Almeer, “Cloud hadoop mapReduce for remote sensing image analysis,” Journal of Emerging Trends in Computing and Information Sciences, vol. 3, no. 4, pp. 637–644, 2012.
[36] Database Set I. [Online]. Available: https://goo.gl/OniC6U
[37] Database Set II. [Online]. Available: https://goo.gl/X2Clrw
[38] A. Pronobis and B. Caputo, “COLD: The CoSy localization database,” The International Journal of Robotics Research, vol. 28, no. 5, pp. 588–594, May
2009.
[39] Y. Liu, C. Li, B. Su, and H. Wang, “Evaluation of feature extraction methods for face recognition,” in Computational Intelligence and Design (ISCID), 2013 Sixth International Symposium on, vol. 2, Oct 2013, pp. 313–316.
[40] C. Le Brese and J. J. Zou, “Affine invariant matching based on orientation estimation,” in Signal Processing and Communication Systems (ICSPCS), 2013 7th International Conference on, Dec 2013, pp. 1–6.
[41] Query Image. [Online]. Available: https://goo.gl/J7RzV0