簡易檢索 / 詳目顯示

回結果列表
研究生： 曾文彥
Tseng, Wen-Yen
論文名稱： 以遊戲類型行動應用程式實現群眾物體標記
Crowdsourced Object-labeling Based on a Game-based Mobile Application
指導教授： 黃仁暐
Huang, Jen-Wei
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 電腦與通信工程研究所
Institute of Computer & Communication Engineering
論文出版年： 2017
畢業學年度： 105
語文別： 英文
論文頁數： 63
中文關鍵詞： 互動式系統 、物體標記 、資料蒐集
外文關鍵詞： interactive system, object labelling, data collection
相關次數： 點閱：146  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

    • 隨著網際網路的迅速發展，於網際網路上分享或儲存的多媒體資料也呈現爆炸性的成長，因此也帶動了聚焦於圖像檢索的相關研究。訓練一個圖像檢索的系統往往需要大量的已標記圖片資料，大部分的研究者選用公開的資料庫進行他們的實驗。然而，如此一來他們的實驗結果就受限於選用的資料庫大小與內容。在此研究中，我們藉由行動應用程式建構了一個開放給群眾的物體標記系統，這個系統藉由使用者的操作，收集某個特定物體在圖片中的位置資訊。並且，這個應用程式的設計是簡單並且容易上手的。對於收集的資料，我們也有效的篩選出較為正確的答案與能提供良好答案的使用者。實驗結果顯示我們的方法對於收集資料的正確性與使用者所花費的時間上都有良好的結果。此外，這個實驗也證實了藉由智慧型手機來收集圖片資訊的可行性。

    Unparalleled growth in the sharing of media via networks has prompted a great deal of research into issues pertaining to image retrieval. The training and verification of image retrieval systems requires a large number of labelled images with ground truth; however, most researchers employ public datasets for their experiments, the results are restricted by the size and content of the dataset. In this study, we developed a system based on a mobile phone App for the collection of information pertaining to the location of objects in images. The proposed system is simple and easy to use. Experiments demonstrate the excellent performance of the proposed system with regard to accuracy and response time. This study demonstrates the feasibility of collecting image information using mobile phones.

    中文摘要 i Abstract ii Acknowledgment iii Table of Contents iv List of Figures vi 1 Introduction 1 2 Related Works 4 2.1 Bottom-neck of Image Recommendation 4 2.2 Ideas of CAPTCHA and reCAPTCHA 4 2.3 Other Works for Public Labelling 6 2.4 Researchers of Interactive System 8 3 Locating Objects by Finger Swiping 10 3.1 Testing Process 10 3.2 Guidance Through the Testing Process 11 3.3 Design of the Interactive Test Panel 11 3.4 Gathering Information 15 3.5 Reliability of Tests on Unknown Images 16 3.6 Response Verification: Control Images 17 3.7 Maximizing Data Gathering 17 4 Evaluating Responses and Users 20 4.1 Selection Evaluation 20 4.2 Evaluate the User 20 5 Experiments 22 5.1 Experimental Setup 22 5.2 Experimental Performance on Various Conditions 28 5.2.1 Performance with Variations in Accuracy 28 5.2.2 Performance Under Various Error Thresholds 29 5.2.3 Performance Under Various Touch Time 30 5.2.4 Performance Under Various Retry Times 33 5.3 Improving the Performance by Filter Out Outliers 34 5.3.1 Definition of an Outlier 34 5.3.2 Performance Under Various Conditions and Without Outliers 35 5.3.3 Get Better Answers without Filtering 41 5.4 Confirming the Existence of an Object 41 5.5 Reliability of Users 42 5.6 Comparison with Other Works 43 5.7 Experiments of Measuring with the Bounding Box 44 5.7.1 Response Verification with the Bounding Box 44 5.7.2 Selection Evaluation with the Bounding Box 45 6 Conclusions and Future Works 59 References 60

    [1] Captcha forms – good or evil?, 2012. https://www.hallaminternet.com/captcha-forms-good-or-evil/.
    [2] Google now using recaptcha to decode street view addresses, 2012. https://cola.workxplay.net/what-is-google-recaptcha/.
    [3] The clipper library performs clipping, and off setting of both lines and polygons., 2014.http://www.angusj.com/delphi/clipper/documentation/Docs/Overview/_Body.htm.
    [4] I am not a robot: Google swaps text captchas for quivery mouse clicks, 2014. https://nakedsecurity.sophos.com/2014/12/05/i-am-not-a-robot-google-swaps-text-captchas-for-quivery-mouse-clicks/.
    [5] Customizing the look and feel of recaptcha, 2016. https://developers.google.com/recaptcha/old/docs/customization.
    [6] recaptcha – i’m not a robot, 2017. http://blog.rubyeffect.com/recaptcha-im-not-robot/.
    [7] H. Bannour and C. Hudelot. Hierarchical image annotation using semantic hierarchies. In Proceedings of the 21st ACM international conference on Information and knowledge management, pages 2431–2434. ACM, 2012.
    [8] K. Chellapilla, K. Larson, P. Simard, and M. Czerwinski. Designing human friendly human interaction proofs (hips). In Proceedings of the SIGCHI conference on Human factors in computing systems, pages 711–720. ACM, 2005.
    [9] K.-H. Chen, C.-R. Wu, Y.-L. Yang, J.-W. Huang, and T.-Y. Ho. Efficient building identification using structural and spatial information on mobile devices. In Multimedia and Expo Workshops (ICMEW), 2014 IEEE International Conference on, pages 1–5. IEEE, 2014.
    [10] R. Datta, D. Joshi, J. Li, and J. Z. Wang. Image retrieval: Ideas, influences, and trends of the new age. ACM Computing Surveys (CSUR), 40(2):5, 2008.
    [11] W. Eom, S. Lee, W. De Neve, and Y. M. Ro. Improving image tag recommendation using favorite image context. In 2011 18th IEEE International Conference on Image Processing, pages 2445–2448. IEEE, 2011.
    [12] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html.
    [13] Y. Gao, J. Peng, H. Luo, D. A. Keim, and J. Fan. An interactive approach for filtering out junk images from keyword-based google search results. IEEE transactions on Circuits and Systems for Video Technology, 19(12):1851–1865, 2009.
    [14] L. Huang, Y. Yang, Y. Deng, and Y. Yu. Densebox: Unifying landmark localization with end to end object detection. arXiv preprint arXiv:1509.04874, 2015.
    [15] T. Joachims. Optimizing search engines using clickthrough data. In Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, pages 133–142. ACM, 2002.
    [16] N. Lerthirunwong and I. Shimizu. Interactive metric learning system for similar image search using linear discriminant analysis. In The 1st IEEE Global Conference on Consumer Electronics 2012, pages 206–209. IEEE, 2012.
    [17] B. Li, W. Xiong, and W. Hu. Web horror image recognition based on context-aware multi-instance learning. In 2011 IEEE 11th International Conference on Data Mining, pages 1158–1163. IEEE, 2011.
    [18] D. Liu, X.-S. Hua, M. Wang, and H.-J. Zhang. Image retagging. In Proceedings of the 18th ACM international conference on Multimedia, pages 491–500. ACM, 2010.
    [19] X. Liu, X. Qian, D. Lu, X. Hou, and L. Wang. Personalized tag recommendation for flickr users. In 2014 IEEE International Conference on Multimedia and Expo (ICME), pages 1–6. IEEE, 2014.
    [20] Y. Liu and T. Mei. Optimizing visual search reranking via pairwise learning. IEEE Transactions on Multimedia, 13(2):280–291, 2011.
    [21] Y. Liu, T. Mei, and X.-S. Hua. Crowdreranking: exploring multiple search engines for visual search reranking. In Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval, pages 500–507. ACM, 2009.
    [22] Y. Liu, F. Wu, Y. Zhang, J. Shao, and Y. Zhuang. Tag clustering and refinement on semantic unity graph. In 2011 IEEE 11th International Conference on Data Mining, pages 417–426. IEEE, 2011.
    [23] J. Philbin, O. Chum, M. Isard, J. Sivic, and A. Zisserman. Object retrieval with large vocabularies and fast spatial matching. In 2007 IEEE Conference on Computer Vision and Pattern Recognition, pages 1–8. IEEE, 2007.
    [24] A. Rae, B. Sigurbj¨ornsson, and R. van Zwol. Improving tag recommendation using social networks. In Adaptivity, Personalization and Fusion of Heterogeneous Information, pages 92–99. LE CENTRE DE HAUTES ETUDES INTERNATIONALES D’INFORMATIQUE DOCUMENTAIRE, 2010.
    [25] B. C. Russell, A. Torralba, K. P. Murphy, and W. T. Freeman. Labelme: a database and web-based tool for image annotation. International journal of computer vision, 77(1-3):157–173, 2008.
    [26] J.-H. Su, C.-L. Chou, C.-Y. Lin, and V. S. Tseng. Effective semantic annotation by image-to-concept distribution model. IEEE Transactions on Multimedia, 13(3):530–538, 2011.
    [27] X. Tang, K. Liu, J. Cui, F. Wen, and X. Wang. Intentsearch: Capturing user intention for one-click internet image search. IEEE transactions on pattern analysis and machine intelligence, 34(7):1342–1353, 2012.
    [28] X. Tian, D. Tao, X.-S. Hua, and X. Wu. Active reranking for web image search. IEEE Transactions on Image Processing, 19(3):805–820, 2010.
    [29] X. Tian, L. Yang, J. Wang, X. Wu, and X.-S. Hua. Bayesian visual reranking. IEEE transactions on multimedia, 13(4):639–652, 2011.
    [30] J. R. Uijlings, K. E. van de Sande, T. Gevers, and A. W. Smeulders. Selective search for object recognition. International journal of computer vision, 104(2):154–171, 2013.
    [31] L. Von Ahn, M. Blum, N. J. Hopper, and J. Langford. Captcha: Using hard ai problems for security. In International Conference on the Theory and Applications of Cryptographic Techniques, pages 294–311. Springer, 2003.
    [32] L. Von Ahn, B. Maurer, C. McMillen, D. Abraham, and M. Blum. recaptcha: Human-based character recognition via web security measures. Science, 321(5895):1465–1468, 2008.
    [33] S. Wan, P. Jin, and L. Yue. An effective image retrieval technique based on color perception. In Image and Graphics (ICIG), 2011 Sixth International Conference on, pages 1017–1022. IEEE, 2011.
    [34] L. Yang and A. Hanjalic. Prototype-based image search reranking. IEEE Transactions on Multimedia, 14(3):871–882, 2012.
    [35] L. Yang and A. Hanjalic. Learning to rerank web images. IEEE MultiMedia, (2):13–21, 2013.
    [36] T. Yao, C.-W. Ngo, and T. Mei. Circular reranking for visual search. IEEE Transactions on Image Processing, 22(4):1644–1655, 2013.

    無法下載圖示 校內：2022-01-01公開
    校外：不公開
    電子論文尚未授權公開，紙本請查館藏目錄
    QR CODE