請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/47682完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳銘憲 | |
| dc.contributor.author | Chien-Ray Kung | en |
| dc.contributor.author | 龔建瑞 | zh_TW |
| dc.date.accessioned | 2021-06-15T06:12:24Z | - |
| dc.date.available | 2013-08-17 | |
| dc.date.copyright | 2010-08-17 | |
| dc.date.issued | 2010 | |
| dc.date.submitted | 2010-08-12 | |
| dc.identifier.citation | [1] Nielson Company, “Trends in Online Shopping: A Global Nielson Consumer Report”, 2008.
[2] D. G. Lowe, “Distinctive image features from scale-invariant keypoints”, International Journal of Computer Vision, 60(2), pp. 91-110, 2004. [3] K. Mikolajczyk and C. Schmid, “A performance evaluation of local descriptors”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 257-263, 2003. [4] K. Mikolajczyk and C. Schmid, “A performance evaluation of local descriptors,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 27, no. 10, pp. 1615-1630, 2005. [5] J. S. Beis and D. G. Lowe, “Shape indexing using approximate nearest-neighbour search in high-dimensional spaces”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Puerto Rico, pp. 1000-1006, 1997 [6] J. Friedman, J. Bently, and R. Finkel, “An Algorithm for Finding Best Matches in Logarithmic Expected Time”, ACM Transactions on Mathematical Software, vol. 3, no. 3, pp. 209-226, 1977. [7] H. Bay, T. Tuytelaars, and L. Van Gool, “SURF: Speeded Up Robust Features,” in European Conference on Computer Vision, Graz, Austria, pp. 404-417, May 2006. [8] Demo Software: SIFT Keypoint Detector, http://www.cs.ubc.ca/~lowe/keypoints/ [9] J. Sivic, and A. Zisserman, “Efficient visual search of videos cast as text retrieval”, Pattern Analysis and Machine Intelligence, IEEE Transactions on , 2009. [10] J. Sivic and A. Zisserman, “Video Google: A text retrieval approach to object matching in videos”, In Proceedings of the International Conference on Computer Vision, 2, pp. 1470-1477, 2003. [11] D. Nister and H. Stewenius, “Scalable recognition with a vocabulary tree”, vol. 2, pp. 2161-2168, 2006. [12] G. J. Burghouts and J. M. Geusebroek, “Performance evaluation of local colour invariants”, Computer Vision and Image Understanding, vol. 113, pp. 48-62, 2009. [13] J. M. Geusebroek, R. van den Boomgaard, A. W. M. Smeulders, and H. Geerts, “Color invariance”, Intelligence, IEEE Transactions on, vol. 23, no. 12, pp. 1338-1350, 2001. [14] Color SIFT Tool , http://staff.science.uva.nl/~mark/downloads.html#colorsift. [15] Snap Tell, http://www.snaptell.com. [16] Google Goggles, http://www.google.com/mobile/goggles. [17] S. S. Tsai, D. Chen, J. P. Singh, and B. Girod, “Rate-efficient, real-time cd cover recognition on a camera-phone”, In MM '08: Proceeding of the 16th ACM international conference on Multimedia, New York, NY, USA, pp. 1023-1024, 2008. [18] D. N. Ta, W. C. Chen, N. Gelfand, and K. Pulli, “Surftrac: Efficient tracking and continuous object recognition using local feature descriptors”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2937-2944, June 2009. [19] Lloyd, Stuart P., “Least squares quantization in PCM”, IEEE Transactions on Information Theory vol. 28, no. 2, pp. 129-137, 1982. [20] H. Y. Chi, “UbiShop, Mobile Photo Search and Visually Similar Commodities Recommendation on Online Shopping Store”, National Taiwan University, 2010 [21] J. Canny, “A computational approach to edge detection”, Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 8, no.6, pp. 679-698, 1986. [22] Jianbo Shi and Jitendra Malik, “Normalized cuts and image segmentation”, Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 22, no. 8, pp. 888-905, 2000 | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/47682 | - |
| dc.description.abstract | 隨著多媒體分析與機器學習等技術日益地進展，藉由比對輸入影像與大量影像資料的特徵值而辨識出所拍攝之影像，並擷取相似影像及其相關資訊，已變得越來越可行。此外，由於智慧型手機的普及與行動通訊革新的迅速成長，人們漸漸可以透過行動裝置無所不在地從遠端伺服器取得想要的資訊。結合這兩種趨勢，我們提出一個線上購物商品影像搜尋系統UbiShop，讓使用者利用智慧型手機對感興趣商品拍照，並取得該商品更多的網路資訊。
本篇論文提出的階層式基於虛擬雜湊之描述子比對演算法(Hierarchical pseudo Hash-based Descriptors Matching)，解決過去區域描述子比對方法需耗費大量時間的問題。此演算法比傳統描述子比對方法大大地加速許多，而只損失些許精確度，於不同測試資料集所做的實驗皆達到優異的效能。此外，我們設計一個兩階層之排序機制；以階層式基於虛擬雜湊之描述子比對演算法保留前K 張最可能相符之影像，並運用傳統區域描述子比對準則，重新排序這些影像。將此機制運用於UbiShop 系統，不但能達到即時的搜尋效率，更兼顧了極佳的搜尋效能。 除此之外，我們也針對每張手錶影像，建立其相似圖片清單。當搜尋到目標手錶時，便能推薦使用者該手錶之其他款式相似的手錶。因此，我們提出基於特定物件之區域性顏色直方圖(Specific Object-based Regional Color Histogram)特徵值比對方法，分別於物件不同區域比較其顏色直方圖，再根據彼此特徵值相似度排序，為每張手錶建立相似圖片清單。 考量目前行動裝置運算與儲存能力的限制，我們設計一個主從式架構系統，將複雜的運算移往伺服器端，而只留下簡易的使用者互動介面於行動裝置。此概念讓大量影像及資訊儲存於伺服器，並使本系統在未來能延伸到更多商品種類。 | zh_TW |
| dc.description.abstract | As advancement of multimedia analysis and machine learning proceeds with each passing day, it becomes more possible to recognize captured images, and retrieve similar images and related information by comparing extracted features of query image with large numbers of images in datasets. In addition, thanks to popularity of smart phone and evolution of mobile telecommunication grow rapidly, people are gradually able to use mobile device to get desired information ubiquitously through transmission from remote servers. Combining these trends, we propose an online shopping commodity image search system, UbiShop, which makes users snap interesting commodities through smart phones and receives information about the commodities from the web.
In this thesis, to solve problem of previous local descriptors matching with high cost time, we propose Hierarchical pseudo Hash-based Descriptors Matching (H-pHDM) algorithm that greatly speeds up traditional descriptors matching with little accuracy loss. The experiments conducted on different testing datasets achieve great performance. Furthermore, to exploit to UbiShop system and concern about both retrieval time and accuracy, we design a two-level ranking mechanism that keeps top-K images which are most likely the matched images by H-pHDM algorithm, and re-ranks these images by conventional local descriptors matching criteria. Besides, we even construct similar images lists for watches datasets that recommend users other watches with similar visual style as target watch is retrieved. Hence, we propose Specific Object-based Regional Color Histogram (SORCH) feature matching approach that compares color histogram on different regions of objects respectively and ranks by similarities with other images to construct the lists. In addition, considering the limitation of computation power and capacity of current mobile devices, we design a client-server architecture system to put complex computation to server side, yet keep simple user interaction on mobile device. The notion lets large numbers of images and information be stored in the server and makes the system be extensible with more commodity categories in the future. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-15T06:12:24Z (GMT). No. of bitstreams: 1 ntu-99-R97921038-1.pdf: 2178435 bytes, checksum: 64461e68da1013db59322897013476c6 (MD5) Previous issue date: 2010 | en |
| dc.description.tableofcontents | 口試委員會審定書 #
Acknowledgements i 中文摘要 ii ABSTRACT iii CONTENTS iv LIST OF FIGURES vii LIST OF TABLES viii Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Problem Description and Proposed Solution 3 1.3 Contributions 5 1.4 Thesis Organization 6 Chapter 2 Preliminaries 7 2.1 Related Works 7 2.2 Scale-Invariant Feature Transform 8 2.3 K-means Clustering 9 2.4 Related Techniques 10 2.4.1 SIFT Keypoints Matching with Best-Bin-First Search algorithm 10 2.4.2 Object Retrieval with Bag-of-visual-words 11 Chapter 3 System Design and Implementation 13 3.1 Mobile Device as Client 14 3.2 Server Architecture 15 3.2.1 Prepared Image Datasets 15 3.2.2 Snapped Photo Retrieval Process 16 3.2.3 Constructed Similar Images Lists 18 3.3 Implementation Description 19 Chapter 4 Snapped Photo Retrieval 21 4.1 Selected Features 21 4.1.1 Scale-Invariant Feature Transform (SIFT) 21 4.1.2 C-colour SIFT 22 4.1.3 Bag-of-visual-words 23 4.2 pseudo Hash-based Descriptors Matching 24 4.2.1 Design Concept and Assumption 24 4.2.2 Training and Preparation 25 4.2.3 Query for Testing Images 26 4.3 Hierarchical pseudo Hash-based Descriptors Matching 29 4.3.1 Design Concept 29 4.3.2 Training and Preparation 29 4.3.3 Query for Testing Images 31 4.4 Techniques in Constructing Similar Images Lists 33 4.4.1 Specific Object-based Regional Color Histogram (SORCH) 34 4.4.2 SORCH Matching 34 Chapter 5 Experiment Results and Evaluation 35 5.1 Training and Testing Dataset Description 35 5.1.1 Training Dataset 35 5.1.2 Testing Dataset 37 5.2 Experiments on Retrieval Time 38 5.3 Experiments on Retrieval Performance 39 5.3.1 Measurement of Accuracy 40 5.3.2 Performance Comparison between H-pHDM and Baseline 40 5.3.3 Performance of H-pHDM on Different Mobile Devices 43 5.4 Evaluation between Local Descriptor Features 45 5.5 Experiment on Constructed Similar Images Lists 48 Chapter 6 Conclusions 50 REFERENCES 51 | |
| dc.language.iso | en | |
| dc.subject | 行動應用 | zh_TW |
| dc.subject | 影像檢索 | zh_TW |
| dc.subject | 多媒體資訊檢索 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | Multimedia Indexing | en |
| dc.subject | Mobile Application | en |
| dc.subject | Machine Learning | en |
| dc.subject | Image Retrieval | en |
| dc.title | UbiShop: 無所不在之線上商品影像搜尋系統 | zh_TW |
| dc.title | UbiShop: A Ubiquitous Image Search System for Online Shopping Commodity | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 98-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 呂俊賢,魏宏宇,楊德年,葉彌妍 | |
| dc.subject.keyword | 影像檢索,多媒體資訊檢索,機器學習,行動應用, | zh_TW |
| dc.subject.keyword | Image Retrieval,Multimedia Indexing,Machine Learning,Mobile Application, | en |
| dc.relation.page | 53 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2010-08-13 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-99-1.pdf 未授權公開取用 | 2.13 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。