透過您的圖書館登入
IP:18.219.189.247
  • 學位論文

一個結合資訊檢索與影像辨識技術的行動商品評鑑平台

A Mobile Merchandise Evaluation Platform Based-On Novel Information Retrieval and Image Recognition Technology

指導教授 : 羅濟群

摘要


近年來,隨著社會經濟的發展與成長,消費者的購買行為在近幾年發生了顯著的變化,這種變化主要表現為消費者的衝動購買(Impulse Buying)急速上升。由於網際網路的普及與便利性,國人利用網路搜尋商品評價或評論的需求越來越多,未來對於商品比價資訊與推薦的應用也將隨著行動網路的擴展而更為重要。本研究有鑑於商品評鑑與行動服務的需要,提出一套有效的決策支援系統(Decision Support System, DSS)-行動式商品評鑑平台(Mobile Merchandise Evaluation Platform, MMEP),包含即時商品辨識子系統(Real-time Merchandise Identification Subsystem, RMIS)、商品評論建議子系統(Merchandise Evaluation Subsystem, MES)、以及商品比價推薦子系統(Merchandise Recommendation Subsystem, MRS)以提供即時之商品評鑑服務相關商品資訊的推薦。其中,即時商品辨識子系統(RMIS)利用區塊相鄰圖(Region Adjacency Graph, RAG)和自我組織映射圖網路(Self-Organizing Maps, SOM)學習各個商品影像特徵,並有效進行分類,影像辨識正確率可達81.25%。商品評論建議子系統(MES)結合多文件自動摘要技術(Multiple Document Summarization, MDS)和化妝品評論詞彙本體論(Merchandise Comment Term Ontology, MCTO),取得商品評論摘要,並經領域專家評論摘要語句比對後,正確率可達78%,以幫助使用者於短時間判斷及取得重要購買決策參考資訊。

並列摘要


Consumers’ purchasing behavior has obviously changed in recent years with developments in social economics. This change has been evident in the decreased ratio of planned purchases but not in the increase of planned (or spontaneous) purchases. This act of spontaneous or otherwise unplanned purchasing is called “impulse buying”. However, buying under these conditions costs more money always comes with negative responses, such as complaints and regret. Therefore, we propose and have designed a new Merchandise Recommendation Subsystem, the Mobile Merchandise Evaluation Platform (MMEP). This is a three-tier system composed of Real-time Merchandise Identification Subsystem (RMIS), Merchandise Evaluation Subsystem (MES), and Merchandise Recommendation Subsystem (MRS). With this system, Mobile Users (MUs) take pictures of merchandise and send them to MMEP, RMIS integrates Region Adjacency Graph (RAG) and Self-Organizing Maps (SOM) to gather information on the merchandise through those photographs. MES and MRS provide Intelligence Agents (IAs) and Multiple-Document Summarization (MDS) to summarize recommendations on merchandise for MUs, all in real time.

參考文獻


[7] Y. L. Huang, J. P. Lee, G. L. Chen, Z. Z. Lee, M. P. Chang, X. J. Huang, “Image Retrieval by Using Region Adjacency Relations”, Tunghai Science, Vol. 6, pp. 17-41, 2004.
[20] H. C. Wang, C. T. Liu, T. H. Huang, “A Concept-Level Ontology Construction Method for Automatic Summarization”, Journal of Internet Technology, Vol. 8, No. 4, pp. 381-387, 2007.
[26] 陳志華,「一個無所不在的情境感知式健康照護系統之設計與實作」,國立交通大學資訊管理研究所,碩士論文,2009。
[4] J. Han and M. Kamber, “Data mining: concepts and techniques, second edition”, Morgan Kaufmann Publishers, 2005.
[5] K. Haris, S. Efstratiadis, N. Maglaveras, and A. Katsaggelos, “Hybrid image segmentation using watersheds and fast region merging”, IEEE Transactions on Image Process. Vol. 7, No. 12, pp. 1684-1699, 1998.

延伸閱讀