3D影像查詢系統

An Image Retrieval System for Three–Dimensional Image

林金樹(Chin-Shu Lin)

指導教授 ： 李朱慧

朝陽科技大學/資訊學院/資訊管理系/碩士(2013年)

摘要

隨著時代的進步， 電腦與網際網路已漸漸普及化，在網路上的使用者會將文字、圖片、照片以及各種多媒體資料上傳至各種網域空間或雲端儲存空間，使得多媒體數據資料庫及技術，必須隨著使用者的腳步不斷地更新及轉變。其中如何有效率地搜尋影像成為一個重要的議題，本文將聚焦在3D影像來做深入探討，將提出一個有效率的3D影像搜尋方式，並以經濟部智慧財產局的立體商標圖庫，作為實驗的分析的對象，其中，一個立體商標影像將使用多張2D影像來代表。本文利用Harris角點偵測並結合CPDH (contour points distribution histogram)形狀描述，以顏色直方圖方法提取顏色特徵，利用兩種特徵進行影像搜尋，並且在形狀特徵提取上運用抗旋轉的機制，能有效減少影像對於旋轉的敏感，以提高在檢索上的準確度。本研究不僅提出了一種全新的特徵提取方法，同時也提出一個新的類似度計算方式，預計在3D影像查詢系統中，可以得到不錯準確度。

關鍵字

3D影像查詢 ； 影像檢索

並列摘要

With the progress of the age, the popularization of the computer and the internet, the text, images, photographs and varieties of multimedia will be uploaded to groups of the network space or cloud storage space by users. Thus, the multimedia data and technology have to renew and transfer with the steps of the users constantly. How to search the images economically is a significant issue. This thesis will focus on 3D images to investigate in depth. It will propose an efficient 3D searching method. The analytical object is used by three-dimensional trademark gallery of the Intellectual Property Office of the Ministry of Economic Affairs, R.O.C.. One three-dimensional trademark image is expressed a set of 2D images. This thesis uses Harris Corner detection and combines CPDH (contour points distribution histogram) method to extract the shape feature and uses color histogram method to refine the color feature. Also, using the anti-rotation mechanism for the shape feature extraction can reduce the sensitive rotation to the image efficiently, so that it can enhance the accuracy of retrieval. This research does not only bring up a brand-new feature extraction method, but also propose a new calculation similarity measurement. The 3D image retrieval system can be predicted to achieve a good accuracy.

並列關鍵字

Three-dimensional image ； Image retrieval system

參考文獻

[37] D. C. SHI, L. XU and, U. Y. HAN(2007), “Image retrieval using both color and texture features” ,The Journal Of China Universities Of Posts and Telecommunications, Vol. 14, pp. 94 –99.

[1] T. Adamek and N. O''Connor(2004), “A Multiscale Representation Method for Nonrigid Shapes with a Single Closed Contour,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 14, No. 5, pp. 742-753.

[2] S. Abbasi, F. Mokhtarian, and J. Kittler(1999), “Curvature scale space image in shape similarity retrieval”, Springer Journal of MultiMedia Systems ,Vol.7, No. 6, pp. 467–476.

[3] M. Awrangjeb and G. Lu(2008), “An improved curvature scale-space corner detector and a robust corner matching approach for transformed image identification,” IEEE Transactions on Image Processing, Vol. 17, No. 12, pp. 2425–2441.

[4] S. Belongie, J. Malik, and J. Puzicha(2002), “Shape Matching and Object Recognition Using Shape Contexts,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 24, No. 4, pp. 705-522.