基於空間關係之色彩分析與紋理特徵的影像查詢技術

Image retrieval based on texture features and color analysis of spatial relationship

楊惠紋(Hui-Wen Yang)

指導教授 ： 吳憲珠

國立臺中科技大學/資訊與流通學院/資訊工程系碩士班/碩士(2014年)

https://doi.org/10.6826/NUTC.2014.00026

摘要

針對影像查詢技術而言，如何精確並迅速地在影像資料庫中取得欲查詢的影像一直是極為重要的研究主題。本碩士論文提出的方法主要針對影像進行全域性的特徵擷取，利用影像中相鄰像素的紋理和顏色特徵搜尋影像資料庫中的相似影像。本文方法將彩色影像經過色彩分析轉換並量化處理後，再利用各像素點與其0度和90度之鄰居像素點進行空間位置關係的運算，分別取得紋理特徵和顏色特徵並建立影像特徵直方圖。接著利用查詢影像和資料庫影像的特徵直方圖進行比對其相似度，藉此以達到最佳效率的影像查詢。經由實驗結果顯示，本研究結果相較以往的查詢技術微結構描述子技術(MSD)而言，具有較佳的查詢效果。

關鍵字

色彩分析 ； 紋理特徵 ； 相鄰空間關係 ； 微結構描述子

並列摘要

For image query technology, how to accurately and quickly achieve inquiring image in the image database is always a very important research topic. This thesis presented an image retrieval method by focusing on the image global feature extraction. With the texture and color characteristics of the adjacent pixels, we could search for similar images in the image database. In the proposed method, color images were converted and quantified according to color analysis, and an image histogram was built with texture and color features which were calculated using spatial relationship calculations for each pixel with its neighboring 0 and 90 degree pixels. Then the histograms of query image and database image were compared for similarity. Thereby the best search efficiency for the query image was achieved. The experiment results showed that the proposed technique compared to the previous query technology micro-structure descriptor (MSD) has better query results.

並列關鍵字

Texture feature ； micro-structure descriptor (MSD) ； color analysis ； spatial relationship

參考文獻

[1] A. W. M. Smeulders, M. Worring, S. Santini, A. Gupta, and R. Jain, “Content-based image retrieval at the end of the early years,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 12, pp. 1349–1380, 2000.

[2] M. Kokare, B. N. Chatterji, and P. K. Biswas, “A survey on current content based image retrieval methods,” IETE Journal of Research, vol. 48, no. 3–4, pp. 261–271, 2002.

[3] S. Liao, M.W. K. Law, and A. C. S. Chung, “Dominant local binary patterns for texture classification,” IEEE Transactions on Image Processing, vol. 18, no. 5, pp. 1107–1118, 2009.

[4] Y. Liu, D. Zhang, G. Lu, and W.-Y. Ma, “A survey of content-based image retrieval with high-level semantics,” Pattern Recognition, vol. 40, no. 1, pp. 262–282, 2007.

[5] Y. Rui, T. S. Huang and S. F. Chang “Image retrieval: Current techniques, promising directions, and open issues,” Journal of Visual Communication and Image Representation, vol. 10, no. 4, pp. 39–62, 1999.