透過您的圖書館登入
IP:18.221.250.212
  • 學位論文

應用不受光照影響之局部二元圖形於影像比對

Illumination Invariant Local Binary Patterns for Image Matching

指導教授 : 黃惠藩
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


在大型影像資料庫中,若要準確地尋找一特徵影像,是需要花費相當大的時間,在影像比對系統中擁有高度的比對準確率與最少的比對時間是很重要的。目前大多數影像比對技術已經日漸成熟,但卻因資料庫中的影像資料受到光照的環境影響導致降低比對準確率。本文提出一不受光照影響的局部二元圖形運算應用於影像比對系統當中。局部二元圖形運算特色為使用一中心像素點與周圍像素點的局部變化所比較後的特徵值。為取代局部二元圖形運算及其應用在色彩影像中,我們實作局部二元圖形運算在每一個色彩影像的單一通道當中,基於雙色反射模型理論,提出了一個新的色彩紋路運算方法,此方法減少光照幾何、光照方向與光照顏色所影響。實驗結果顯示出使用新的色彩紋路運算方法於不同光照條件下的物件,物件影像特徵點更強健,不受光照影響而得到更好的影像比對正確率。

並列摘要


This paper presents an illumination invariant Local Binary Pattern (LBP) operator for image matching. LBP operator characterizes the local variation around a pixel by comparing the pixel value to the values of its neighboring pixels. Instead of applying LBP operator on the color component directly, our method performs the LBP operation on the color differences in each color channel. Based on the dichromatic reflection model, the proposed color texture operator is invariant with respect to lighting geometry, highlights, and illumination color. Experimental results show robust image matching using the new color texture operator on objects that are illuminated under different illumination conditions.

參考文獻


[2] T. Ahonen, A. Hadid, and M. Pietikäinen, "Face description with local binary patterns: application to face recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 12, pp. 2037-2041, 2006.
[5] J. Geusebroek, R. Boomgaard, A. Smeulders, and H. Geerts, "Color invariance," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 12, pp. 1338-1350, 2001.
[6] H. Ng, "Illumination and highlights invariant color model for image matching," The Imaging Science Journal, vol. 57, no. 3, pp. 167-173, 2009.
[8] D. He, L. Wang, and J. Guibert, "Texture discrimination based on an optimal utilization of texture features," Pattern Recognition, vol. 21, no. 2, pp. 141-146, 1988.
[11] 建昌 曾, "使用小波係數具抗旋轉性之顏色紋理影像檢索系統," 電機工程學系, 國立成功大學, 碩士論文 2001.

被引用紀錄


張志忠(2014)。氣囊式安全帶進氣導管之影像視覺特徵檢測〔碩士論文,國立虎尾科技大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0028-1308201400555200

延伸閱讀