局部二值模式及韋伯描述子延伸演算法與彩色影像轉灰階影像處理

隨著科技時代的到來，電腦視覺被廣泛地應用在許多領域，例如，臉部辨識、物件偵測、影像檢索和監控系統。在影像處理中，特徵擷取是不可或缺的步驟之一，經由特徵擷取能夠從一群龐大的資料中，選擇出真實反映影像資訊的成分。我利用兩個演算法，分別為局部二值模式以及韋伯局部描述子，進行臉部辨識以及中國書法作家辨認的實驗。局部二值模式是利用空間灰階共生的方法，有效率地計算局部範圍內中心像素與周圍鄰近像素間的亮度關係，來形成一特徵灰階圖。韋伯局部描述子則是受到韋伯定理的啟發，定理指出個體對兩個重量（或聲、光等）之間的差異，須在這個差異達到可辨識的程度，即所謂的「恰好可分辨的差異度」(just noticeable difference, JND)，才能有所覺察，此演算法被認為是較符合人類感知的方法。除此之外，我修改了局部二值模式演算法中的缺點，並且結合傳統局部二值模式的方法與方向性的概念，形成一個更強大的描述子，稱為“程度方向差異局部二值描述子”。此外，過去研究大部份將局部二值模式的方法應用於灰階的影像中，我嘗試將此演算法應用於彩色影像上，也保留傳統局部二值模式演算法的精神，並加入色彩資訊，稱為“HSV色彩空間-局部二值模式”。我提出的方法顯示在彩色影像中，能夠擷取出更清楚的輪廓特徵。最後一部分，則是著重在彩色與灰階影像的轉換，我提出的演算法不僅能夠在灰階影像上保留原彩色影像中的輪廓，更能達到加強對比性的效果。

關鍵字

局部二值模式；韋伯描述子；方向及大小差異；臉部辨識；書法辨識；灰階影像辨識；深度影像辨識；彩色局部二值模式；彩色影像轉灰階影像處理；色彩對比

並列摘要

With the advent of the technological era, computer vision is used widely in many fields such as face recognition, object detection, image retrieval and surveillance systems. In image processing, feature extraction is an indispensable step, which can reflect the intrinsic content (information) from the images (data). I utilized Local Binary Pattern (LBP) and Weber Local Descriptor (WLD), these two powerful descriptors to do experiments including face recognition, and Chinese Calligraphy Recognition. LBP is a spatial gray-level dependence method (co-occurrence method) and can be computed efficiently by thresholding the neighborhood of each pixel with the center pixel value to form a gray-scale invariant pattern. Weber local descriptor was inspired by Weber’s Law and was deemed to base on the fact of human perception. Besides, I revised the disadvantage of Local Binary Pattern algorithm and made a combination of conventional LBP with direction information to form a robust descriptor named “Magnitude and Direction Difference Local Binary Descriptor”. Furthermore, Local Binary Pattern was used to apply to grayscale images. I attempted to make use of the descriptor on color images. I also revised the traditional method but preserving the spirit when dealing with color images, called “HSV-LBP”. My results show that the revised version can extract clear features than previous LBP on color images. Last, I put emphasis on the topic about converting color images to grayscale images and not only preserving contrast but enhancing contrast.

並列關鍵字

Local Binary Pattern ； Weber Local Descriptor ； Magnitude and direction difference ； Face Recognition ； Calligraphy Identification ； Grayscale images Classification ； Depth images Classification ； HSV-LBP ； Color Image to Grayscale Conversion ； Contrast Preserving

參考文獻

[3] T. Ahonen, A. Hadid, and M. Pietikainen. Face description with local binary patterns: Application to face recognition. IEEE Trans. Pattern Anal. Mach. Intell., 28(12):2037–2041, Dec. 2006.

[6] A. Aissaoui, J. Martinet, and C. Djeraba. Dlbp: A novel descriptor for depth image based face recognition. In 2014 IEEE International Conference on Image Processing (ICIP), pages 298–302, Oct 2014.

[10] M. Fairchild. Color Appearance Models. The Wiley-IS&T Series in Imaging Science and Technology. Wiley, 2005.

[13] S. Gupta, M. K. Markey, and A. C. Bovik. Texas 3d face recognition database. http://www.kasrl.org/jaffe.html.

[14] S. Gupta, M. K. Markey, and A. C. Bovik. Anthropometric 3d face recognition. International Journal of Computer Vision, 90(3):331–349, 2010.

國際替代計量

局部二值模式及韋伯描述子延伸演算法與彩色影像轉灰階影像處理

全文下載

主題瀏覽