透過您的圖書館登入
IP:3.21.100.34
  • 學位論文

即時人臉偵測及辨識系統的開發

Development of Real Time Face Detection and Recognition System

指導教授 : 蔡孟伸

摘要


本論文所開發的系統由人臉偵測與人臉辨識所組成。人臉偵測常常作為人臉辨識的前置作業,其結果足以影響整個系統的效能。由於本系統是即時系統,所以快速、準確地定位出人臉區域是本文人臉偵測系統的主要目標。 當影像輸入時,辨識系統先根據色彩資訊自背景中分離出可能有人臉存在的區域,接著以形態學的方法在可能是人臉的區域中萃取出可能是臉部特徵的區塊,然後再以臉部特徵的色彩資訊以及眼睛與嘴唇的幾何關係定位出正確的人臉位置,最後再以Fisherface的方法進行辨認。

關鍵字

人臉偵測 人臉辨識

並列摘要


The system developed in this thesis consists of face detection and recognition sub-systems. Face detection usually serves as a pre-processor in face recognition systems. This process will affect the performance of the recognition system. Because the proposed system is a real time system, locating the face region rapidly and precisely is one of the main goals of this thesis. First, the recognition system separates the face candidates from the background by color information when image is acquired. The system identifies the eyes and lip candidates from face candidates by morphologic methods. Next, the system locates the real face region by color information and the geometrical relation of eyes and lips. Finally, the recognition process is performed by applying Fisherface algorithm.

並列關鍵字

Face Detection Face Recognition

參考文獻


pp. 696-706.
[5] Turk M., Pentland A, “Eigenfaces for Recognition,” Journal of Cognitive Neuroscience, 1991, pp.3:71-86.
[6] Baback Moghaddam, Alex Pentland, “Probabilistic Visual Learning for Object Representation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, VOL. 19, NO. 7, July 1997, pp. 696-710.
[7] Peter N. Belhumeur, Joao P. Hespanha, David J. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition Using Specific Linear Projection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, VOL. 19, NO. 7, July 1997, pp. 711-720.
[11] J. Birgitta Martinkauppi, Maricor N. Sorianob, Mika H. Laaksonenc, “Behavior of skin color under varying illumination seen by different cameras at different color spaces,” SPIE Machine Vision in Industrial Inspection IX, VOL. 4301, San Jose, California, USA, January 2001, pp.1-15.

被引用紀錄


Li, C. W. (2017). 一種防止ATM盜用的人臉面膜檢測機制 [master's thesis, Chung Yuan Christian University]. Airiti Library. https://doi.org/10.6840/cycu201700449
weng, M. K. (2015). 即時頭髮輔助之人臉辨識 [master's thesis, Chung Yuan Christian University]. Airiti Library. https://doi.org/10.6840/cycu201500611
陳泰宏(2007)。人臉偵測與辨識應用於電腦使用者眼睛保護之研究〔碩士論文,國立臺北科技大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0006-2808200714362500

延伸閱讀