三維人臉模型化與手勢辨識

近年來三維人臉辨識一直是重要的研究課題。因為二維的人臉辨識遭遇到很大的瓶頸，那就是它的辨識結果經常會受到不同拍攝角度和頭的姿勢所影響。相較之下，三維人臉辨識可以克服這個問題，所以它具有更高的辨識率。而處理三維的人臉辨識的第一步驟就是重建三維人臉模型。在電腦視覺及圖學領域中，產生一個仿真的三維人臉模型已經被廣泛運用。我們利用具有深度資訊的相機發展一個有紋理的三維人臉模型，此系統可以自動生成一個三維仿真的人臉模型，我們可以運用在它可以在很多領域，如三維人臉辨識、3D動畫、電腦遊戲和人機互動等。一般日常生活中，人與電腦的的溝通主要是依靠鍵盤及滑鼠，可是這些方法對人而言都不是自然的溝通方式。理想的方式是透過我們的身體語言來傳達，所以對於人機互動，手勢辨識就特別地有吸引力，因此我們提出基於計算投影直方圖的方法來自動辨識手勢。在這篇論文中，我們利用具有深度資訊的相機：SR-3000來取得深度資訊及灰階的二維影像，並運用這些資料來建立三維人臉模型及手勢辨識。此外我們還提出一個結合數位相機與SR-3000的方法，透過特殊的相機架設就可以很簡單地達成對位的效果，並且得到高解析度和彩色的資訊，最後利用這些資訊來建立三維人臉的彩色模型。

關鍵字

三維人臉模型；手勢辦識

並列摘要

3D face recognition is an important research topic nowadays. The performance of a face recognition system degrades incredibly due to the variation of facial appearance with different pose, which is well known as one of the bottlenecks in face recognition. Comparing to the bottleneck on 2D face recognition and face synthesis technique, 3D face model has better accuracy and performance than 2D face image on recognition and synthesis. And the first step of 3D face recognition is 3D face modeling. Generating realistic 3D human face models has been widely applied in computer vision and graphics. We have developed a system that constructs textured 3D face models from the depth camera. The system automatically generates a 3D human head model which can be used in many applications, such as 3D face recognition, 3D animation, video games, man-machine interface, and so on. Nowadays, the communication between man and machine is done mainly by the use of devices like keyboard and mouse, which are not natural for man-machine communication. The ideal manner of communication is body language. Hence, gesture recognition of the hand is an extremely attractive method for user-computer interaction. We propose an approach which is based on projective histogram to detect the number of fingers automatically. In this thesis, we use the range camera SR-3000 to acquire the depth information and intensity images. We apply these data to reconstruct 3D face model and recognize hand gestures.

並列關鍵字

3D Face Modeling ； Hand Gestures Recognition

參考文獻

[1] G. Yang and T. S. Huang, “Human Face Detection in a Complex Background’’, Pattern Recognition, Vol. 27, No.1, pp. 53-63, 1994

[3] K. Sung and T. Poggio, “Example-Based Learning for View-Based Human Face Detection’’, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 20, No. 1, pp. 39-51, 1998.

[4] H. A. Rowley, S. Baluja and T. Kanade, “Neural Network- Based Face Detection”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 20, No. 1, pp. 23-38, 1998.

[5] A. J. Colmenarez and T. S. Huang, “Face Detection With Information-Based Maximum Discrimination”, CVPR '97

[6] S. Lin, S. Kung and L. Lin, “Face Recognition/Detection by Probabilistic Decision-Based Neural Network”, IEEE Trans. Neural Networks, Vol. 8, No. 1, pp. 114-132, 1997.

國際替代計量

三維人臉模型化與手勢辨識

全文下載

主題瀏覽