複雜背景之視覺手勢辨識

本文提出了能夠從複雜背景中找出手部所在位置的影像分割演算法。一般而言，視覺手勢辨識的困難包含了環境光會改變、背景含有膚色物體以及背景物體可能移動等。本文的核心目標是針對彩色相機之影像，能將人手從複雜的背景中分割出來。為肆應複雜之背景，我們提出拇指扣偵測演算法，其所支援的手形包含拳頭、指向以及勝利三種。拇指扣是上述三種手形正面視角的共同部位。因為拇指扣與背景物之外觀有著明顯的差異（特別是臉部器官），這使它成為一個理想的偵測目標。一旦拇指扣從畫面中偵測到，便可以對其周圍區域作進一步的分析，判斷使用者的手勢。為了訓練拇指扣偵測器，我們由十個人蒐集210張拇指扣影像，並加入2521張隨機的影像作為訓練樣本。這些訓練樣本被取樣成32×40像素大小的影像，並被用來訓練使用局部二值形樣特徵之支持向量機分類器。以拇指扣偵測為核心技術，我們還建立了虛擬滑鼠人機介面。使用者可以藉由移動拇指扣與點擊手指來操控滑鼠游標。本文使用αβγ濾波器來追蹤並平滑化拇指扣之軌跡，並以光流法偵測使用者手指之點擊動作。這個人機介面程式每秒約可以處理25張影像，勉強符合即時互動的要求。

關鍵字

手勢；分割演算法；支持向量機； αβγ濾波器；光流法；人機介面

並列摘要

A robust algorithm capable of segmenting specified hand gestures in cluttered image sequences is proposed. Typically, vision-based gesture recognition systems suffer from the difficulty of hand region segmentation, which includes the change of lighting conditions, the presence of other skin color objects and the movement of background objects. The main concern of this paper is to design an algorithm for RGB camera that locates hand region correctly even under complex backgrounds. The proposed segmentation algorithm, thumb-cover detection algorithm, restricts itself to support only three hand shapes, i.e. fist, pointing and victory. The thumb cover is the common part appearing in above mentioned hand shapes. It is an ideal target to detect for its distinctness from other background objects (especially facial organs). Once the thumb cover is detected, one can further apply other techniques on its neighboring region to recognize what gesture is posed. To train a detector of thumb cover, we collected 210 thumb-cover images from 10 people and 2521 random images as training samples. These samples, resized to 32 by 40 pixels, are combined to train an SVM with LBP feature applied. A virtual mouse human computer interaction (HCI) program basing on thumb-cover detection is also implemented. Users can manipulate the mouse cursor by moving his/her thumb cover and clicking his/her index finger in front of a camera. The αβγ filter is adopted to track and smooth the trajectory of thumb cover and optical flow is used to detect the clicking of finger. The HCI program runs at the speed of 25 frames per second (fps), which might be suitable for real time interaction.

並列關鍵字

hand gesture ； segmentation ； SVM ； αβγ filter ； optical flow ； HCI

參考文獻

[1] S. S. Rautaray, A. Agrawal, “Vision Based Hand Gesture Recognition for Human Computer Interaction: A Survey,” in Artificial Intelligence Review, vol. 43, no. 1, pp. 1–54, 2015.

[2] G. ElKoura, K. Singh, “Handrix: Animating the Human Hand,” in ACM SIGGRAPH Symposium on Computer Animation, pp. 110-119, 2003.

[3] D. D. Yang, L. W. Lin, J. X. Yin, L. X. Zhen, and J. C. Huang, “An Effective Robust Fingertip Detection Method for Finger Writing Character Recognition System,” in Internationl Conference on Machine Learning and Cybernetics, vol. 8, pp. 18-21, 2005.

[4] T. Lee and T. Höllerer, “Handy AR: Markerless Inspection of Augmented Reality Objects Using Fingertip Tracking,” in IEEE International Symposium on Wearable Computers, pp. 1-8, 2007.

[5] D. Lee and S. G. Lee, “Vision-based Finger Action Recognition by Angle Detection and Contour Analysis,” ETRI Journal, vol. 33, pp. 1141-1158, 2009.

國際替代計量

複雜背景之視覺手勢辨識

全文下載

主題瀏覽