Low cost eye based human computer interface system (Eye controlled mouse)

This paper presents a low cost eye based Human Computer Interface (HCI) developed for amputees and paralyzed persons. The system is a computer interface that provides the functionality of an input device like mouse based on eye actions such as eye blink, eye-gaze and gaze control. For initialization, the subject just holds his/her head still for a few seconds: using involuntary blinks that would naturally occur during this time, the system both locates the user's eye pair as well as forms online templates of the open and shut eyes of the specific user, valid for the rest of that session. The located eyes are tracked in real time using template matching and histogram back projection. Reasonable amount of head motion, carried out at reasonable speeds, are automatically detected and compensated. Automatic re-initialization of the system occurs if the user goes out of frame or during excessive rapid head movement. When the eyes are detected as more than 70% open, the iris tracker module is triggered. In order to detect the iris, the eye image is subjected to image conditioning to eliminate the eyelashes and eyebrow. The iris is detected on the basis of colour and shape, and the Hough transform is used on the region to determine its centre and radius. Iris detection is continuously repeated whenever the eye is open, so that it is continuously tracked. Later on, continuous gaze does the mouse clicking action replacing the mouse of the computer with this HCI.

[1]  Tiziana D'Orazio,et al.  An algorithm for real time eye detection in face images , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[2]  Peter Eisert,et al.  Eye Center Localization Using Adaptive Templates , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[3]  Pong C. Yuen,et al.  Multi-cues eye detection on gray intensity image , 2001, Pattern Recognit..

[4]  Paola Campadelli.  LOCALIZATION OF FACIAL FEATURES AND FIDUCIAL POINTS , 2002 .

[5]  Tiziana D'Orazio,et al.  An algorithm for real time eye detection in face images , 2004, ICPR 2004.

[6]  Takeo Kanade,et al.  Neural network-based face detection , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  Narendra Ahuja,et al.  Detecting human faces in color images , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[8]  Ioannis Pitas,et al.  A novel method for automatic face segmentation, facial feature extraction and tracking , 1998, Signal Process. Image Commun..

[9]  Azriel Rosenfeld,et al.  Eye detection in a face image using linear and nonlinear filters , 2001, Pattern Recognit..

[10]  Irfan A. Essa,et al.  Detecting and tracking eyes by using their physiological properties, dynamics, and appearance , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[11]  Harry Wechsler,et al.  Eye Detection Using Optimal Wavelet Packets and Radial Basis Functions (RBFs) , 1999, Int. J. Pattern Recognit. Artif. Intell..

[12]  Alexander H. Waibel,et al.  Skin-Color Modeling and Adaptation , 1998, ACCV.

[13]  Takeo Kanade,et al.  Neural Network-Based Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Clement T. Yu,et al.  Detecting human faces in color images , 1998, Proceedings International Workshop on Multi-Media Database Management Systems (Cat. No.98TB100249).