Effective Color Components for Pupil Diameter Measurement of Brown Eye Using a Visible-Light Camera

The pupil diameter variation are used for various intelligent system. The measurement of pupil diameter is generally performed using eye images taken with a near-infrared camera. However, the near-infrared camera is not mounted on a general PC or mobile devices. Therefore, if the pupil diameter can be measured using a visible-light camera mounted on a general PC or mobile devices, the system using pupil diameter variation can be generalized. In this paper, we investigate the effective color components for pupil detection using the visible-light camera under visible-light conditions. From the experimental results, the effective color components for pupil detection and pupil diameter measurement are R in RGB color space and H in HSV color space. In addition, as a result of measuring the pupil diameter with R and H color components, the accuracy of the visible-light camera is almost same as that of the near-infrared camera.

[1]  Mohammad Saberi,et al.  An Innovative Skin Detection Approach Using Color Based Image Retrieval Technique , 2012, ArXiv.

[2]  Jie Li,et al.  Shadow detection in color aerial images based on HSI space and color attenuation relationship , 2012, EURASIP J. Adv. Signal Process..

[3]  Tarun Jain,et al.  Specific Color Detection in Images using RGB Modelling in MATLAB , 2017 .

[4]  A. Malik,et al.  Machine Learning to Differentiate Between Positive and Negative Emotions Using Pupil Diameter , 2015, Front. Psychol..

[5]  Hiromitsu Shimakawa,et al.  Touch Gesture and Pupil Reaction on Mobile Terminal to Find Occurrences of Interested Items in Web Browsing , 2016 .

[6]  P. S. Hiremath,et al.  Detection of multiple faces in an image using skin color information and lines-of-separability face model , 2006, Int. J. Pattern Recognit. Artif. Intell..

[7]  Kostas Stathis,et al.  Automatic detection of microaneurysms in diabetic retinopathy fundus images using the L*a*b color space. , 2016, Journal of the Optical Society of America. A, Optics, image science, and vision.

[8]  P. Ganesan,et al.  International Conference on Recent Trends in Computing 2015 ( ICRTC-2015 ) Comparative Study of Skin Color Detection and Segmentation in HSV and YCbCr Color Space , 2015 .

[9]  Wataru Kameyama,et al.  A Consideration on Comic Reader's Behavior using Gaze Path and Pupil Size(画像符号化,通信・ストリーム技術,一般) , 2012 .

[10]  Hamid Reza Pourreza,et al.  Fast and Accurate Pupil Positioning Algorithm using Circular Hough Transform and Gray Projection , 2011 .

[11]  Armando J. Pinho,et al.  Color-spaces and color segmentation for real-time object recognition in robotic applications , 2007 .

[12]  Yoshinobu Ebisawa,et al.  PupilMouse supported by head pose detection , 2008, 2008 IEEE Conference on Virtual Environments, Human-Computer Interfaces and Measurement Systems.