Comparison between type-1 fuzzy membership functions for sign language applications

The paper presents a comparison between different membership functions based type-1 fuzzy set for automatic hand gesture recognition for American Sign Language recognition. First pre-processing of the images is done using skin color based segmentation, morphological operations and to extract the hand gesture image from the background, Sobel edge detection technique is performed. Then the image is sub-divided into 9 quadrants and for each quadrant, the area enclosed by the image in that specific quadrant is calculated. Based on areas from 15 images for a particular quadrant, the Gaussian three membership curves triangular, trapezoidal and Gaussian are designed. Now for an unknown gesture, nine membership values are determined and the summation of these membership values produces the strength of the unknown hand gesture matched with a known gesture. The highest strength obtained for a known gesture is the desired result. Experimentally, it is found that trapezoidal membership function outperforms the other two membership functions and gives overall an accuracy of 85.83%.

[1]  Robert LIN,et al.  NOTE ON FUZZY SETS , 2014 .

[2]  Chung-Lin Huang,et al.  Hand gesture recognition using a real-time tracking method and hidden Markov models , 2003, Image Vis. Comput..

[3]  Alex Pentland,et al.  Real-Time American Sign Language Recognition Using Desk and Wearable Computer Based Video , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Mariusz Oszust,et al.  Recognition of signed expressions observed by Kinect Sensor , 2013, 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[5]  N.D. Georganas,et al.  Real-time Vision-based Hand Gesture Recognition Using Haar-like Features , 2007, 2007 IEEE Instrumentation & Measurement Technology Conference IMTC 2007.

[6]  Junsong Yuan,et al.  Robust Part-Based Hand Gesture Recognition Using Kinect Sensor , 2013, IEEE Transactions on Multimedia.

[7]  Richard Bellman,et al.  Decision-making in fuzzy environment , 2012 .

[8]  Sriparna Saha,et al.  Fuzzy L Membership Function Based Hand Gesture Recognition for Bharatanatyam Dance , 2013, 2013 5th International Conference on Computational Intelligence and Communication Networks.

[9]  Sriparna Saha,et al.  Fuzzy image matching for posture recognition in ballet dance , 2013, 2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[10]  Sriparna Saha,et al.  Topomorphological approach to automatic posture recognition in ballet dance , 2015, IET Image Process..

[11]  W. Stokoe.  Sign Language Structure , 1980 .

[12]  Ching-Hua Chuan,et al.  American Sign Language Recognition Using Leap Motion Sensor , 2014, 2014 13th International Conference on Machine Learning and Applications.

[13]  Jan Peters,et al.  Computational Intelligence: Principles, Techniques and Applications , 2007, Comput. J..

[14]  Anant Agarwal,et al.  Sign language recognition using Microsoft Kinect , 2013, 2013 Sixth International Conference on Contemporary Computing (IC3).

[15]  Vladimir Pavlovic,et al.  Hand Gesture Modeling, Analysis, and Synthesis , 1995 .