A novel approach to American sign language recognition using MAdaline neural network

Sign language interpretation is gaining a lot of research attention because of its social contributions which is proved to be extremely beneficial for the people suffering from hearing or speaking disabilities. This paper proposes a novel image processing sign language detection framework that employs MAdaline network for classification purpose. This paper mainly highlights two novel aspects, firstly it introduces an advanced feature set comprising of seven distinct features that has not been used widely for sign language interpretation purpose, more over utilization of such features negates the cumbersome step of cropping of irrelevant background image, thus reducing system complexity. Secondly it suggests a possible solution of the concerned problem can be obtained using an extension of the traditional Adaline network, formally termed as MAdaline Network. Although the concept of MAdaline network has originated much earlier, the provision of application of this framework in this domain definitely help in designing an improved sign language interpreting interface. The newly formulated framework has been implemented to recognize standardized American sign language containing 26 English alphabets from ‘A’ to ‘Z’. The performance of the proposed algorithm has also been compared with the standardized algorithms, and in each case the former one outperformed its contender algorithms by a large margin establishing the efficiency of the same.

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

[2]  Alan J. Dix.  Human-Computer Interaction , 2018, Encyclopedia of Database Systems.

[3]  Russell C. Eberhart,et al.  Neural network PC tools: a practical guide , 1990 .

[4]  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.

[5]  Thomas G. Dietterich.  Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms , 1998, Neural Computation.

[6]  Yuxuan Wang,et al.  A Leaf Recognition Algorithm for Plant Classification Using Probabilistic Neural Network , 2007, 2007 IEEE International Symposium on Signal Processing and Information Technology.

[7]  Junsong Yuan,et al.  Robust hand gesture recognition based on finger-earth mover's distance with a commodity depth camera , 2011, ACM Multimedia.

[8]  Dimitris N. Metaxas,et al.  Handshapes and Movements: Multiple-Channel American Sign Language Recognition , 2003, Gesture Workshop.

[9]  Bernard Widrow,et al.  30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[10]  W. T. Illingworth,et al.  Practical guide to neural nets , 1991 .

[11]  Thad Starner,et al.  American sign language recognition in game development for deaf children , 2006, Assets '06.

[12]  Ming Ouhyoung,et al.  A real-time continuous gesture recognition system for sign language , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

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

[14]  W. Buxton.  Human-Computer Interaction , 1988, Springer Berlin Heidelberg.

[15]  Aaron F. Bobick,et al.  Parametric Hidden Markov Models for Gesture Recognition , 1999, IEEE Trans. Pattern Anal. Mach. Intell..