Sign Language Recognition Based on Intelligent Glove Using Machine Learning Techniques

We present an intelligent electronic glove system able to detect numbers of sign language in order to automate the process of communication between a deaf-mute person and others. This is done by translating the hands move sign language into an oral language. The system is inside to a glove with flex sensors in each finger that we are used to collect data that are analyzed through a methodology involving the following stages: (i) Data balancing with the Kennard-Stone (KS), (ii) Comparison of prototypes selection between CHC evolutionary Algorithm and Decremental Reduction Optimization Procedure 3 (DROP3) to define the best one. Subsequently, the K-Nearest Neighbors (kNN) as classifier (iii) is implemented. As a result, the amount of data reduced from stage (i) from storage within the system is 98%. Also, a classification performance of 85% is achieved with CHC evolutionary algorithm.

[1]  Tony R. Martinez,et al.  Reduction Techniques for Instance-Based Learning Algorithms , 2000, Machine Learning.

[2]  Li Lei,et al.  Design of data-glove and Chinese sign language recognition system based on ARM9 , 2015, 2015 12th IEEE International Conference on Electronic Measurement & Instruments (ICEMI).

[3]  Paul D. Rosero-Montalvo,et al.  Human Sit Down Position Detection Using Data Classification and Dimensionality Reduction , 2017 .

[4]  Carlos Oppus,et al.  User-oriented finger-gesture glove controller with hand movement virtualization using flex sensors and a digital accelerometer , 2014, 2014 International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM).

[5]  Paul Rosero-Montalvo,et al.  Human-sitting-pose detection using data classification and dimensionality reduction , 2016, 2016 IEEE Ecuador Technical Chapters Meeting (ETCM).

[6]  Juan C. Alvarado-Pérez,et al.  Interactive Data Visualization Using Dimensionality Reduction and Similarity-Based Representations , 2016, CIARP.

[7]  A. Guzman,et al.  Neighborhood Criterion Analysis for Prototype Selection Applied in WSN Data , 2017, 2017 International Conference on Information Systems and Computer Science (INCISCOS).

[8]  Diego Hernán Peluffo-Ordóñez,et al.  Data Visualization Using Interactive Dimensionality Reduction and Improved Color-Based Interaction Model , 2017, IWINAC.

[9]  Federica Pascucci,et al.  A low cost smart glove for visually impaired people mobility , 2015, 2015 23rd Mediterranean Conference on Control and Automation (MED).

[10]  Diego H. Peluffo-Ordóñez,et al.  Prototype reduction algorithms comparison in nearest neighbor classification for sensor data: Empirical study , 2017, 2017 IEEE Second Ecuador Technical Chapters Meeting (ETCM).

[11]  Derek Ho,et al.  Glove-based hand gesture recognition sign language translator using capacitive touch sensor , 2016, 2016 IEEE International Conference on Electron Devices and Solid-State Circuits (EDSSC).

[12]  Francisco Herrera,et al.  Using evolutionary algorithms as instance selection for data reduction in KDD: an experimental study , 2003, IEEE Trans. Evol. Comput..

[13]  Francisco Herrera,et al.  Prototype Selection for Nearest Neighbor Classification: Taxonomy and Empirical Study , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Nooritawati Md Tahir,et al.  Review in Sign Language Recognition Systems , 2012, 2012 IEEE Symposium on Computers & Informatics (ISCI).