Recognition of American Sign Language Fingerspelling by Applying Matrix Matching Algorithm Using Leap Motion Controller Sensor

Abstract

This paper presents the recognition of American Sign Language Fingerspelling by applying Matrix Matching algorithm using Leap Motion Controller Sensor. The study focused on the recognition of all the static and dynamic letters to increase the recognition rate and avoid misclassification. With proper hand orientation of the user and using the Leap Motion Controller Sensor’s skeletal tracking feature, the researchers were able to acquire the joint coordinates of the distal and proximal phalanges of the human hand. These acquired joint coordinates were then used to create two matrices where matrix multiplication was then applied to generate a unique output matrix. Reduction of row elements as well as the column elements were used by the researchers to derive the Horizontal and Vertical resultant matrices to uniquely represent the letters in American Sign Language Fingerspelling. The letters would then be recognized by the system once the generated resultant matrix matched the reference resultant matrix in the system program. The process of matrix subtraction was executed in the matching process of the algorithm.

Authors and Affiliations

Aljhon N. Abila, Rafael Joseph C. Dichoso, Reditt John B. Rance, Jhon Nathaniel M. Umali, Ralph Anthony Yanza

Keywords

Related Articles

Comparison of Microwave and Optical Wireless Inter-Satellite Links

microwaves inter-satellite links are considered as the traditional technology of space satellite to satellite communication systems. However, the major next step in the evolution of satellite communication technology is...

Weight Reduction and Strengthening Of RC Beam Using CFRP and GFRP Layers by ANSYS 15.0

The current paper focuses on the study of RC beam with FRP as external layers. CFRP and GFRP as FRP materials are considered during the current work to study their behaviour on the deformation, strain and weight by mean...

Introduction and Parametric Analysis of Air Bearings

Bearing technology represents one of the age old challenges for mechanical engineers. Plain bearings and rolling bearings have been pushed to their limits in applications like electric motors and high resolution scannin...

Study of Accident Control System in Automobile in India

In this paper we studied that in every year number of accident in India due to not using safety precautions like don’t drink and drive, not wearing seatbelt, not using vehicles in proper maintenance, etc. In India one d...

An Experimental Study of Advanced Universal Impeller System with Limited RPM using Pedal Mechanism

In this paper discuss that the technical evolution and latest technological trends with considerations need effectively creation an optimistic system like to design and construct advanced universal impeller system with...

Download PDF file
  • EP ID EP23241
  • DOI http://doi.org/10.22214/ijraset.2017.3044
  • Views 256
  • Downloads 8

How To Cite

Aljhon N. Abila, Rafael Joseph C. Dichoso, Reditt John B. Rance, Jhon Nathaniel M. Umali, Ralph Anthony Yanza (2017). Recognition of American Sign Language Fingerspelling by Applying Matrix Matching Algorithm Using Leap Motion Controller Sensor. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 5(3), -. https://europub.co.uk/articles/-A-23241