Recognition of American Sign Language Fingerspelling by Applying Matrix Matching Algorithm Using Leap Motion Controller Sensor
Aljhon N. Abila · International Journal for Research in Applied Science and Engineering Technology · 2017
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 ControllerSensor'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.