Precise Motif Sequence Pattern Recognition of American Sign Language (ASL) Letter Signs
Anthony M. Kutscher Sr. and Yanzhen Qu
Colorado Technical University, Colorado Springs, CO, USA
Abstract—Unsuccessful pattern recognition of the complete set of fingerspelled letter signs were reported by studies using specialized video, RGB video, and Infrared (IR) video cameras, combined with various technologies. One reviewed study scaled (resized) letters to a specific size for ease of pattern recognition. Our study used the five similarly contoured ASL closed hand letter signs (ACLHS) A, M, N, S and T, with differentiation problems due to similar contours to show that motif sequences, formulated from the unique signatures of each of the five ACHLS, are less complex and faster at pattern recognition than scaling each captured letter sign dynamically. Thus, IR photo sensor data can be rotated to specific targets, creating unique signature patterns for each of the five ACHLS, and those unique signatures can be formulated into motif sequences for consistent and accurate pattern recognition of unknown ACHLS, regardless of similar handshape contours.
Index Terms—Kinect, ASL, fingerspelling, similar contours, pattern matching, and motif sequences
Cite: Anthony M. Kutscher Sr. and Yanzhen Qu, "Precise Motif Sequence Pattern Recognition of American Sign Language (ASL) Letter Signs," International Journal of Signal Processing Systems, Vol. 4, No. 5, pp. 405-410, October 2016. doi: 10.18178/ijsps.4.5.405-410
Cite: Anthony M. Kutscher Sr. and Yanzhen Qu, "Precise Motif Sequence Pattern Recognition of American Sign Language (ASL) Letter Signs," International Journal of Signal Processing Systems, Vol. 4, No. 5, pp. 405-410, October 2016. doi: 10.18178/ijsps.4.5.405-410