Classification of the Korean Sign Language Alphabet Using an Accelerometer with a Support Vector Machine

Figure 5

Schematic of the automatic segmentation process: (a) the accelerometer signal is normalized by the baseline correcting process; (b) the gesture offset time point is extracted from the vector sum of the low-pass-filtered three-axis signals; (c) the segmented data are determined based on the gesture offset time point.

(a)

(b)

(c)