Handwriting recognition by derivative dynamic time warping methodology via sensor-based gesture recognition

A handwritten character recognition methodology based on signals of acceleration obtained from gesture sensors with dynamic time warping (DTW) is presented. After applying the preprocessing steps of filtering, character separation and normalisation, similarities are detected by DTW and each signal component corresponding to a character is classified. However, the nature of the writing process may induce additional time-shifting problems among repetitions of characters since DTW uses only the amplitude values of signals to calculate the distance between them. Accordingly, when signals have different acceleration and deceleration values, irrelevant points of the signals may match each other just because their amplitude values are close. To overcome this problem, derivative dynamic time warping (DDTW) methodology is also implemented. The methodologies mentioned as well as the linear alignment approach were tested with Euclidean, Manhattan and Chessboard distance metrics to detect user-dependent/independent acceleration signals of lower-case characters of the English alphabets and digits. Recognition accuracy rates of Euclidean and Chessboard metrics with DDTW are 98.65%, which is the highest value among all methods applied and metrics. The comparison of Euclidean and Chessboard durations shows that Chessboard with DDTW is the most efficient method in terms of time.