In this paper, we present a novel framework for HMM-based handwriting verification in which the training is performed using a one-shot algorithm for segmentation and HMMparameter estimation using a constrained k-means clustering procedure, instead of the recursive expectation maximization algorithm. This new framework allows training based on a single observation set which results in a straight forward reference model construction and elimination of computationally expensive re-training. Results of a human study using this verification system for handwritten signature and password verification demonstrate that this new efficient approach is still able to maintain high accuracy of 99 % while only three training sets were used.

Additional Metadata
Keywords Expectation maximization, Handwriting verification, Hidden Markov models, Viterbi algorithm
Persistent URL dx.doi.org/10.1109/IMTC.2008.4547350
Conference 2008 IEEE International Instrumentation and Measurement Technology Conference, I2MTC
Citation
Talebinejad, M. (Mehran), Miri, A. (Ali), & Chan, A. (2008). A computationally efficient HMM-based handwriting verification system. In Conference Record - IEEE Instrumentation and Measurement Technology Conference (pp. 1868–1872). doi:10.1109/IMTC.2008.4547350