Abstract
This work proposes a text independent writer identification framework for online handwritten data. We derive a strategy that encodes the sequence of feature vectors extracted at sample points of the temporal trace with descriptors obtained from a codebook. The derived descriptors take into account, the scores of each of the attributes in a feature vector, that are computed with regards of the proximity to their corresponding values in the assigned codevector of the codebook. A codebook comprises a set of codevectors that are pre-learnt by a k-means algorithm applied on feature vectors of handwritten documents pooled from several writers. In addition, for constructing the codebook, we consider features that are derived by incorporating a so called ‘gap parameter’ that captures characteristics of sample points in the neighborhood of the point under consideration. We formulate our strategy in a way that, for a given codebook size k, we employ the descriptors of only k−1 codevectors to construct the final descriptor by concatenation. The usefulness of the descriptor is demonstrated by several experiments that are reported on publicly available databases.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have