Pattern Recognition
Pattern Recognition
5 years ago

An improved online writer identification framework using codebook descriptors

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.

Publisher URL: www.sciencedirect.com/science

DOI: S0031320318300402

You might also like
Discover & Discuss Important Research

Keeping up-to-date with research can feel impossible, with papers being published faster than you'll ever be able to read them. That's where Researcher comes in: we're simplifying discovery and making important discussions happen. With over 19,000 sources, including peer-reviewed journals, preprints, blogs, universities, podcasts and Live events across 10 research areas, you'll never miss what's important to you. It's like social media, but better. Oh, and we should mention - it's free.

  • Download from Google Play
  • Download from App Store
  • Download from AppInChina

Researcher displays publicly available abstracts and doesn’t host any full article content. If the content is open access, we will direct clicks from the abstracts to the publisher website and display the PDF copy on our platform. Clicks to view the full text will be directed to the publisher website, where only users with subscriptions or access through their institution are able to view the full article.