Writer Adaptation for Online Handwriting Recognition

• Authors: Scott D. Connell;Anil K. Jain
• Venue: IEEE Transactions on Pattern Analysis and Machine Intelligence
• Year: 2002

Writer-adaptation is the process of converting a writer-independent handwriting recognition system, which models the characteristics of a large group of writers, into a writer-dependent system, which is tuned for a particular writer. This adaptation has the potential of greatly increasing recognition accuracies, provided adequate models can be constructed for a particular writer. The limited amount of data a writer is willing to provide during the training phase constrains the complexity of these models. We show how the appropriate use of writer-independent models is important for the adaptation process. Our approach to writer-adaptation makes use of writer-independent writing style models (called lexemes), to identify the styles present in a particular writer's training data. These models are then updated using the writer's data. Lexemes that are present in the writer's data, but for which an inadequate number of training examples is available, are replaced with the writer-independent models. We demonstrate the feasibility of this approach on both isolated handwritten character recognition and unconstrained word recognition tasks. Our results show an average reduction in error rate of 16.3 percent for lowercase characters as compared against representing each of the writer's character classes with a single model. In addition, an average error rate reduction of 9.2 percent is shown on handwritten words using only a small amount of data for adaptation.