2000 · 37 citations · 0 references
ComputingComputer SystemsEnglish WritingNatural Language ProcessingWriting InstructionPattern RecognitionWord RecognitionHandwriting RecognitionHandwriting StylesHandwritten Character RecognitionLexeme Recognition
The shift to handheld devices has increased demand for pen‑based input, but the vast variability in writing styles makes writer‑independent unconstrained online handwriting recognition a difficult problem, with current state‑of‑the‑art limited to constrained settings. The thesis proposes a method to identify distinct writing styles, called lexemes. The approach builds non‑parametric and parametric classifiers that use lexeme‑based compact representations, fuses lexeme models across feature sets, and adapts to individual writers by leveraging lexemes derived from a large writer pool. Experiments on unconstrained online handwritten characters and words, including English and Devanagari, demonstrate the effectiveness of the lexeme‑based classifiers and adaptation methods.
The field of personal computing has begun to make a transition from the desk-top to handheld devices, thereby requiring input paradigms that are more suited for single hand entry than a keyboard and recent developments in online handwriting recognition allow for such input modalities. Data entry using a pen forms a natural, convenient interface. The large number of writing styles and the variability between them makes the problem of writer-independent unconstrained handwriting recognition a very challenging pattern recognition problem. The state-of-the-art in online handwriting recognition is such that it has found practical success in very constrained problems. In this thesis, a method of identifying different writing styles, referred to as lexemes, is described. Approaches for constructing both non-parametric and parametric classifiers are described that take advantage of the identified lexemes to form a more compact representation of the data, while maintaining good recognition accuracies. Experimental results are presented on different sets of unconstrained online handwritten characters and words. In addition, a method of combining information from lexeme models built on different feature sets is described, and results are presented on both English characters and Devanagari characters. Finally, a method of writer-adaptation is described which makes use of the lexemes identified from a large group of writers to define lexemes within a small amount of data from a single writer.