Title :
Style transfer matrix learning for writer adaptation
Author :
Zhang, Xu-Yao ; Liu, Cheng-Lin
Author_Institution :
Nat. Lab. of Pattern Recognition (NLPR), Chinese Acad. of Sci., Beijing, China
Abstract :
In this paper, we propose a novel framework of style transfer matrix (STM) learning to reduce the writing style variation in handwriting recognition. After writer-specific style transfer learning, the data of different writers is projected onto a style-free space, where a writer independent classifier can yield high accuracy. We combine STM learning with a specific nearest prototype classifier: learning vector quantization (LVQ) with discriminative feature extraction (DFE), where both the prototypes and the subspace transformation matrix are learned via online discriminative learning. To adapt the basic classifier (trained with writer-independent data) to particular writers, we first propose two supervised models, one based on incremental learning and the other based on supervised STM learning. To overcome the lack of labeled samples for particular writers, we propose an unsupervised model to learn the STM using the self-taught strategy (also known as self-training). Experiments on a large-scale Chinese online handwriting database demonstrate that STM learning can reduce recognition errors significantly, and the unsupervised adaptation model performs even better than the supervised models.
Keywords :
feature extraction; handwriting recognition; image classification; matrix algebra; natural language processing; unsupervised learning; discriminative feature extraction; error recognition; handwriting recognition; incremental learning; large-scale Chinese online handwriting database; learning vector quantization; nearest prototype classifier; online discriminative learning; self-taught strategy; self-training; style transfer matrix learning; style-free space; subspace transformation matrix; supervised STM learning classifier; unsupervised adaptation model; writer adaptation; writer independent classifier; writer-specific style transfer learning; writing style variation; Adaptation models; Handwriting recognition; Hidden Markov models; Loss measurement; Mathematical model; Prototypes; Training;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4577-0394-2
DOI :
10.1109/CVPR.2011.5995661