TY - CONF AU - Volkmar Frinken AU - Andreas Fischer AU - Horst Bunke AU - Alicia Fornes A2 - ICDAR PY - 2011// TI - Co-training for Handwritten Word Recognition BT - 11th International Conference on Document Analysis and Recognition SP - 314 EP - 318 N2 - To cope with the tremendous variations of writing styles encountered between different individuals, unconstrained automatic handwriting recognition systems need to be trained on large sets of labeled data. Traditionally, the training data has to be labeled manually, which is a laborious and costly process. Semi-supervised learning techniques offer methods to utilize unlabeled data, which can be obtained cheaply in large amounts in order, to reduce the need for labeled data. In this paper, we propose the use of Co-Training for improving the recognition accuracy of two weakly trained handwriting recognition systems. The first one is based on Recurrent Neural Networks while the second one is based on Hidden Markov Models. On the IAM off-line handwriting database we demonstrate a significant increase of the recognition accuracy can be achieved with Co-Training for single word recognition. UR - http://dx.doi.org/10.1109/ICDAR.2011.71 N1 - DAG ID - Volkmar Frinken2011 ER -