PT Unknown
AU Lei Kang
   Pau Riba
   Marçal Rusiñol
   Alicia Fornes
   Mauricio Villegas
TI Distilling Content from Style for Handwritten Word Recognition
BT 17th International Conference on Frontiers in Handwriting Recognition
PY 2020
AB Despite the latest transcription accuracies reached using deep neural network architectures, handwritten text recognition still remains a challenging problem, mainly because of the large inter-writer style variability. Both augmenting the training set with artificial samples using synthetic fonts, and writer adaptation techniques have been proposed to yield more generic approaches aimed at dodging style unevenness. In this work, we take a step closer to learn style independent features from handwritten word images. We propose a novel method that is able to disentangle the content and style aspects of input images by jointly optimizing a generative process and a handwrittenword recognizer. The generator is aimed at transferring writing style features from one sample to another in an image-to-image translation approach, thus leading to a learned content-centric features that shall be independent to writing style attributes.Our proposed recognition model is able then to leverage such writer-agnostic features to reach better recognition performances. We advance over prior training strategies and demonstrate with qualitative and quantitative evaluations the performance of boththe generative process and the recognition efficiency in the IAM dataset.
ER