Distilling Content from Style for Handwritten Word Recognition
2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR)(2020)
摘要
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 handwritten word 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 both the generative process and the recognition efficiency in the IAM dataset.
更多查看译文
关键词
Handwritten word recognition,content and style disentanglement,image-to-image translation,handwriting generation,sequence-to-sequence neural networks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络