Fully Convolutional Networks for Handwriting Recognition

Citations Over Time

Abstract

Handwritten text recognition is challenging because of the virtually infinite ways a human can write the same message. Our fully convolutional handwriting model takes in a handwriting sample of unknown length and outputs an arbitrary stream of symbols. Our dual stream architecture uses both local and global context and mitigates the need for heavy preprocessing steps such as symbol alignment correction as well as complex post processing steps such as connectionist temporal classification, dictionary matching or language models. Using over 100 unique symbols, our model is agnostic to Latin-based languages, and is shown to be quite competitive with state of the art dictionary based methods on the popular IAM and RIMES datasets. When a dictionary is known, we further allow a probabilistic character error rate to correct errant word blocks. Finally, we introduce an attention based mechanism which can automatically target variants of handwriting, such as slant, stroke width, or noise.

Related Papers

• → On-line cursive script recognition using time-delay neural networks and hidden Markov models(1995)115 cited
• → Two streams deep neural network for handwriting word recognition(2020)12 cited
• → Script independent online handwriting recognition(2015)11 cited
• → Symbol Knowledge Extraction from a Simple Graphical Language(2011)2 cited
• → Separating Optical and Language Models Through Encoder-Decoder Strategy for Transferable Handwriting Recognition(2018)