Multi-lingual Handwriting Recovery Framework based on Convolutional
Denoising Autoencoder with Attention model
Abstract
For several decades, the offline handwriting recognition problem has
escaped a satisfactory solution. In the field of online recognition,
researchers have had more successful performance, but the ability to
extract dynamic information from static images has not been well
explored yet. In this paper, we introduce a novel multi-lingual word
handwriting recovery framework based on a convolutional denoising
autoencoder with an attention model for pen up / down, velocity and
temporal order recovery. The proposed framework consists of extracting
robust features from a handwriting image using a stacked denoising
autoencoder and an encoder Bidirectional Gated Recurrent Unit (BGRU)
model. Then, the obtained vectors are decoded to produce an online
script with dynamic characteristics using a BGRU with temporal
attention. Evaluation is done on a Latin and Arabic Online and offline
handwriting character / word databases and the proposed framework
achieves high competitive results. To the best of our knowledge, this is
the first work of its kind.