Attention-based Fully Gated CNN-BGRU for Russian Handwritten Text

TL;DR

This paper introduces a novel attention-based Fully Gated CNN-BGRU neural network for recognizing handwritten Kazakh and Russian text, achieving state-of-the-art accuracy on the HKR dataset.

Contribution

The work presents a new Fully Gated CNN architecture combined with bidirectional GRU and attention mechanisms, specifically tailored for handwritten Kazakh and Russian text recognition.

Findings

Achieved 0.045 CER on first dataset

Achieved 0.064 CER on second dataset

First application of deep neural networks on HKR dataset

Abstract

This research approaches the task of handwritten text with attention encoder-decoder networks that are trained on Kazakh and Russian language. We developed a novel deep neural network model based on Fully Gated CNN, supported by Multiple bidirectional GRU and Attention mechanisms to manipulate sophisticated features that achieve 0.045 Character Error Rate (CER), 0.192 Word Error Rate (WER) and 0.253 Sequence Error Rate (SER) for the first test dataset and 0.064 CER, 0.24 WER and 0.361 SER for the second test dataset. Also, we propose fully gated layers by taking the advantage of multiple the output feature from Tahn and input feature, this proposed work achieves better results and We experimented with our model on the Handwritten Kazakh & Russian Database (HKR). Our research is the first work on the HKR dataset and demonstrates state-of-the-art results to most of the other existing models.