mlsanityData to 7 Oct 2026

CNN-BiLSTM model for English Handwriting Recognition: Comprehensive Evaluation on the IAM Dataset

arXiv 2307.00664 ↗First posted 2 Jul 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a CNN-BiLSTM system for the problem of offline English handwriting recognition, with extensive evaluations on the public IAM dataset, including the effects of model size, data augmentation and the lexicon. Our best model achieves 3.59% CER and 9.44% WER using CNN-BiLSTM network with CTC layer. Test time augmentation with rotation and shear transformations applied to the input image, is proposed to increase recognition of difficult cases and found to reduce the word error rate by 2.5% points. We also conduct an error analysis of our proposed method on IAM dataset, show hard cases of handwriting images and explore samples with erroneous labels. We provide our source code as public-domain, to foster further research to encourage scientific reproducibility.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 47 references that are in the map. First posted on arXiv 2 Jul 2023.

Builds on

16 of 47 references.

References · 16

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  7. 2016Pointer Sentinel Mixture Modelscited by 2,992
  8. 2015Spatial Transformer Networkscited by 1,423
  9. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 519
  10. 2021TrOCR: Transformer-based Optical Character Recognition with Pre-trained Modelscited by 278
  11. 2020Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognitioncited by 71
  12. 2019Evaluating Sequence-to-Sequence Models for Handwritten Text Recognitioncited by 58
4 more
  1. 2021Rethinking Text Line Recognition Modelscited by 45
  2. 2020Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognitioncited by 36
  3. 2019Candidate Fusion: Integrating Language Modelling into a Sequence-to-Sequence Handwritten Word Recognition Architecturecited by 12
  4. 2022AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networkscited by 12

Built on by

Not cited yet.