EASTER: Simplifying Text Recognition using only 1D Convolutions

Chaudhary, Kartik; Bali, Raghav

doi:10.21428/594757db.65eda33c

Cited by 3 publications

(4 citation statements)

References 22 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The architecture of Easter2.0 is inspired by the design of Easter [1] which is a fully convolutional architecture with only 1D convolutions. However, there are some key differences in our proposed Easter2.0 architecture.…”

Section: Model Architecturementioning

confidence: 99%

“…The experiments are carried out with Tensorflow [24] toolkit with a weighted Connectionist Temporal Classification (w-CTC)(similar to [1]) as loss function. We have used Adam optimizer with an initial learning rate of 10 −3 and a batch size of 32 with early stopping criteria.…”

Section: Training Detailsmentioning

confidence: 99%

“…Easter2.0(Ours) T ransf ormer [7] Seq2Seq [7] GRCL [2] F CN/CT C [1] Figure 1: Few-shot training and performance comparison in terms of case-sensitive CER with different portions of publicly available IAM-Training data.…”

mentioning

confidence: 99%

“…In the context of handwritten text recognition, very few works have used entirely convolutional architectures devoid of any recurrence [1,4,5]. Some recent works [2,15] combine CNNs with a gating mechanism to compensate for the dependency on LSTM cells, known as Gated Convolutional Neural Networks (GCN).…”

mentioning

confidence: 99%

See 3 more Smart Citations

Easter2.0: Improving convolutional models for handwritten text recognition

Chaudhary¹,

Bali²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Convolutional Neural Networks (CNN) have shown promising results for the task of Handwritten Text Recognition (HTR) but they still fall behind Recurrent Neural Networks (RNNs)/Transformer based models in terms of performance. In this paper, we propose a CNN based architecture that bridges this gap. Our work, Easter2.0, is composed of multiple layers of 1D Convolution, Batch Normalization, ReLU, Dropout, Dense Residual connection, Squeeze-and-Excitation module and make use of Connectionist Temporal Classification (CTC) loss. In addition to the Easter2.0 architecture, we propose a simple and effective data augmentation technique 'Tiling and Corruption (T ACo)' relevant for the task of HTR/OCR. Our work achieves state-of-the-art results on IAM handwriting database when trained using only publicly available training data. In our experiments, we also present the impact of T ACo augmentations and Squeeze-and-Excitation (SE) on text recognition accuracy. We further show that Easter2.0 is suitable for few-shot learning tasks and outperforms current best methods including Transformers when trained on limited amount of annotated data. Code and model is available at: https://github.com/kartikgill/Easter2.

show abstract

Section: Model Architecturementioning

confidence: 99%

Section: Training Detailsmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Easter2.0: Improving convolutional models for handwritten text recognition

Chaudhary¹,

Bali²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Towards Robust Handwritten Text Recognition with On-the-fly User Participation

Mondal

Saluja

Jawahar

2022

Proceedings of the Thirteenth Indian Conference on Computer Vision, Graphics and Image Processing

View full text Add to dashboard Cite

Recurrent Neural Networks with Continuous Learning in Problems of News Streams Multifunctional Processing

Osipov¹,

Kuleshov²,

Miloserdov³

et al. 2022

View full text Add to dashboard Cite

The main task of using neural networks is the prompt and accurate solution of various creative tasks, including the analysis and synthesis of news flows, while maintaining the continuity of learning. The result of such processing can be digests, filtered news streams, as well as event forecasts that allow for proactivity in management decisions. Known methods of news processing by neural networks and technical solutions that implement them do not fully provide a solution to the problems that arise in this area. It is necessary to expand their functionality, and improve the space-time signal binding in recurrent neural networks. When processing news flows, simultaneously with continuous training of recurrent neural networks, selection, recognition, restoration, prediction and synthesis of news should be carried out. To reduce the severity of the problem, a promising method of multifunctional processing of news flows is proposed using recurrent neural networks with a logical organization of layers and continuous learning. The method is based on the development of associative processing of textual information in streaming recurrent neural networks with controlled elements. The key features of this method are the multifunctional processing of information flows with changing laws of news appearance. The method provides for operational selection, recognition, restoration, forecasting and synthesis of news based on deep associative continuous processing of links between text elements. The neural network system that implements the proposed method differs from the known solutions by new elements, connections between them, as well as by the functions performed. The results of the experiments confirmed the extended functionality of the method. New features of processing news texts by streaming RNNs are revealed. The proposed solutions can be used to create a new generation of intelligent systems not only for word processing, but also for other types of information.

show abstract

EASTER: Simplifying Text Recognition using only 1D Convolutions

Cited by 3 publications

References 22 publications

Easter2.0: Improving convolutional models for handwritten text recognition

Easter2.0: Improving convolutional models for handwritten text recognition

Towards Robust Handwritten Text Recognition with On-the-fly User Participation

Recurrent Neural Networks with Continuous Learning in Problems of News Streams Multifunctional Processing

Contact Info

Product

Resources

About