Self-Training of BLSTM with Lexicon Verification for Handwriting Recognition

Stuner, Bruno; Chatelain, Clément; Paquet, Thierry

doi:10.1109/icdar.2017.109

Cited by 12 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 5 shows the comparison of our method on the RIMES dataset with [8,27,29,30,35,38] in the terms of a number of characteristics: number of recognizers, homogeneity of the algorithm, word accuracy (%), and the complexity of the approach, not to be confused with computational complexity, e.g., deep learning method without extra complicated modules.…”

Section: Quantitative Resultsmentioning

confidence: 99%

“…1 A historical spelling of a word, Afdeeling, in the historical KdK dataset. The contemporary spelling of this word would be Afdeling Neural Computing and Applications ensembles with different RNN-based models using different feature extraction [7,26] and different decoding methods [8,14,[27][28][29].…”

Section: The State Of the Art On Handwriting Recognition Taskmentioning

confidence: 99%

“…The second is using CTC [11]. The approach of using an RNN followed by a CTC layer has been widely used [8,14,[27][28][29].…”

Section: The State Of the Art On Handwriting Recognition Taskmentioning

confidence: 99%

See 2 more Smart Citations

A limited-size ensemble of homogeneous CNN/LSTMs for high-performance word classification

Ameryan

Schomaker

2021

Neural Comput & Applic

View full text Add to dashboard Cite

The strength of long short-term memory neural networks (LSTMs) that have been applied is more located in handling sequences of variable length than in handling geometric variability of the image patterns. In this paper, an end-to-end convolutional LSTM neural network is used to handle both geometric variation and sequence variability. The best results for LSTMs are often based on large-scale training of an ensemble of network instances. We show that high performances can be reached on a common benchmark set by using proper data augmentation for just five such networks using a proper coding scheme and a proper voting scheme. The networks have similar architectures (convolutional neural network (CNN): five layers, bidirectional LSTM (BiLSTM): three layers followed by a connectionist temporal classification (CTC) processing step). The approach assumes differently scaled input images and different feature map sizes. Three datasets are used: the standard benchmark RIMES dataset (French); a historical handwritten dataset KdK (Dutch); the standard benchmark George Washington (GW) dataset (English). Final performance obtained for the word-recognition test of RIMES was 96.6%, a clear improvement over other state-of-the-art approaches which did not use a pre-trained network. On the KdK and GW datasets, our approach also shows good results. The proposed approach is deployed in the Monk search engine for historical-handwriting collections.

show abstract

Section: Quantitative Resultsmentioning

confidence: 99%

Section: The State Of the Art On Handwriting Recognition Taskmentioning

confidence: 99%

See 1 more Smart Citation

A limited-size ensemble of homogeneous CNN/LSTMs for high-performance word classification

Ameryan

Schomaker

2021

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…In this section, we evaluate our model on the RIMES and the KdK datasets in terms of coding scheme (Plain vs Extra separator) and ensemble/single network. Moreover, for the RIMES dataset, the results of our model is compared with the-state-of-the-art methods suggested in [8,21,[27][28][29]77]. In [31], very good result are reported.…”

Section: Quantitative Resultsmentioning

confidence: 95%

A limited-size ensemble of homogeneous CNN/LSTMs for high-performance word classification

Ameryan,

Schomaker

2019

Preprint

View full text Add to dashboard Cite

In recent years, long short-term memory neural networks (LSTMs) have been applied quite successfully to problems in handwritten text recognition. However, their strength is more located in handling sequences of variable length than in handling geometric variability of the image patterns. Furthermore, the best results for LSTMs are often based on large-scale training of an ensemble of network instances. In this paper, an end-to-end convolutional LSTM Neural Network is used to handle both geometric variation and sequence variability. We show that high performances can be reached on a common benchmark set by using proper data augmentation for just five such networks using a proper coding scheme and a proper voting scheme. The networks have similar architectures (Convolutional Neural Network (CNN): five layers, bidirectional LSTM (BiLSTM): three layers followed by a connectionist temporal classification (CTC) processing step). The approach assumes differently-scaled input images and different feature map sizes. Two datasets are used for evaluation of the performance of our algorithm: A standard benchmark RIMES dataset (French), and a historical handwritten dataset KdK (Dutch). Final performance obtained for the word-recognition test of RIMES was 96.6%, a clear improvement over other state-of-the-art approaches. On the KdK dataset, our approach also shows good results. The proposed approach is deployed in the Monk search engine for historical-handwriting collections.

show abstract

“…The range of applications that deal with structured output data is large. One can cite, among others, image labeling [12,26,31,35,49,16,24,39], statistical natural language processing (NLP) [17,33,38,37], bioinformatics [18,43], speech processing [34,47] and handwriting recognition [15,40]. Another example which is considered in the evaluation of our proposal in this paper is the facial landmark detection problem.…”

Section: Introductionmentioning

confidence: 99%

Deep neural networks regularization for structured output prediction

Belharbi¹,

Hérault²,

Chatelain³

et al. 2018

Neurocomputing

View full text Add to dashboard Cite

A deep neural network model is a powerful framework for learning representations. Usually, it is used to learn the relation x → y by exploiting the regularities in the input x. In structured output prediction problems, y is multi-dimensional and structural relations often exist between the dimensions. The motivation of this work is to learn the output dependencies that may lie in the output data in order to improve the prediction accuracy. Unfortunately, feedforward networks are unable to exploit the relations between the outputs. In order to overcome this issue, we propose in this paper a regularization scheme for training neural networks for these particular tasks using a multi-task framework. Our scheme aims at incorporating the learning of the output representation y in the training process in an unsupervised fashion while learning the supervised mapping function x → y. We evaluate our framework on a facial landmark detection problem which is a typical structured output task. We show over two public challenging datasets (LFPW and HELEN) that our regularization scheme improves the generalization of deep neural networks and accelerates their training. The use of unlabeled data and label-only data is also explored, showing an additional improvement of the results. We provide an opensource implementation 2 of our framework.

show abstract

Self-Training of BLSTM with Lexicon Verification for Handwriting Recognition

Cited by 12 publications

References 18 publications

A limited-size ensemble of homogeneous CNN/LSTMs for high-performance word classification

A limited-size ensemble of homogeneous CNN/LSTMs for high-performance word classification

A limited-size ensemble of homogeneous CNN/LSTMs for high-performance word classification

Deep neural networks regularization for structured output prediction

Contact Info

Product

Resources

About