Handwriting recognition using cohort of LSTM and lexicon verification with extremely large lexicon

Stuner, Bruno; Chatelain, Clément; Paquet, Thierry

doi:10.1007/s11042-020-09198-6

Cited by 18 publications

(14 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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%

“…In [8], two architectures are used to generate more than a thousand networks to construct an ensemble. Each network is either a two-layer BiLSTM or a three-layer MDLSTMs.…”

Section: Ensemble Systemmentioning

confidence: 99%

“…Convolutional neural networks (CNNs) [1] and long shortterm memory networks (LSTM) [2] and its variants [3,4] have recently achieved impressive results [5][6][7]. This exceptional performance comes, however, at the cost of having an ensemble of, e.g., 100-2000 recognizers [8]. The high cost of training and operation brings to mind the question of whether less costly methods can be applied to boost the performance of handwriting recognizers.…”

Section: Introductionmentioning

confidence: 99%

“…Also, complicated machine-printed documents such as German, Fraktur, Egyptian hieroglyphs, and historical language are available in the Monk system. For such a system with almost 600 manuscripts, it is not feasible to use human effort for fine-tuning a model for each of the manuscripts to reach higher accuracy as [8]. An essential consideration is that it should be possible to add our suggested algorithm to the Monk system, with a minimum of required operational human effort.…”

Section: Introductionmentioning

confidence: 99%

See 4 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: 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%

“…In [8], two architectures are used to generate more than a thousand networks to construct an ensemble. Each network is either a two-layer BiLSTM or a three-layer MDLSTMs.…”

Section: Ensemble Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 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

show abstract

Character-based handwritten text transcription with attention networks

Poulos

Valle

2021

Neural Comput & Applic

View full text Add to dashboard Cite

Artificial intelligence in deep learning algorithms for multimedia analysis

Jeon

Anisetti

Damiani

et al. 2020

Multimed Tools Appl

View full text Add to dashboard Cite

Deep learning has gained a lot of research interest in artificial intelligence (AI) in many applications, such as image understanding, object detection, feature extraction, audio/ video processing, image demosaicking and denoising, overhead views in industrial applications. In addition, exploitation of deep learning in the field of data science, particularly in big data analytics focuses on high-level feature extraction and abstraction as data representation based on the hierarchical learning process. Moreover, deep learning is also designed to tackle supervised learning problems for a wide variety of tasks. How to reliably solve unsupervised tasks with a similar degree of success is an important issue to address. Such studies are investigated based on the adoption of parallel computing, i.e., GPUs and CPUs clusters.Various algorithms are already applied to achieve the desired goals. For instance, convolutional neural network has established superior performance on large-scale image and video classification. The supervised learning (semi/weakly) methods have expressively enhanced the performance when only a small amount of annotated data is available. In addition, correlation analysis, transfer learning, multi-tasking have proven

show abstract

Handwriting recognition using cohort of LSTM and lexicon verification with extremely large lexicon

Cited by 18 publications

References 39 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

Character-based handwritten text transcription with attention networks

Artificial intelligence in deep learning algorithms for multimedia analysis

Contact Info

Product

Resources

About