Improving CNN-RNN Hybrid Networks for Handwriting Recognition

Dutta, Kartik; Krishnan, Praveen; Mathew, Minesh; Jawahar, C. V.

doi:10.1109/icfhr-2018.2018.00023

Cited by 147 publications

(119 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

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%

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

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%

“…CNNs are sometimes used as feature extraction method for classifiers, in particular LSTMs [10,26,28,30]. In [30], a framework consisting of a deep CNN, LSTM layers as encoder/decoder, and a attention mechanism for isolated handwritten-word recognition is given.…”

Section: The State Of the Art On Handwriting Recognition Taskmentioning

confidence: 99%

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

“…Besides, combining neural network architecture with other classification is done to reach maximum accuracy [5]. A hybrid approach using deep learning and other machine learning would be a good interest to reach better accuracy [50][51][52][53][54].…”

Section: Classification In Handwriting Analysismentioning

confidence: 99%

Automated handwriting analysis based on pattern recognition: a survey

Samsuryadi¹,

Kurniawan²,

Mohamad³

2021

IJEECS

View full text Add to dashboard Cite

<span>Handwriting analysis has wide scopes include recruitment, medical diagnosis, forensic, psychology, and human-computer interaction. Computerized handwriting analysis makes it easy to recognize human personality and can help graphologists to understand and identify it. The features of handwriting use as input to classify a person’s personality traits. This paper discusses a pattern recognition point of view, in which different stages are described. The stages of study are data collection and pre-processing technique, feature extraction with associated personality characteristics, and the classification model. Therefore, the purpose of this paper is to present a review of the methods and their achievements used in various stages of a pattern recognition system. </span>

show abstract

“…Augmenting the input image by applying distortions in order to increase the variance and therefore, performance, is a very common use both in character and text recognition [25]- [27]. Examples of different distortions such as shifting, scaling, skewing, and compression is represented in the popular MNIST dataset.…”

Section: Data Augmentationmentioning

confidence: 99%