Spotting handwritten words and REGEX using a two stage BLSTM-HMM architecture

Bideault, Gautier; Mioulet, Luc; Chatelain, Clément; Paquet, Thierry

doi:10.1117/12.2075796

Cited by 5 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Fig. 23, the probabilities of target sample T 1 /T 2 and training sample I C could be calculated using (8) and (9), respectively: log(max…”

Section: E: Target Sample Classification Predictionmentioning

confidence: 99%

“…Principal component analysis (PCA) is used to extract the character components in fixed-size images [7], [8]. In a study by Bideault et al [9], a histogram of oriented gradients (HOG) was proposed for character feature extraction. Graves and Schmidhuber [10] used the feature extraction of column pixels for the character image, such as the mean, centroid, conversion, and fusion.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recognition of Handwritten Chinese Characters Based on Concept Learning

Liang

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Many deep-learning character recognition methods have been developed over the past few years. Chinese characters are widely used in many countries; however, the deep-learning-based Chinese character recognition methods are faced with various problems, such as a large amount of data required for training, numerous parameters, and a large consumption of computing resources. Concept learning is a hominine learning approach. Unlike existing deep-learning models, conceptual model learning can be realized by using as little as one sample. This paper is the first to propose a handwritten Chinese character recognition method based on concept learning. Different from the existing image representation-based character recognition methods, the proposed method builds a meta stroke library with prior knowledge, and then, presents a Chinese character conceptual model based on stroke relationship learning using a character stroke extraction method and Bayesian program learning. During character recognition, Monte Carlo Markov chain sampling is utilized to obtain the character generation model for each character conceptual. This generation model can calculate the probability of the target and training characters being the same classification, and thereby determines the classification of the target character. The experimental results indicate that, with the proposed method, the conceptual model of each character can be built for character classification prediction using as few as one character sample. Our approach obtains better performance than the state-of-the-art methods on ICDAR-2013 competition dataset. INDEX TERMS Character conceptual model, character recognition, concept learning, stroke extraction.

show abstract

“…As shown in Fig. 23, the probabilities of target sample T 1 /T 2 and training sample I C could be calculated using (8) and (9), respectively: log(max…”

Section: E: Target Sample Classification Predictionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Recognition of Handwritten Chinese Characters Based on Concept Learning

Liang

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…For example, a sequence composed of 12 frames of 1 pixel width is transformed into a sequence of length 3 corresponding to 3 frames of 4 pixels width. As input features, we use histogram of oriented gradients (HOG) [45] that have demonstrated their efficiency for handwriting recognition [46]. Images are normalized to 64 pixels height.…”

Section: Architecturementioning

confidence: 99%

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

Stuner¹,

Chatelain²,

Paquet³

2016

Preprint

Self Cite

View full text Add to dashboard Cite

State-of-the-art methods for handwriting recognition are based on Long Short Term Memory (LSTM) recurrent neural networks (RNN), which now provides very impressive character recognition performance. The character recognition is generally coupled with a lexicon driven decoding process which integrates dictionaries. Unfortunately these dictionaries are limited to hundred of thousands words for the best systems, which prevent from having a good language coverage, and therefore limit the global recognition performance. In this article, we propose an alternative to the lexicon driven decoding process based on a lexicon verification process, coupled with an original cascade architecture. The cascade is made of a large number of complementary networks extracted from a single training (called cohort), making the learning process very light. The proposed method achieves new state-of-the art word recognition performance on the Rimes and IAM datasets. Dealing with gigantic lexicon of 3 millions words, the methods also demonstrates interesting performance with a fast decision stage.

show abstract

“…Recently, Bideault et al published a similar approach to ours in [1]. They proposed an HMM -BDLSTM hybrid model for word spotting exploiting regular expressions.…”

Section: Introductionmentioning

confidence: 98%

Regular expressions for decoding of neural network outputs

et al. 2016

View full text Add to dashboard Cite

This article proposes a convenient tool for decoding the output of neural networks trained by Connectionist Temporal Classification (CTC) for handwritten text recognition. We use regular expressions to describe the complex structures expected in the writing. The corresponding finite automata are employed to build a decoder. We analyze theoretically which calculations are relevant and which can be avoided. A great speed-up results from an approximation. We conclude that the approximation most likely fails if the regular expression does not match the ground truth which is not harmful for many applications since the low probability will be even underestimated. The proposed decoder is very efficient compared to other decoding methods. The variety of applications reaches from information retrieval to full text recognition. We refer to applications where we integrated the proposed decoder successfully.

show abstract

Spotting handwritten words and REGEX using a two stage BLSTM-HMM architecture

Cited by 5 publications

References 21 publications

Recognition of Handwritten Chinese Characters Based on Concept Learning

Recognition of Handwritten Chinese Characters Based on Concept Learning

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

Regular expressions for decoding of neural network outputs

Contact Info

Product

Resources

About