Assisting fuzzy offline handwriting recognition using recurrent belief propagation

Yilan Li, Zhe Li, Qinru Qiu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Recognizing handwritten texts is a challenging task due to many different writing styles and lack of clear boundary between adjacent characters. This problem has been tackled by many previous researchers using techniques such as deep learning networks and hidden Markov Models (HMM), etc. In this work we aim at offline fuzzy recognition of handwritten texts. A probabilistic inference network that performs recurrent belief propagation is developed to post process the recognition results of deep convolutional neural network (CNN) (e.g. LeNet) and form individual characters to words. The post processing has the capability of correcting deletion, insertion and replacement errors in a noisy input. The output of the inference network is a set of words with their probability of being the correct one. To limit the size of candidate words, a series of improvements have been made to the probabilistic inference network, including using a post Gaussian Mixture Estimation model to prune insignificant words. The experiments show that this model gives a competitively average accuracy of 85.5%, and the improvements provides 46.57% reduction of invalid candidate words.

Original languageEnglish (US)
Title of host publication2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509042401
DOIs
StatePublished - Feb 9 2017
Event2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016 - Athens, Greece
Duration: Dec 6 2016Dec 9 2016

Other

Other2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016
CountryGreece
CityAthens
Period12/6/1612/9/16

Fingerprint

Handwriting Recognition
Belief Propagation
Probabilistic Inference
Hidden Markov models
Neural networks
Gaussian Mixture
Processing
Post-processing
Markov Model
Deletion
Insertion
Replacement
Adjacent
Experiments
Neural Networks
Series
Inference
Propagation
Output
Model

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems and Management
  • Control and Optimization
  • Artificial Intelligence

Cite this

Li, Y., Li, Z., & Qiu, Q. (2017). Assisting fuzzy offline handwriting recognition using recurrent belief propagation. In 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016 [7850026] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSCI.2016.7850026

Assisting fuzzy offline handwriting recognition using recurrent belief propagation. / Li, Yilan; Li, Zhe; Qiu, Qinru.

2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016. Institute of Electrical and Electronics Engineers Inc., 2017. 7850026.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, Y, Li, Z & Qiu, Q 2017, Assisting fuzzy offline handwriting recognition using recurrent belief propagation. in 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016., 7850026, Institute of Electrical and Electronics Engineers Inc., 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016, Athens, Greece, 12/6/16. https://doi.org/10.1109/SSCI.2016.7850026
Li Y, Li Z, Qiu Q. Assisting fuzzy offline handwriting recognition using recurrent belief propagation. In 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016. Institute of Electrical and Electronics Engineers Inc. 2017. 7850026 https://doi.org/10.1109/SSCI.2016.7850026
Li, Yilan ; Li, Zhe ; Qiu, Qinru. / Assisting fuzzy offline handwriting recognition using recurrent belief propagation. 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{f6d67e1250fa40d4a17b3fcd86720380,
title = "Assisting fuzzy offline handwriting recognition using recurrent belief propagation",
abstract = "Recognizing handwritten texts is a challenging task due to many different writing styles and lack of clear boundary between adjacent characters. This problem has been tackled by many previous researchers using techniques such as deep learning networks and hidden Markov Models (HMM), etc. In this work we aim at offline fuzzy recognition of handwritten texts. A probabilistic inference network that performs recurrent belief propagation is developed to post process the recognition results of deep convolutional neural network (CNN) (e.g. LeNet) and form individual characters to words. The post processing has the capability of correcting deletion, insertion and replacement errors in a noisy input. The output of the inference network is a set of words with their probability of being the correct one. To limit the size of candidate words, a series of improvements have been made to the probabilistic inference network, including using a post Gaussian Mixture Estimation model to prune insignificant words. The experiments show that this model gives a competitively average accuracy of 85.5{\%}, and the improvements provides 46.57{\%} reduction of invalid candidate words.",
author = "Yilan Li and Zhe Li and Qinru Qiu",
year = "2017",
month = "2",
day = "9",
doi = "10.1109/SSCI.2016.7850026",
language = "English (US)",
booktitle = "2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Assisting fuzzy offline handwriting recognition using recurrent belief propagation

AU - Li, Yilan

AU - Li, Zhe

AU - Qiu, Qinru

PY - 2017/2/9

Y1 - 2017/2/9

N2 - Recognizing handwritten texts is a challenging task due to many different writing styles and lack of clear boundary between adjacent characters. This problem has been tackled by many previous researchers using techniques such as deep learning networks and hidden Markov Models (HMM), etc. In this work we aim at offline fuzzy recognition of handwritten texts. A probabilistic inference network that performs recurrent belief propagation is developed to post process the recognition results of deep convolutional neural network (CNN) (e.g. LeNet) and form individual characters to words. The post processing has the capability of correcting deletion, insertion and replacement errors in a noisy input. The output of the inference network is a set of words with their probability of being the correct one. To limit the size of candidate words, a series of improvements have been made to the probabilistic inference network, including using a post Gaussian Mixture Estimation model to prune insignificant words. The experiments show that this model gives a competitively average accuracy of 85.5%, and the improvements provides 46.57% reduction of invalid candidate words.

AB - Recognizing handwritten texts is a challenging task due to many different writing styles and lack of clear boundary between adjacent characters. This problem has been tackled by many previous researchers using techniques such as deep learning networks and hidden Markov Models (HMM), etc. In this work we aim at offline fuzzy recognition of handwritten texts. A probabilistic inference network that performs recurrent belief propagation is developed to post process the recognition results of deep convolutional neural network (CNN) (e.g. LeNet) and form individual characters to words. The post processing has the capability of correcting deletion, insertion and replacement errors in a noisy input. The output of the inference network is a set of words with their probability of being the correct one. To limit the size of candidate words, a series of improvements have been made to the probabilistic inference network, including using a post Gaussian Mixture Estimation model to prune insignificant words. The experiments show that this model gives a competitively average accuracy of 85.5%, and the improvements provides 46.57% reduction of invalid candidate words.

UR - http://www.scopus.com/inward/record.url?scp=85016061167&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016061167&partnerID=8YFLogxK

U2 - 10.1109/SSCI.2016.7850026

DO - 10.1109/SSCI.2016.7850026

M3 - Conference contribution

AN - SCOPUS:85016061167

BT - 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -