Deep Convolutional Neural Network Based Hidden Markov Model for Offline Handwritten Chinese Text Recognition

2017 ◽  
Author(s):  
Zi-Rui Wang ◽  
Jun Du ◽  
Jin-Shui Hu ◽  
Yu-Long Hu
Keyword(s):  
Neural Network ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Convolutional Neural Network ◽  
Chinese Text ◽  
Hidden Markov ◽  
Deep Convolutional Neural Network ◽  
Text Recognition ◽  
Chinese Text Recognition

scholarly journals A Method of Combining Hidden Markov Model and Convolutional Neural Network for the 5G RCS Message Filtering

2021 ◽  
Vol 11 (14) ◽  
pp. 6350
Author(s):  
Bibu Gao ◽  
Wenqiang Zhang
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Convolutional Neural Network ◽  
Hidden Markov ◽  
Short Text ◽  
Feature Extraction Algorithm ◽  
Extraction Algorithm ◽  
Message Service

As one of the 5G applications, rich communication suite (RCS), known as the next generation of Short Message Service (SMS), contains multimedia and interactive information for a better user experience. Meanwhile, the RCS industry worries that spammers may migrate their spamming misdeeds to RCS messages, the complexity of which challenges the filtering technology because each of them contains hundreds of fields with various types of data, such as texts, images and videos. Among the data, the hundreds of fields of text data contain the main content, which is adequate and more efficient for combating spam. This paper first discusses the text fields, which possibly contain spam information, then use the hidden Markov model (HMM) to weight the fields and finally use convolutional neural network (CNN) to classify the RCS messages. In the HMM step, the text fields are treated differently. The short texts of these fields are represented as feature weight sequences extracted by a feature extraction algorithm based on a probability density function. Then, the proposed HMM learns the weight sequence and produces a proper weight for each short text. Other text fields with fewer words are also weighted by the feature extraction algorithm. In the CNN step, all these feature weights first construct the RCS message matrix. The matrices of the training RCS messages are used as the CNN model inputs for learning and the matrices of testing messages are used as the trained CNN model inputs for RCS message property prediction. Four optimization technologies are introduced into the CNN classification process. Promising experiment results are achieved on the real industrial data.

Sign in / Sign up

Export Citation Format

Share Document