Deep Learning-Aided OCR Techniques for Chinese Uppercase Characters in the Application of Internet of Things

Optical character recognition (OCR) has become one of the most important techniques in computer vision, given that it can easily obtain digital information from various images on the Internet of Things (IoT). However, existing OCR techniques pose a big challenge in the recognition of the Chinese uppercase characters due to their poor performance. In order to solve the problem, this paper proposes a deep learning-aided OCR technique for improving recognition accuracy. First, we generate a database of the Chinese uppercase characters to train four neural networks: a convolution neural network (CNN), a visual geometry group, a capsule network, and a residual network. Second, the four networks are tested on the generated dataset in terms of accuracy, network weight, and test time. Finally, in order to reduce test time and save computational resources, we also develop a lightweight CNN method to prune the network weight by 96.5% while reducing accuracy by no more than 1.26%.

[1]  Félix J. García Clemente,et al.  A Self-Adaptive Deep Learning-Based System for Anomaly Detection in 5G Networks , 2018, IEEE Access.

[2]  Guan Gui,et al.  Anti-Shadowing Resource Allocation for General Mobile Cognitive Radio Networks , 2018, IEEE Access.

[3]  Nei Kato,et al.  An Internet of Things Traffic-Based Power Saving Scheme in Cloud-Radio Access Network , 2019, IEEE Internet of Things Journal.

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Tao Jiang,et al.  Deep learning for wireless physical layer: Opportunities and challenges , 2017, China Communications.

[6]  Kartika Gunadi,et al.  The Application of Deep Convolutional Denoising Autoencoder for Optical Character Recognition Preprocessing , 2017, 2017 International Conference on Soft Computing, Intelligent System and Information Technology (ICSIIT).

[7]  Joohyung Lee,et al.  Deep Learning Based Pilot Allocation Scheme (DL-PAS) for 5G Massive MIMO System , 2018, IEEE Communications Letters.

[8]  Qi Li,et al.  Recognition of Offline Handwritten Chinese Characters Using the Tesseract Open Source OCR Engine , 2016, 2016 8th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC).

[9]  C. V. Jawahar,et al.  Unconstrained scene text and video text recognition for Arabic script , 2017, 2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR).

[10]  Nader Karimi,et al.  Simplified Neural Network Based on Auxiliary Layer and Adaptive Pruning Rate , 2018, Electrical Engineering (ICEE), Iranian Conference on.

[11]  Yogesh R. Risodkar,et al.  Deep Learning Based Gujarati Handwritten Character Recognition , 2018, 2018 International Conference On Advances in Communication and Computing Technology (ICACCT).

[12]  Gaurav Jaiswal,et al.  Ensemble of Hybrid CNN-ELM Model for Image Classification , 2018, 2018 5th International Conference on Signal Processing and Integrated Networks (SPIN).

[13]  Wataru Ohyama,et al.  An Impact of OCR Errors on Automated Classification of OCR Japanese Texts with Parts-of-Speech Analysis , 2011, 2011 International Conference on Document Analysis and Recognition.

[14]  Mianxiong Dong,et al.  A Hierarchical Security Framework for Defending Against Sophisticated Attacks on Wireless Sensor Networks in Smart Cities , 2016, IEEE Access.

[15]  Malay Kishore Dutta,et al.  Handwriting comenia script recognition with convolutional neural network , 2017, 2017 40th International Conference on Telecommunications and Signal Processing (TSP).

[16]  Anisha Mohammed,et al.  Text recognition using poisson filtering and edge enhanced maximally stable extremal regions , 2017, 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT).

[17]  Jianhua Li,et al.  Big Data Analysis-Based Secure Cluster Management for Optimized Control Plane in Software-Defined Networks , 2018, IEEE Transactions on Network and Service Management.

[18]  Nei Kato,et al.  Value Iteration Architecture Based Deep Learning for Intelligent Routing Exploiting Heterogeneous Computing Platforms , 2019, IEEE Transactions on Computers.

[19]  Ignazio Gallo,et al.  Hand Written Characters Recognition via Deep Metric Learning , 2018, 2018 13th IAPR International Workshop on Document Analysis Systems (DAS).

[20]  Min-Yuh Day,et al.  Analysis of identifying linguistic phenomena for recognizing inference in text , 2014, Proceedings of the 2014 IEEE 15th International Conference on Information Reuse and Integration (IEEE IRI 2014).

[21]  Rui Peng,et al.  Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures , 2016, ArXiv.

[22]  Shashank Shetty,et al.  Ote-OCR based text recognition and extraction from video frames , 2014, 2014 IEEE 8th International Conference on Intelligent Systems and Control (ISCO).

[23]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[24]  Guan Gui,et al.  Deep Cognitive Perspective: Resource Allocation for NOMA-Based Heterogeneous IoT With Imperfect SIC , 2019, IEEE Internet of Things Journal.

[25]  Guan Gui,et al.  Deep Learning for an Effective Nonorthogonal Multiple Access Scheme , 2018, IEEE Transactions on Vehicular Technology.

[26]  Guan Gui,et al.  Deep Learning for Super-Resolution Channel Estimation and DOA Estimation Based Massive MIMO System , 2018, IEEE Transactions on Vehicular Technology.

[27]  Xianfu Chen,et al.  Deep Reinforcement Learning for Resource Management in Network Slicing , 2018, IEEE Access.

[28]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[29]  Jun Wu,et al.  NLES: A Novel Lifetime Extension Scheme for Safety-Critical Cyber-Physical Systems Using SDN and NFV , 2019, IEEE Internet of Things Journal.

[30]  Jian Zhang,et al.  License Plate Segmentation and Recognition of Chinese Vehicle Based on BPNN , 2016, 2016 12th International Conference on Computational Intelligence and Security (CIS).

[31]  Ab Al-Hadi Ab Rahman,et al.  Improved optical character recognition with deep neural network , 2018, 2018 IEEE 14th International Colloquium on Signal Processing & Its Applications (CSPA).

[32]  Nei Kato,et al.  Historical Hand-Written String Recognition by Non-linear Discriminant Analysis using Kernel Feature Selection , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[33]  Chen Xu,et al.  MS-CapsNet: A Novel Multi-Scale Capsule Network , 2018, IEEE Signal Processing Letters.