International Scientific Journal

Authors of this Paper

External Links


Aiming at the problem that the recognition accuracy based on convolutional neural network of thermal power system record text is not high, a method of thermal power system record text recognition based on residual and multi-scale feature combination was proposed and implemented. Combined with the residual, a new network is designed to replace the traditional convolutional neural network and improve the feature extraction ability of the network. The 1 × 1 convolution core was used to increase the network depth and reduce the parameters instead of the 3 × 3 convolution core. The network order of each layer in residual block was adjusted so that the network representation ability can be improved. Combining feature information of different scales and retaining more vertical feature information, the classification accuracy of the network is improved. Experiments on the self-built image data set of thermal power system records show that the proposed network model improves the accuracy by 11% compared with convolutional recurrent neural network, and has better robustness to image distortion and blurring.
PAPER REVISED: 2019-01-25
PAPER ACCEPTED: 2019-01-05
CITATION EXPORT: view in browser or download as text file
THERMAL SCIENCE YEAR 2019, VOLUME 23, ISSUE Issue 5, PAGES [2631 - 2640]
  1. Mori S, et al., Historical review of OCR research and development. Proceedings of the IEEE, 80(1992), 7, pp. 1029-1058.
  2. Zhang Y, et al., Scene text recognition with deeper convolutional neural networks
  3. Yao C, et al., Strokelets: A Learned Multi-scale Representation for Scene Text Recognition
  4. Heutte L, et al., A structural/statistical feature based vector for handwritten character recognition
  5. Das N, et al., A statistical-topological feature combination for recognition of handwritten numerals
  6. YunTao W, et al., End-to-End Text Recognition with Convolutional Neural Networks
  7. Jaderberg M, et al., Reading Text in the Wild with Convolutional Neural Networks
  8. Ahranjany S S, et al., A very high accuracy handwritten character recognition system for Farsi/Arabic digits using Convolutional Neural Networks
  9. Wang Z, et al., Trilateral constrained sparse representation for Kinect depth hole filling. Pattern Recognit Lett 65 (2015), pp.95-102
  10. Liu H, et al., Distributed source localization under anchor position uncertainty. Chin J Electron 23 (2014), 1, pp. 93-96
  11. Zhong L, et al., OHRank: an algorithm integrating mentality and influence of opinion holder for opinion mining. Chin J Electron 22 (2013), 4, pp. 655-660
  12. Peng, Li , et al. A robust method for estimating image geometry with local structure constraint. IEEE Access 99(2018), PP. 1-10.
  13. Lu, Tao , et al. Robust Face Super-Resolution via Locality-constrained Low-rank Representation. IEEE Access (2017), pp. 1-10.
  14. Wang Z, et al., Trilateral constrained sparse representation for Kinect depth hole filling
  15. YunTao W, et al., Utilizing Principal Singular Vectors for 2D DOA Estimation in Single Snapshot Case with Uniform Rectangular Array
  16. YunTao W, et al., HOSVD-Based Subspace Algorithm for Multidimensional Frequency Estimation Without Pairing Parameters, CHINESE JOURNAL OF ELECTRONICS, 23 (2014), 4, pp. 729-734
  17. Jiao L, et al., Offline handwritten English character recognition based on convolutional neural network
  18. Yu N, et al., Handwritten digits recognition base on improved LeNet5
  19. Yann LeCun, Learning Invariant Feature Hierarchies, in Fusiello, Andrea and Murino, Vittorio and Cucchiara, Rita (Eds), European Conference on Computer Vision (ECCV 2012), 7583 (2012), pp.496-505
  20. T. Wang, et al., End-to-end text recognition with convolutional neural networks, Proceedings of the 21st International Conference on Pattern Recognition(ICPR 2012. Tsukuba Science City, JAPAN), (2012)
  21. Shi B, et al., An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
  22. He K, et al., Deep Residual Learning for Image Recognition
  23. Ioffe S, et al., Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
  24. Hochreiter S, et al., Long short-term memory.Neural Computation, 9 (1997), 8, pp. 1735-1780.
  25. Graves A, Gomez F. Connectionist temporal classification:labelling unsegmented sequence data with recurrent neural networks
  26. Kingma D,Ba J.Adam:A method for stochastic optimization

© 2024 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence