Optical Character Recognition of Power Equipment Nameplate for Energy Systems Based on Recurrent Neural Network
To address the problems of poor accuracy and response time of optical character recognition of power equipment nameplates for energy systems, which are ascribed to exposure to natural light and rainy weather, this paper proposes an optical character recognition algorithm for nameplates of power equi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-08-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2021.834283/full |
| _version_ | 1818484627823656960 |
|---|---|
| author | Xun Zhang Wanrong Bai Haoyang Cui |
| author_facet | Xun Zhang Wanrong Bai Haoyang Cui |
| author_sort | Xun Zhang |
| collection | DOAJ |
| description | To address the problems of poor accuracy and response time of optical character recognition of power equipment nameplates for energy systems, which are ascribed to exposure to natural light and rainy weather, this paper proposes an optical character recognition algorithm for nameplates of power equipment that integrates recurrent neural network theory and algorithms with complex environments. The collected image power equipment nameplates are preprocessed via graying and binarization in order to enhance the contrast among features of the power equipment nameplates and thus reduce the difficulty of positioning. This innovation facilitates the application of image recognition processing algorithms in power equipment nameplate positioning, character segmentation, and character recognition operations. Following segmentation of the power equipment nameplate and normalization thereof, the characters obtained are unified according to size, and then used as the input of the recurrent neural network (RNN); meanwhile, corresponding Chinese characters, numbers and alphabetic characters are used as the output. The text data recognition system model is realized via the trained RNN network, and is verified by inputting a large dataset into training. Compared with existing text data recognition systems, the algorithm proposed in this paper achieves a Chinese character recognition accuracy of 99.90%, an alphabetic and numeric character recognition accuracy of 99.30%, and a single image recognition speed of 2.15 ms. |
| first_indexed | 2024-12-10T15:57:41Z |
| format | Article |
| id | doaj.art-f5f0e89f5ade4d238313b2144f6bf5e2 |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-12-10T15:57:41Z |
| publishDate | 2022-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-f5f0e89f5ade4d238313b2144f6bf5e22022-12-22T01:42:34ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2022-08-01910.3389/fenrg.2021.834283834283Optical Character Recognition of Power Equipment Nameplate for Energy Systems Based on Recurrent Neural NetworkXun Zhang0Wanrong Bai1Haoyang Cui2Gansu Power Grid Co., Ltd., Electric Power Research Institute, Lanzhou, ChinaGansu Power Grid Co., Ltd., Electric Power Research Institute, Lanzhou, ChinaCollege of Electronic and Information Engineering, Shanghai University of Electric Power, Shanghai, ChinaTo address the problems of poor accuracy and response time of optical character recognition of power equipment nameplates for energy systems, which are ascribed to exposure to natural light and rainy weather, this paper proposes an optical character recognition algorithm for nameplates of power equipment that integrates recurrent neural network theory and algorithms with complex environments. The collected image power equipment nameplates are preprocessed via graying and binarization in order to enhance the contrast among features of the power equipment nameplates and thus reduce the difficulty of positioning. This innovation facilitates the application of image recognition processing algorithms in power equipment nameplate positioning, character segmentation, and character recognition operations. Following segmentation of the power equipment nameplate and normalization thereof, the characters obtained are unified according to size, and then used as the input of the recurrent neural network (RNN); meanwhile, corresponding Chinese characters, numbers and alphabetic characters are used as the output. The text data recognition system model is realized via the trained RNN network, and is verified by inputting a large dataset into training. Compared with existing text data recognition systems, the algorithm proposed in this paper achieves a Chinese character recognition accuracy of 99.90%, an alphabetic and numeric character recognition accuracy of 99.30%, and a single image recognition speed of 2.15 ms.https://www.frontiersin.org/articles/10.3389/fenrg.2021.834283/fullenergy systemsoptical character recognitionartificial intelligencepower equipment nameplaterecurrent neural network (RNN)deep learning |
| spellingShingle | Xun Zhang Wanrong Bai Haoyang Cui Optical Character Recognition of Power Equipment Nameplate for Energy Systems Based on Recurrent Neural Network Frontiers in Energy Research energy systems optical character recognition artificial intelligence power equipment nameplate recurrent neural network (RNN) deep learning |
| title | Optical Character Recognition of Power Equipment Nameplate for Energy Systems Based on Recurrent Neural Network |
| title_full | Optical Character Recognition of Power Equipment Nameplate for Energy Systems Based on Recurrent Neural Network |
| title_fullStr | Optical Character Recognition of Power Equipment Nameplate for Energy Systems Based on Recurrent Neural Network |
| title_full_unstemmed | Optical Character Recognition of Power Equipment Nameplate for Energy Systems Based on Recurrent Neural Network |
| title_short | Optical Character Recognition of Power Equipment Nameplate for Energy Systems Based on Recurrent Neural Network |
| title_sort | optical character recognition of power equipment nameplate for energy systems based on recurrent neural network |
| topic | energy systems optical character recognition artificial intelligence power equipment nameplate recurrent neural network (RNN) deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2021.834283/full |
| work_keys_str_mv | AT xunzhang opticalcharacterrecognitionofpowerequipmentnameplateforenergysystemsbasedonrecurrentneuralnetwork AT wanrongbai opticalcharacterrecognitionofpowerequipmentnameplateforenergysystemsbasedonrecurrentneuralnetwork AT haoyangcui opticalcharacterrecognitionofpowerequipmentnameplateforenergysystemsbasedonrecurrentneuralnetwork |