Handwritten Character Recognition Based on Decomposition Extreme Learning Machine
Handwritten character recognition(HCR) is an important branch of image recognition,which recognizes the handwritten characters with the data mining and machine learning technologies.Currently,the HCR methods mainly focus on the improvements of different deep learning models,where the multiple-layer...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial office of Computer Science
2022-11-01
|
| Series: | Jisuanji kexue |
| Subjects: | |
| Online Access: | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-11-148.pdf |
| _version_ | 1797845169118117888 |
|---|---|
| author | HE Yu-lin, LI Xu, JIN Yi, HUANG Zhe-xue |
| author_facet | HE Yu-lin, LI Xu, JIN Yi, HUANG Zhe-xue |
| author_sort | HE Yu-lin, LI Xu, JIN Yi, HUANG Zhe-xue |
| collection | DOAJ |
| description | Handwritten character recognition(HCR) is an important branch of image recognition,which recognizes the handwritten characters with the data mining and machine learning technologies.Currently,the HCR methods mainly focus on the improvements of different deep learning models,where the multiple-layer extreme learning machine(ML-ELM) has attracted the wide attention from the academia and industry due to its faster training speed and better recognition performance than deep belief net(DBN) and deep Boltzmann machine(DBM).However,the recognition performance of ML-ELM is severely influenced by the random weights when determining the input weights for each hidden-layer.This paper first proposes a decomposition ELM(DE-ELM) which is a shallow ELM training scheme based on the hidden-layer output matrix decomposition and then applies DE-ELM to deal with HCR problems,i.e.,handwritten digits in MNIST,handwritten digits and English letters in EMNIST,handwritten Japanese characters in KMNIST and K49-MNIST.In comparison with ML-ELM,DE-ELM reduces the randomness of ELM-based HCR model.Meanwhile,DE-ELM can obtain higher recognition accuracy than ML-ELM with the same training time and faster training speed than ML-ELM with the equal recognition accuracy.Experimental results demonstrate the feasibility and effectiveness of the proposed DE-ELM when dealing with HCR problems. |
| first_indexed | 2024-04-09T17:34:12Z |
| format | Article |
| id | doaj.art-f556c9fd478b4c35b018a0b72d466afe |
| institution | Directory Open Access Journal |
| issn | 1002-137X |
| language | zho |
| last_indexed | 2024-04-09T17:34:12Z |
| publishDate | 2022-11-01 |
| publisher | Editorial office of Computer Science |
| record_format | Article |
| series | Jisuanji kexue |
| spelling | doaj.art-f556c9fd478b4c35b018a0b72d466afe2023-04-18T02:32:50ZzhoEditorial office of Computer ScienceJisuanji kexue1002-137X2022-11-01491114815510.11896/jsjkx.211200265Handwritten Character Recognition Based on Decomposition Extreme Learning MachineHE Yu-lin, LI Xu, JIN Yi, HUANG Zhe-xue01 College of Computer Science & Software Engineering,Shenzhen University,Shenzhen,Guangdong 518060,China ;2 Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,Guangdong 518107,China ;3 Department of Criminal Science and Technology,Criminal Investigation Police University of China,Shenyang 110854,ChinaHandwritten character recognition(HCR) is an important branch of image recognition,which recognizes the handwritten characters with the data mining and machine learning technologies.Currently,the HCR methods mainly focus on the improvements of different deep learning models,where the multiple-layer extreme learning machine(ML-ELM) has attracted the wide attention from the academia and industry due to its faster training speed and better recognition performance than deep belief net(DBN) and deep Boltzmann machine(DBM).However,the recognition performance of ML-ELM is severely influenced by the random weights when determining the input weights for each hidden-layer.This paper first proposes a decomposition ELM(DE-ELM) which is a shallow ELM training scheme based on the hidden-layer output matrix decomposition and then applies DE-ELM to deal with HCR problems,i.e.,handwritten digits in MNIST,handwritten digits and English letters in EMNIST,handwritten Japanese characters in KMNIST and K49-MNIST.In comparison with ML-ELM,DE-ELM reduces the randomness of ELM-based HCR model.Meanwhile,DE-ELM can obtain higher recognition accuracy than ML-ELM with the same training time and faster training speed than ML-ELM with the equal recognition accuracy.Experimental results demonstrate the feasibility and effectiveness of the proposed DE-ELM when dealing with HCR problems.https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-11-148.pdfhandwritten character recognition|extreme learning machine|multiple layer extreme learning machine|deep lear-ning|feature extraction |
| spellingShingle | HE Yu-lin, LI Xu, JIN Yi, HUANG Zhe-xue Handwritten Character Recognition Based on Decomposition Extreme Learning Machine Jisuanji kexue handwritten character recognition|extreme learning machine|multiple layer extreme learning machine|deep lear-ning|feature extraction |
| title | Handwritten Character Recognition Based on Decomposition Extreme Learning Machine |
| title_full | Handwritten Character Recognition Based on Decomposition Extreme Learning Machine |
| title_fullStr | Handwritten Character Recognition Based on Decomposition Extreme Learning Machine |
| title_full_unstemmed | Handwritten Character Recognition Based on Decomposition Extreme Learning Machine |
| title_short | Handwritten Character Recognition Based on Decomposition Extreme Learning Machine |
| title_sort | handwritten character recognition based on decomposition extreme learning machine |
| topic | handwritten character recognition|extreme learning machine|multiple layer extreme learning machine|deep lear-ning|feature extraction |
| url | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-11-148.pdf |
| work_keys_str_mv | AT heyulinlixujinyihuangzhexue handwrittencharacterrecognitionbasedondecompositionextremelearningmachine |