Filtering Approaches and Mish Activation Function Applied on Handwritten Chinese Character Recognition
Handwritten Chinese Characters (HCC) have recently received much attention as a global means of exchanging information and knowledge. The start of the information age has increased the number of paper documents that must be electronically saved and shared. The recognition accuracy of online handwrit...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ediciones Universidad de Salamanca
2024-11-01
|
| Series: | Advances in Distributed Computing and Artificial Intelligence Journal |
| Subjects: | |
| Online Access: | https://revistas.usal.es/cinco/index.php/2255-2863/article/view/31218 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590584418664448 |
|---|---|
| author | Zhong Yingna Kauthar Mohd Daud Kohbalan Moorthy Ain Najiha Mohamad Nor |
| author_facet | Zhong Yingna Kauthar Mohd Daud Kohbalan Moorthy Ain Najiha Mohamad Nor |
| author_sort | Zhong Yingna |
| collection | DOAJ |
| description | Handwritten Chinese Characters (HCC) have recently received much attention as a global means of exchanging information and knowledge. The start of the information age has increased the number of paper documents that must be electronically saved and shared. The recognition accuracy of online handwritten Chinese characters has reached its limit as online characters are more straightforward than offline characters. Furthermore, online character recognition enables stronger involvement and flexibility than offline characters. Deep learning techniques, such as convolutional neural networks (CNN), have superseded conventional Handwritten Chinese Character Recognition (HCCR) solutions, as proven in image identification. Nonetheless, because of the large number of comparable characters and styles, there is still an opportunity to improve the present recognition accuracy by adopting different activation functions, including Mish, Sigmoid, Tanh, and ReLU. The main goal of this study is to apply a filter and activation function that has a better impact on the recognition system to improve the performance of the recognition CNN model. In this study, we implemented different filter techniques and activation functions in CNN to offline Chinese characters to understand the effects of the model's recognition outcome. Two CNN layers are proposed given that they achieve comparative performances using fewer-layer CNN. The results demonstrate that the Weiner filter has better recognition performance than the median and average filters. Furthermore, the Mish activation function performs better than the Sigmoid, Tanh, and ReLU functions. |
| format | Article |
| id | doaj-art-193d646d28b14a7b8e4317323516d5b9 |
| institution | Kabale University |
| issn | 2255-2863 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Ediciones Universidad de Salamanca |
| record_format | Article |
| series | Advances in Distributed Computing and Artificial Intelligence Journal |
| spelling | doaj-art-193d646d28b14a7b8e4317323516d5b92025-01-23T11:25:18ZengEdiciones Universidad de SalamancaAdvances in Distributed Computing and Artificial Intelligence Journal2255-28632024-11-0113e31218e3121810.14201/adcaij.3121836690Filtering Approaches and Mish Activation Function Applied on Handwritten Chinese Character RecognitionZhong Yingna0Kauthar Mohd Daud1Kohbalan Moorthy2Ain Najiha Mohamad Nor3Fakulti Teknologi dan Sains Maklumat, Universiti Kebangsaan Malaysia, Bangi, Selangor, 43600Fakulti Teknologi dan Sains Maklumat, Universiti Kebangsaan Malaysia, Bangi, Selangor, 43600Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah, Pekan, Pahang, 26600Fakulti Teknologi dan Sains Maklumat, Universiti Kebangsaan Malaysia, Bangi, Selangor, 43600Handwritten Chinese Characters (HCC) have recently received much attention as a global means of exchanging information and knowledge. The start of the information age has increased the number of paper documents that must be electronically saved and shared. The recognition accuracy of online handwritten Chinese characters has reached its limit as online characters are more straightforward than offline characters. Furthermore, online character recognition enables stronger involvement and flexibility than offline characters. Deep learning techniques, such as convolutional neural networks (CNN), have superseded conventional Handwritten Chinese Character Recognition (HCCR) solutions, as proven in image identification. Nonetheless, because of the large number of comparable characters and styles, there is still an opportunity to improve the present recognition accuracy by adopting different activation functions, including Mish, Sigmoid, Tanh, and ReLU. The main goal of this study is to apply a filter and activation function that has a better impact on the recognition system to improve the performance of the recognition CNN model. In this study, we implemented different filter techniques and activation functions in CNN to offline Chinese characters to understand the effects of the model's recognition outcome. Two CNN layers are proposed given that they achieve comparative performances using fewer-layer CNN. The results demonstrate that the Weiner filter has better recognition performance than the median and average filters. Furthermore, the Mish activation function performs better than the Sigmoid, Tanh, and ReLU functions.https://revistas.usal.es/cinco/index.php/2255-2863/article/view/31218activation functionsconvolutional neural networkcnnfiltering approachesmachine learning |
| spellingShingle | Zhong Yingna Kauthar Mohd Daud Kohbalan Moorthy Ain Najiha Mohamad Nor Filtering Approaches and Mish Activation Function Applied on Handwritten Chinese Character Recognition Advances in Distributed Computing and Artificial Intelligence Journal activation functions convolutional neural network cnn filtering approaches machine learning |
| title | Filtering Approaches and Mish Activation Function Applied on Handwritten Chinese Character Recognition |
| title_full | Filtering Approaches and Mish Activation Function Applied on Handwritten Chinese Character Recognition |
| title_fullStr | Filtering Approaches and Mish Activation Function Applied on Handwritten Chinese Character Recognition |
| title_full_unstemmed | Filtering Approaches and Mish Activation Function Applied on Handwritten Chinese Character Recognition |
| title_short | Filtering Approaches and Mish Activation Function Applied on Handwritten Chinese Character Recognition |
| title_sort | filtering approaches and mish activation function applied on handwritten chinese character recognition |
| topic | activation functions convolutional neural network cnn filtering approaches machine learning |
| url | https://revistas.usal.es/cinco/index.php/2255-2863/article/view/31218 |
| work_keys_str_mv | AT zhongyingna filteringapproachesandmishactivationfunctionappliedonhandwrittenchinesecharacterrecognition AT kautharmohddaud filteringapproachesandmishactivationfunctionappliedonhandwrittenchinesecharacterrecognition AT kohbalanmoorthy filteringapproachesandmishactivationfunctionappliedonhandwrittenchinesecharacterrecognition AT ainnajihamohamadnor filteringapproachesandmishactivationfunctionappliedonhandwrittenchinesecharacterrecognition |