Advanced Dense Text Detection in Graded Examinations Leveraging Chinese Character Components
The dense text detection and segmentation of Chinese characters has always been a research hotspot due to the complex background and diverse scenarios. In the field of education, the detection of handwritten Chinese characters is affected by background noise, texture interference, etc. Especially in...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/4/1818 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850081453483753472 |
|---|---|
| author | Renyuan Liu Yunyu Shi Xian Tang Xiang Liu |
| author_facet | Renyuan Liu Yunyu Shi Xian Tang Xiang Liu |
| author_sort | Renyuan Liu |
| collection | DOAJ |
| description | The dense text detection and segmentation of Chinese characters has always been a research hotspot due to the complex background and diverse scenarios. In the field of education, the detection of handwritten Chinese characters is affected by background noise, texture interference, etc. Especially in low-quality handwritten text, character overlap or occlusion makes the character boundaries blurred, which increases the difficulty of detection and segmentation; In this paper, an improved EAST network CEE (Components-ECA-EAST Network), which fuses the attention mechanism with the feature pyramid structure, is proposed based on the analysis of the structure of Chinese character mini-components. The ECA (Efficient Channel Attention) attention mechanism is incorporated during the feature extraction phase; in the feature fusion stage, the convolutional features are extracted from the self-constructed mini-component dataset and then fused with the feature pyramid in a cascade manner, and finally, Dice Loss is used as the regression task loss function. The above improvements comprehensively improve the performance of the network in detecting and segmenting the mini-components and subtle strokes of handwritten Chinese characters; The CEE model was tested on the self-constructed dataset with an accuracy of 84.6% and a mini-component mAP of 77.6%, which is an improvement of 7.4% and 8.4%, respectively, compared to the original model; The constructed dataset and improved model are well suited for applications such as writing grade examinations, and represent an important exploration of the development of educational intelligence. |
| format | Article |
| id | doaj-art-215f1a93b94140acaa36fe3c3d34e7be |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-215f1a93b94140acaa36fe3c3d34e7be2025-08-20T02:44:43ZengMDPI AGApplied Sciences2076-34172025-02-01154181810.3390/app15041818Advanced Dense Text Detection in Graded Examinations Leveraging Chinese Character ComponentsRenyuan Liu0Yunyu Shi1Xian Tang2Xiang Liu3College of Electrical and Electronic Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaCollege of Electrical and Electronic Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaCollege of Electrical and Electronic Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaCollege of Electrical and Electronic Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaThe dense text detection and segmentation of Chinese characters has always been a research hotspot due to the complex background and diverse scenarios. In the field of education, the detection of handwritten Chinese characters is affected by background noise, texture interference, etc. Especially in low-quality handwritten text, character overlap or occlusion makes the character boundaries blurred, which increases the difficulty of detection and segmentation; In this paper, an improved EAST network CEE (Components-ECA-EAST Network), which fuses the attention mechanism with the feature pyramid structure, is proposed based on the analysis of the structure of Chinese character mini-components. The ECA (Efficient Channel Attention) attention mechanism is incorporated during the feature extraction phase; in the feature fusion stage, the convolutional features are extracted from the self-constructed mini-component dataset and then fused with the feature pyramid in a cascade manner, and finally, Dice Loss is used as the regression task loss function. The above improvements comprehensively improve the performance of the network in detecting and segmenting the mini-components and subtle strokes of handwritten Chinese characters; The CEE model was tested on the self-constructed dataset with an accuracy of 84.6% and a mini-component mAP of 77.6%, which is an improvement of 7.4% and 8.4%, respectively, compared to the original model; The constructed dataset and improved model are well suited for applications such as writing grade examinations, and represent an important exploration of the development of educational intelligence.https://www.mdpi.com/2076-3417/15/4/1818Chinese character detectionmini componentsattention mechanismmulti-scale feature fusiondice loss |
| spellingShingle | Renyuan Liu Yunyu Shi Xian Tang Xiang Liu Advanced Dense Text Detection in Graded Examinations Leveraging Chinese Character Components Applied Sciences Chinese character detection mini components attention mechanism multi-scale feature fusion dice loss |
| title | Advanced Dense Text Detection in Graded Examinations Leveraging Chinese Character Components |
| title_full | Advanced Dense Text Detection in Graded Examinations Leveraging Chinese Character Components |
| title_fullStr | Advanced Dense Text Detection in Graded Examinations Leveraging Chinese Character Components |
| title_full_unstemmed | Advanced Dense Text Detection in Graded Examinations Leveraging Chinese Character Components |
| title_short | Advanced Dense Text Detection in Graded Examinations Leveraging Chinese Character Components |
| title_sort | advanced dense text detection in graded examinations leveraging chinese character components |
| topic | Chinese character detection mini components attention mechanism multi-scale feature fusion dice loss |
| url | https://www.mdpi.com/2076-3417/15/4/1818 |
| work_keys_str_mv | AT renyuanliu advanceddensetextdetectioningradedexaminationsleveragingchinesecharactercomponents AT yunyushi advanceddensetextdetectioningradedexaminationsleveragingchinesecharactercomponents AT xiantang advanceddensetextdetectioningradedexaminationsleveragingchinesecharactercomponents AT xiangliu advanceddensetextdetectioningradedexaminationsleveragingchinesecharactercomponents |