A Neural Network Model for Text Detection in Chinese Drug Package Insert
The text information in the medical photocopies is of great significance to the construction of medical digital platform. Text region detection, the very first step of extracting medical photocopies information, is functional to detect text area or locate text instance on the sample. Researchers hav...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9373364/ |
| _version_ | 1818727652851187712 |
|---|---|
| author | Haiwen Wu Ri-Gui Zhou Yaochong Li |
| author_facet | Haiwen Wu Ri-Gui Zhou Yaochong Li |
| author_sort | Haiwen Wu |
| collection | DOAJ |
| description | The text information in the medical photocopies is of great significance to the construction of medical digital platform. Text region detection, the very first step of extracting medical photocopies information, is functional to detect text area or locate text instance on the sample. Researchers have done a lot works on text area detection in natural scenes, yet few of them in turn pay attention to the medical photocopies scenario which is urgent to be settled. Here, a text line area detection dataset based on Chinese medical photocopies (CMPTD) are created and a fine-grained text line region detection model based on multi-scale feature extraction and fusion are proposed in this paper. The detection model consists of three parts. The first part is feature extraction module. Cspdarknet53 in You Only Look Once version 4 (YOLOv4) is used as the backbone network of our model, and the spatial pyramid pool strategy is used to extract multi-scale features to enhance the robustness of the model. The second part is feature fusion module. By referring to the PANet structure, the three effective feature layers in feature extraction module are fused repeatedly. The last part is prediction module. The network outputs a series of fine-grained text proposals by referring to the CTPN structure, which are connected into text lines by text line construction algorithm. We experimentally demonstrate the effectiveness of the detection model with the precision of 92.46% and the recall of 91.74% in the text detection task of the dataset CMPTD. |
| first_indexed | 2024-12-17T22:17:31Z |
| format | Article |
| id | doaj.art-0429b84fc00d48039a4ed86c9cb5ca0f |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T22:17:31Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-0429b84fc00d48039a4ed86c9cb5ca0f2022-12-21T21:30:34ZengIEEEIEEE Access2169-35362021-01-019397813979110.1109/ACCESS.2021.30645649373364A Neural Network Model for Text Detection in Chinese Drug Package InsertHaiwen Wu0https://orcid.org/0000-0003-3961-2429Ri-Gui Zhou1https://orcid.org/0000-0002-8894-8108Yaochong Li2https://orcid.org/0000-0002-1474-9800College of Information Engineering, Shanghai Maritime University, Shanghai, ChinaCollege of Information Engineering, Shanghai Maritime University, Shanghai, ChinaCollege of Information Engineering, Shanghai Maritime University, Shanghai, ChinaThe text information in the medical photocopies is of great significance to the construction of medical digital platform. Text region detection, the very first step of extracting medical photocopies information, is functional to detect text area or locate text instance on the sample. Researchers have done a lot works on text area detection in natural scenes, yet few of them in turn pay attention to the medical photocopies scenario which is urgent to be settled. Here, a text line area detection dataset based on Chinese medical photocopies (CMPTD) are created and a fine-grained text line region detection model based on multi-scale feature extraction and fusion are proposed in this paper. The detection model consists of three parts. The first part is feature extraction module. Cspdarknet53 in You Only Look Once version 4 (YOLOv4) is used as the backbone network of our model, and the spatial pyramid pool strategy is used to extract multi-scale features to enhance the robustness of the model. The second part is feature fusion module. By referring to the PANet structure, the three effective feature layers in feature extraction module are fused repeatedly. The last part is prediction module. The network outputs a series of fine-grained text proposals by referring to the CTPN structure, which are connected into text lines by text line construction algorithm. We experimentally demonstrate the effectiveness of the detection model with the precision of 92.46% and the recall of 91.74% in the text detection task of the dataset CMPTD.https://ieeexplore.ieee.org/document/9373364/Chinese medical photocopyingtext detectionYOLOv4text line construction algorithmconvolutional neural network |
| spellingShingle | Haiwen Wu Ri-Gui Zhou Yaochong Li A Neural Network Model for Text Detection in Chinese Drug Package Insert IEEE Access Chinese medical photocopying text detection YOLOv4 text line construction algorithm convolutional neural network |
| title | A Neural Network Model for Text Detection in Chinese Drug Package Insert |
| title_full | A Neural Network Model for Text Detection in Chinese Drug Package Insert |
| title_fullStr | A Neural Network Model for Text Detection in Chinese Drug Package Insert |
| title_full_unstemmed | A Neural Network Model for Text Detection in Chinese Drug Package Insert |
| title_short | A Neural Network Model for Text Detection in Chinese Drug Package Insert |
| title_sort | neural network model for text detection in chinese drug package insert |
| topic | Chinese medical photocopying text detection YOLOv4 text line construction algorithm convolutional neural network |
| url | https://ieeexplore.ieee.org/document/9373364/ |
| work_keys_str_mv | AT haiwenwu aneuralnetworkmodelfortextdetectioninchinesedrugpackageinsert AT riguizhou aneuralnetworkmodelfortextdetectioninchinesedrugpackageinsert AT yaochongli aneuralnetworkmodelfortextdetectioninchinesedrugpackageinsert AT haiwenwu neuralnetworkmodelfortextdetectioninchinesedrugpackageinsert AT riguizhou neuralnetworkmodelfortextdetectioninchinesedrugpackageinsert AT yaochongli neuralnetworkmodelfortextdetectioninchinesedrugpackageinsert |