Commit
•
d65fd5b
1
Parent(s):
3dae3d4
Update README2.md
Browse files- README2.md +7 -9
README2.md
CHANGED
|
@@ -3,10 +3,9 @@ _\\-------- **Image Data Extractor** -------\\_
|
|
| 3 |
_\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\_
|
| 4 |
|
| 5 |
---
|
| 6 |
-
|
| 7 |
# Overview:
|
| 8 |
The **Image Data Extractor** is a Python-based tool designed to extract and structure text data from images of visiting cards using **PaddleOCR**. The tool processes the extracted text to recognize key information such as name, designation, contact number, address, and company name, organizing the output into a well-defined structure. The **Mistral 7B model** is used for advanced text analysis, and if it becomes unavailable, the system seamlessly switches to the **Gliner urchade/gliner_mediumv2.1** model.
|
| 9 |
-
|
| 10 |
# Installation Guide:
|
| 11 |
|
| 12 |
1. **Create and Activate a Virtual Environment**
|
|
@@ -37,7 +36,7 @@ The **Image Data Extractor** is a Python-based tool designed to extract and stru
|
|
| 37 |
```bash
|
| 38 |
HF_TOKEN=<your_huggingface_token>
|
| 39 |
```
|
| 40 |
-
|
| 41 |
# File Structure Overview:
|
| 42 |
|
| 43 |
```
|
|
@@ -71,7 +70,7 @@ ImageDataExtractor/
|
|
| 71 |
│
|
| 72 |
└── .env # Environment variables (includes Hugging Face token)
|
| 73 |
```
|
| 74 |
-
|
| 75 |
# Program Overview:
|
| 76 |
|
| 77 |
### PaddleOCR Integration (utility/utils.py):
|
|
@@ -88,7 +87,7 @@ ImageDataExtractor/
|
|
| 88 |
### Web Interface (app.py):
|
| 89 |
- **Flask API**: Provides endpoints for image uploads and displays the results in a structured manner.
|
| 90 |
- **HTML Interface**: A frontend for users to upload images of visiting cards and view the parsed results.
|
| 91 |
-
|
| 92 |
# Tree Map of the Program:
|
| 93 |
|
| 94 |
```
|
|
@@ -108,11 +107,11 @@ Backup/backup.py
|
|
| 108 |
└── Backup and error handling
|
| 109 |
|
| 110 |
```
|
| 111 |
-
|
| 112 |
# Licensing:
|
| 113 |
- **Mistral 7B model** is used under the [Apache 2.0 license](https://www.apache.org/licenses/LICENSE-2.0).
|
| 114 |
- **Gliner urchade/gliner_mediumv2.1 model** is used under the [Apache 2.0 license](https://www.apache.org/licenses/LICENSE-2.0).
|
| 115 |
-
|
| 116 |
# Main Task:
|
| 117 |
The main objective is to extract and structure text data from visiting cards. The system identifies and organizes:
|
| 118 |
- **Name**
|
|
@@ -120,7 +119,7 @@ The main objective is to extract and structure text data from visiting cards. Th
|
|
| 120 |
- **Phone Number**
|
| 121 |
- **Address**
|
| 122 |
- **Company Name**
|
| 123 |
-
|
| 124 |
# References:
|
| 125 |
|
| 126 |
- [PaddleOCR Documentation](https://github.com/PaddlePaddle/PaddleOCR)
|
|
@@ -129,5 +128,4 @@ The main objective is to extract and structure text data from visiting cards. Th
|
|
| 129 |
- [Flask Documentation](https://flask.palletsprojects.com/)
|
| 130 |
- [Docker Documentation](https://docs.docker.com/)
|
| 131 |
- [Virtual Environments in Python](https://docs.python.org/3/tutorial/venv.html)
|
| 132 |
-
|
| 133 |
---
|
|
|
|
| 3 |
_\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\_
|
| 4 |
|
| 5 |
---
|
|
|
|
| 6 |
# Overview:
|
| 7 |
The **Image Data Extractor** is a Python-based tool designed to extract and structure text data from images of visiting cards using **PaddleOCR**. The tool processes the extracted text to recognize key information such as name, designation, contact number, address, and company name, organizing the output into a well-defined structure. The **Mistral 7B model** is used for advanced text analysis, and if it becomes unavailable, the system seamlessly switches to the **Gliner urchade/gliner_mediumv2.1** model.
|
| 8 |
+
---
|
| 9 |
# Installation Guide:
|
| 10 |
|
| 11 |
1. **Create and Activate a Virtual Environment**
|
|
|
|
| 36 |
```bash
|
| 37 |
HF_TOKEN=<your_huggingface_token>
|
| 38 |
```
|
| 39 |
+
---
|
| 40 |
# File Structure Overview:
|
| 41 |
|
| 42 |
```
|
|
|
|
| 70 |
│
|
| 71 |
└── .env # Environment variables (includes Hugging Face token)
|
| 72 |
```
|
| 73 |
+
---
|
| 74 |
# Program Overview:
|
| 75 |
|
| 76 |
### PaddleOCR Integration (utility/utils.py):
|
|
|
|
| 87 |
### Web Interface (app.py):
|
| 88 |
- **Flask API**: Provides endpoints for image uploads and displays the results in a structured manner.
|
| 89 |
- **HTML Interface**: A frontend for users to upload images of visiting cards and view the parsed results.
|
| 90 |
+
---
|
| 91 |
# Tree Map of the Program:
|
| 92 |
|
| 93 |
```
|
|
|
|
| 107 |
└── Backup and error handling
|
| 108 |
|
| 109 |
```
|
| 110 |
+
---
|
| 111 |
# Licensing:
|
| 112 |
- **Mistral 7B model** is used under the [Apache 2.0 license](https://www.apache.org/licenses/LICENSE-2.0).
|
| 113 |
- **Gliner urchade/gliner_mediumv2.1 model** is used under the [Apache 2.0 license](https://www.apache.org/licenses/LICENSE-2.0).
|
| 114 |
+
---
|
| 115 |
# Main Task:
|
| 116 |
The main objective is to extract and structure text data from visiting cards. The system identifies and organizes:
|
| 117 |
- **Name**
|
|
|
|
| 119 |
- **Phone Number**
|
| 120 |
- **Address**
|
| 121 |
- **Company Name**
|
| 122 |
+
---
|
| 123 |
# References:
|
| 124 |
|
| 125 |
- [PaddleOCR Documentation](https://github.com/PaddlePaddle/PaddleOCR)
|
|
|
|
| 128 |
- [Flask Documentation](https://flask.palletsprojects.com/)
|
| 129 |
- [Docker Documentation](https://docs.docker.com/)
|
| 130 |
- [Virtual Environments in Python](https://docs.python.org/3/tutorial/venv.html)
|
|
|
|
| 131 |
---
|