Shabdobhedi commited on
Commit
cd3b7ff
Β·
verified Β·
1 Parent(s): 8c7b9bc

Update README

Browse files
Files changed (1) hide show
  1. README (1).md +92 -0
README (1).md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ # OCR and Document Search Web Application Prototype
3
+
4
+ ## Introduction
5
+ This project is a web-based prototype designed to perform Optical Character Recognition (OCR) on images containing text in both Hindi and English. The application allows users to upload an image, extract the text, and search for specific keywords within the extracted content. The goal is to demonstrate the functionality of OCR technology in a user-friendly web application.
6
+
7
+ ## Technologies
8
+ The following technologies and libraries were used in this project:
9
+
10
+ - **Python**: Programming language used for development.
11
+ - **EasyOCR**: Library for performing OCR on images.
12
+ - **Streamlit**: Framework for building the web application interface.
13
+ - **Pillow**: Library for image processing.
14
+
15
+ ## Requirements
16
+ To run this project, you will need the following libraries installed:
17
+
18
+ ```plaintext
19
+ easyocr
20
+ streamlit
21
+ Pillow
22
+ ```
23
+
24
+
25
+
26
+
27
+
28
+ ## Project Structure
29
+
30
+
31
+
32
+ ```
33
+
34
+ /OCR-Document-Search-App
35
+ β”‚
36
+ β”œβ”€β”€ app.py # Main application file
37
+ β”œβ”€β”€ ocr_utils.py # Utility functions for OCR processing
38
+ └── requirements.txt # List of required libraries
39
+
40
+ ```
41
+ # How to Run the Application
42
+
43
+ ## 1.Clone the Repository:
44
+
45
+
46
+ ```
47
+ git clone <repository-url>
48
+ ```
49
+
50
+ ## 2.Navigate to the Project Directory:
51
+
52
+
53
+ ```
54
+ cd OCR-Document-Search-App
55
+ ```
56
+
57
+ ## 3.Install Dependencies:
58
+
59
+ ```
60
+ pip install -r requirements.txt
61
+ ```
62
+ ## 4.Run the Application:
63
+
64
+ ```
65
+ streamlit run app.py
66
+ ```
67
+ ## 5.Access the Application:
68
+ ```
69
+ Open your web browser and go to http://localhost:8501.
70
+ ```
71
+
72
+ ##Features
73
+
74
+ ##Image Upload: Users can upload images in JPG, JPEG, or PNG format.
75
+ Text Extraction: The application uses EasyOCR to extract text from the uploaded image.
76
+ Keyword Search: Users can enter keywords to search within the extracted text, with matching sections highlighted.
77
+
78
+ ## Features
79
+
80
+
81
+ - **Image Upload**: Users can upload images in JPG, JPEG, or PNG format.
82
+ - **Text Extraction**: The application uses EasyOCR to extract text from the uploaded image.
83
+ - **Keyword Search**: Users can enter keywords to search within the extracted text, with matching sections highlighted.
84
+ ## Deployment
85
+ The application can be deployed on platforms such as Streamlit Sharing or Hugging Face Spaces. Follow their instructions to make your application accessible via a public URL.
86
+ ## Live URL
87
+ ## Conclusion
88
+ This project demonstrates how OCR technology can be integrated into a web application, providing an efficient tool for extracting and searching text from images.
89
+ ## Demo
90
+
91
+ Insert gif or link to demo
92
+