Himanshu2003 commited on
Commit
6fce979
Β·
verified Β·
1 Parent(s): 5f18f57

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -63
README.md CHANGED
@@ -65,66 +65,3 @@ It seamlessly combines **object detection** and **optical character recognition
65
  | πŸ’Ύ Language | **Python 3.11+** | Development language |
66
 
67
  ---
68
-
69
- ## πŸš€ Quick Start
70
-
71
- ### 1️⃣ Install Dependencies
72
- ```bash
73
- pip install -r requirements.txt
74
- # πŸš— PlateVision πŸ”
75
- ### AI-Powered License Plate Detection & Recognition from Images and Videos
76
-
77
- ---
78
-
79
- ## 🧠 Overview
80
-
81
- **PlateVision** is an AI-powered web app built with **Streamlit** that detects and recognizes vehicle license plates from **images** and **videos** using a **fine-tuned YOLOv8 model** and **EasyOCR**.
82
-
83
- It seamlessly combines **object detection** and **optical character recognition (OCR)** to deliver a simple, intuitive, and interactive platform where users can upload their media files and get annotated results in seconds β€” complete with **confidence scores** and **recognized text overlays**.
84
-
85
- ---
86
-
87
- ## ✨ Features
88
-
89
- βœ… Detects license plates from both **images** and **videos**
90
- βœ… Extracts **license numbers** using OCR (EasyOCR)
91
- βœ… Displays **detection confidence** and recognized text on output
92
- βœ… Supports multiple formats β€” `.jpg`, `.jpeg`, `.png`, `.mp4`, `.mkv`
93
- βœ… Shows **real-time progress** while processing videos
94
- βœ… Provides a **clean Streamlit interface** for easy interaction
95
- βœ… Outputs processed results with bounding boxes and plate numbers drawn on frames
96
-
97
- ---
98
-
99
- ## βš™οΈ How It Works
100
-
101
- 1. **Upload Input File**
102
- - The user uploads an image or video through the Streamlit interface.
103
-
104
- 2. **License Plate Detection (YOLOv8)**
105
- - A **custom fine-tuned YOLOv8 model** detects the position of license plates in the media.
106
-
107
- 3. **Text Recognition (EasyOCR)**
108
- - The detected plate region is passed through **EasyOCR** to read and extract the license number.
109
-
110
- 4. **Annotation & Output**
111
- - Detected plates are annotated with bounding boxes, confidence percentages, and extracted text.
112
- - For videos, frames are processed sequentially and stitched back together using **MoviePy**.
113
-
114
- 5. **Display**
115
- - The processed media (image or video) is displayed directly in the Streamlit app.
116
-
117
- ---
118
-
119
- ## 🧩 Tech Stack
120
-
121
- | Component | Technology / Library | Purpose |
122
- |------------|----------------------|----------|
123
- | 🧱 Frontend & UI | **Streamlit** | Builds the interactive web interface |
124
- | 🧠 Object Detection | **YOLOv8 (Ultralytics)** | Detects license plate locations |
125
- | πŸ” OCR Engine | **EasyOCR** | Recognizes alphanumeric text from plates |
126
- | πŸŽ₯ Video Handling | **MoviePy** | Processes and reconstructs video frames |
127
- | πŸ‘οΈ Computer Vision | **OpenCV** | Image manipulation and annotation |
128
- | πŸ’Ύ Language | **Python 3.11+** | Development language |
129
-
130
- ---
 
65
  | πŸ’Ύ Language | **Python 3.11+** | Development language |
66
 
67
  ---