-Traffic_Sign_recognition
所属分类：模式识别(视觉/语音等)
开发工具：Python
文件大小：0KB
下载次数：0
上传日期：2023-08-23 06:18:56
上 传 者：
sh-1993
说明： 交通标志识别由高级分类器CNN（卷积神经网络）组成，精度为97%，
(traffic sign recognition consist of advance classifier CNN(convolutional neural network) with 97% accuracy,)
文件列表:
.DS_Store (8196, 2023-10-01)
Datadset/ (0, 2023-10-01)
Datadset/.DS_Store (6148, 2023-10-01)
Datadset/Meta.csv (1033, 2023-10-01)
Datadset/Meta/ (0, 2023-10-01)
Datadset/Meta/.~lock.ClassesInformation.ods# (80, 2023-10-01)
Datadset/Meta/.~lock.ClassesInformationStrong.ods# (80, 2023-10-01)
Datadset/Meta/0.png (9974, 2023-10-01)
Datadset/Meta/1.png (10062, 2023-10-01)
Datadset/Meta/10.png (7131, 2023-10-01)
Datadset/Meta/11.png (5725, 2023-10-01)
Datadset/Meta/12.png (1772, 2023-10-01)
Datadset/Meta/13.png (4848, 2023-10-01)
Datadset/Meta/14.png (5831, 2023-10-01)
Datadset/Meta/15.png (5841, 2023-10-01)
Datadset/Meta/16.png (6681, 2023-10-01)
Datadset/Meta/17.png (5476, 2023-10-01)
Datadset/Meta/18.png (5701, 2023-10-01)
Datadset/Meta/19.png (5497, 2023-10-01)
Datadset/Meta/2.png (10065, 2023-10-01)
Datadset/Meta/20.png (5510, 2023-10-01)
Datadset/Meta/21.png (5765, 2023-10-01)
Datadset/Meta/22.png (6027, 2023-10-01)
Datadset/Meta/23.png (6572, 2023-10-01)
Datadset/Meta/24.png (5493, 2023-10-01)
Datadset/Meta/25.png (7175, 2023-10-01)
Datadset/Meta/26.png (5771, 2023-10-01)
Datadset/Meta/27.png (7078, 2023-10-01)
Datadset/Meta/28.png (7131, 2023-10-01)
Datadset/Meta/29.png (7005, 2023-10-01)
Datadset/Meta/3.png (10068, 2023-10-01)
Datadset/Meta/30.png (7869, 2023-10-01)
Datadset/Meta/31.png (6530, 2023-10-01)
Datadset/Meta/32.png (9216, 2023-10-01)
Datadset/Meta/33.png (8283, 2023-10-01)
Datadset/Meta/34.png (8210, 2023-10-01)
Datadset/Meta/35.png (5912, 2023-10-01)
Datadset/Meta/36.png (6338, 2023-10-01)
Datadset/Meta/37.png (6307, 2023-10-01)
... ...
# Project Overview
The Traffic Sign Recognition project aims to demonstrate the application of AI and machine learning in recognizing traffic signs from images. The project includes a trained machine learning model and a Flask-based GUI for users to upload images and get real-time predictions for traffic signs.
### Installation:
To get started with the project, follow these steps:
#### Clone the repository:
```
git clone https://github.com/PruthvirajIngale81/Traffic_Sign_recognition.git
```
#### Navigate to the project directory:
```
cd Traffic_Sign_recognition
```
#### Install the required packages using pip:
```
pip install -r requirements.txt
```
### Usage:
#### Run the Flask application:
```
python app.py
```
Open a web browser and go to `http://localhost:5000` to access the GUI.
Upload an image containing a traffic sign and submit it.
The application will display the recognized traffic sign and its prediction.
### File Structure:
app.py: The Flask application script.
requirements.txt: List of required Python packages.
static/: Folder containing static files (CSS, images).
templates/: Folder containing HTML templates.
model/: Folder containing the trained machine learning model.
### Technologies Used:
Python: Programming language for the backend.
Flask: Web framework for creating the GUI.
HTML and CSS: Structuring and styling the GUI.
TensorFlow/Keras: Framework for training and using the machine learning model.
### Machine Learning Model:
The project uses a pre-trained machine learning model (traffic_sign_model.h5) to recognize traffic signs from images. This model was trained using a labeled dataset of traffic sign images.
### Flask GUI:
The Flask-based GUI allows users to:
Upload an image containing a traffic sign.
Display the recognized traffic sign and its prediction.
### Contact Information:
For any inquiries or feedback, contact `pruthvirajingale0081@gmail.com`.
近期下载者：
相关文件：
收藏者：