https://github.com/vsmidhun21/lego-identification

this project employs machine learning to accurately detect and classify LEGO bricks by color and size from images and videos. It features a Streamlit web application for real-time brick detection via camera feed or file upload, enhancing accessibility and usability.
https://github.com/vsmidhun21/lego-identification

python streamlit yolo

Last synced: 22 days ago
JSON representation

this project employs machine learning to accurately detect and classify LEGO bricks by color and size from images and videos. It features a Streamlit web application for real-time brick detection via camera feed or file upload, enhancing accessibility and usability.

• Host: GitHub
• URL: https://github.com/vsmidhun21/lego-identification
• Owner: vsmidhun21
• Created: 2024-09-12T07:00:43.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-09-28T05:23:51.000Z (5 months ago)
• Last Synced: 2024-11-21T16:14:34.424Z (3 months ago)
• Topics: python, streamlit, yolo
• Language: Jupyter Notebook
• Homepage: https://lego-detection.streamlit.app
• Size: 41.4 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# LEGO BRICK COLOUR AND SIZE DETECTION

The goal of this project is to develop an automated system that can accurately detect and classify the color and size of LEGO bricks from images.

# WORKFLOW

![WORKFLOW](https://github.com/user-attachments/assets/49037f61-b237-4368-a113-c290fe0b6618)

#  TECHNOLOGY USED: 

- PYTHON PROGRAMMING

- YOLO ARCHITECHTURE

# WHY WE PREFER PYTHON?

Python is used because of its simple syntax, extensive libraries, strong community support, and versatility across various applications like web development, data analysis, and machine learning. It’s also platform-independent and ideal for rapid prototyping.

# WHY WE PREFER YOLO?

YOLO outperforms CNN and k-NN in object detection tasks by offering real-time speed, integrated object detection and localization, and the ability to handle multiple objects simultaneously. While CNNs are powerful for classification and feature extraction, and k-NN is simple and intuitive for classification, YOLO provides a more comprehensive and efficient solution for tasks that require both classification and localization, like predicting LEGO pieces in an image.

# TO RUN:

```

git clone https://github.com/MidhunVS21/Lego-Detection.git

cd Lego-Detection

streamlit run app.py

```

# LINK OF DEPLOYED APP:

- [lego-detection.streamlit.app](https://lego-detection.streamlit.app)

- [lego-app.streamlit.app](https://lego-app.streamlit.app)

# DEMONSTRATION VIDEO:

https://github.com/user-attachments/assets/e963629c-580e-425f-b7c3-880549bb2423