Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
2 views

Automated IoT Based Quality Inspection System Using Computer Vision

The project aims to develop an automated quality inspection system using computer vision and deep learning to identify flaws in manufactured parts, significantly reducing manual inspection efforts. Key objectives include enhancing accuracy, integrating with existing workflows, and providing a user-friendly interface for real-time monitoring and reporting. The methodology involves data acquisition, image processing, defect detection, system integration, and the development of a web-based dashboard for visualization.

Uploaded by

Pranoy Mukherjee
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
2 views

Automated IoT Based Quality Inspection System Using Computer Vision

The project aims to develop an automated quality inspection system using computer vision and deep learning to identify flaws in manufactured parts, significantly reducing manual inspection efforts. Key objectives include enhancing accuracy, integrating with existing workflows, and providing a user-friendly interface for real-time monitoring and reporting. The methodology involves data acquisition, image processing, defect detection, system integration, and the development of a web-based dashboard for visualization.

Uploaded by

Pranoy Mukherjee
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Project Title:

Automated IoT Based Quality Inspection System Using Computer Vision

Project Overview:

The project's goal is to create an automated quality inspection system that checks
produced parts for flaws and irregularities using deep learning and computer vision. By
identifying surface flaws, dimensional errors, and texture irregularities in real time, the
technology will drastically cut down on the amount of manual inspection work required.

Objectives:

1. Develop a computer vision-based inspection system to enhance accuracy and


e iciency in quality control.

2. Implement deep learning algorithms to detect common manufacturing defects


such as cracks, scratches, and dimensional deviations.

3. Integrate the system with existing manufacturing workflows for real-time monitoring.

4. Provide a user-friendly interface for visualizing inspection results and generating


reports.

Motivation:

Manual inspection of manufactured parts is labor-intensive and prone to human error. An


automated inspection system would enhance consistency and reduce quality control
costs. This project aligns with your interests in manufacturing automation and AI
applications.

Methodology:

1. Data Acquisition:

o Capture high-resolution images of manufactured parts using industrial


cameras.

o Develop a controlled lighting setup to minimize reflections and shadows.

2. Image Processing:

o Preprocess the images to enhance features (e.g., edge detection, noise


reduction).

o Implement techniques like thresholding and contour detection for basic


defect identification.
3. Defect Detection and Classification:

o Train deep learning models (e.g., CNNs) using datasets of defective and non-
defective parts.

o Use frameworks like TensorFlow or PyTorch for model development.

o Integrate OpenCV for real-time image processing and analysis.

4. System Integration:

o Implement a Raspberry Pi 4 as the primary processing unit for image


capture and analysis.

o Integrate the system with a centralized platform for monitoring and data
logging.

5. User Interface:

o Develop a web-based dashboard using React and Node.js for real-time


visualization and reporting.

o Display defect statistics, image samples, and inspection logs.

Tools and Technologies:

 Programming Languages: Python3, C++

 Libraries/Frameworks: OpenCV, TensorFlow, PyTorch, React, Node.js

 Hardware: Raspberry Pi 4, Industrial Cameras

 Design Tools: SolidWorks for fixture and camera mount design

 Simulation and Prototyping: MATLAB for initial algorithm testing

Expected Outcomes:

 A fully automated system capable of real-time quality inspection.

 A modular and scalable solution that can be adapted to di erent manufacturing


environments.

 An interactive dashboard for visualization and analytics.

You might also like