Scribd
Upload
3 views5 pages

Iot 9 Soyam

The document outlines an experiment conducted by a student in the Computer Science and Engineering department, focusing on designing a Machine Vision-based automated quality control system for industrial products. The system inspects products based on shape and dimensions, calculates a likeness score, and achieves millimeter-level precision with an average inspection time of 266 ms per object. The experiment highlights the advantages of automated inspection over manual methods in terms of speed, accuracy, and consistency.

Uploaded by

muskan872b
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
3 views5 pages

Iot 9 Soyam

The document outlines an experiment conducted by a student in the Computer Science and Engineering department, focusing on designing a Machine Vision-based automated quality control system for industrial products. The system inspects products based on shape and dimensions, calculates a likeness score, and achieves millimeter-level precision with an average inspection time of 266 ms per object. The experiment highlights the advantages of automated inspection over manual methods in terms of speed, accuracy, and consistency.

Uploaded by

muskan872b
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

DEPARTMENT OF

COMPUTER SCIENCE & ENGINEERING

Experiment 9
Student Name: Bhaskar Kumar UID: 22BCS10403
Branch: Be-CSE Section/Group:22BCS_FL_IOT-601
Semester: 6th Date of Performance:3/04/25
Subject Name: Foundation of Cloud IoT Code: 22CSP-367
Edge ML Lab
1. Aim:To design and implement a Machine Vision-based automated quality control system
capable of performing real-time dimensional analysis of industrial products.

2. Objective:
• To inspect manufactured products for quality assurance based on shape and
dimensions.
• To calculate a likeness score for comparing tested items to standard objects.
• To improve product inspection speed and consistency using non-contact
blob analysis techniques. 3. Hardware / Software Used:
• 5MP CMOS Industrial Camera (Hikvision)
• Circular LED lighting source
• Dobot® metal rig • Software Requirements:
• Dobot Vision Studio
• Blob analysis and shape similarity algorithms
• Calibrated camera setup 4. Implementation/Code:
• Step 1: Inspect a known-good object to extract standard parameters (area,
perimeter, circularity, rectangularity).
• Step 2: Store these parameters as reference.
• Step 3: Continuously capture images of new objects.
• Step 4: Perform blob analysis and compute likeness score.
• Step 5: Accept or reject the product based on whether the score exceeds a defined
threshold.
• The likeness score formula:
• L=aP+bA+cR+dCL = aP + bA + cR + dCL=aP+bA+cR+dC
DEPARTMENT OF
COMPUTER SCIENCE & ENGINEERING

• where P, A, R, C = perimeter, area, rectangularity, circularity differences with


respective weights.
5. Output:
DEPARTMENT OF
COMPUTER SCIENCE & ENGINEERING
DEPARTMENT OF
COMPUTER SCIENCE & ENGINEERING

6. Result:- The MV-based inspection system successfully detected and differentiated between
acceptable and defective products based on geometrical dimensions. It achieved millimeter-
level precision with an average inspection time of 266 ms per object, proving effective for
industrial applications.
DEPARTMENT OF
COMPUTER SCIENCE & ENGINEERING

7. Learning Outcome:
• Learned to implement and evaluate a Machine Vision system for QC.
• Understood the importance of parameters like perimeter, circularity, and
rectangularity in product inspection.
• Gained experience in calculating a likeness score for automated defect
detection.
• Observed practical advantages over manual inspection methods in terms of
speed, accuracy, and consistency.

You might also like