Scribd
Upload
35 views3 pages

Proposal 2

This document describes an automated product sorting system using image processing techniques as an alternative to complex machine learning models. The system uses cameras to capture images of products on a conveyor belt. Through image preprocessing, color, shape, and texture analysis, products are classified and sorted without training datasets or complex algorithms. The total estimated budget for the system is 30,000 Tk. It provides a cost-effective solution for industries needing automated product sorting.

Uploaded by

Abdullah Alam Manna
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
35 views3 pages

Proposal 2

This document describes an automated product sorting system using image processing techniques as an alternative to complex machine learning models. The system uses cameras to capture images of products on a conveyor belt. Through image preprocessing, color, shape, and texture analysis, products are classified and sorted without training datasets or complex algorithms. The total estimated budget for the system is 30,000 Tk. It provides a cost-effective solution for industries needing automated product sorting.

Uploaded by

Abdullah Alam Manna
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Automated Product Sorting System Using Image-processing

1.Introduction:
The effective sorting of products is essential to ensure efficient operations and prompt
deliveries in the fast-paced worlds of manufacturing, transportation, and e-commerce.
Innovative automation systems have been created as a result of the requirement for accuracy
and speed in product sorting. By utilizing the strength of computer vision and image processing
techniques, our project, the "Automated Product Sorting System using Image Processing aims to
answer this urgent demand by developing a smart and flexible solution.
2. Literature review:
A research on project sorting name “Applications of Sensor-Based Sorting for the Processing of
Mineral Resources” by Prof. Dr-Ing. Hermann Wotruba, Henning Knapp, Killian Neubert,
Christian Schropp where they use sensor to distinguish different ore.[1]

Another research “PLC Operated Color Based Product Sorting machine” by S Vandana1, K
Shamukha Sri Sai2, P Rohila2 and V Manideep2 where they use electro-magnetic actuators with
TCS2300 color sensor to automate the whole system.[2]
3. Project details:
3.1 Objective:
Traditional approaches to automated sorting have often relied on costly machine
learning models for classification. However, we recognize that not all applications
require the complexity and computational demands associated with machine learning.
In this project, we present an alternative approach that leverages rule-based image
processing methods to achieve accurate and efficient product sorting without the need
for extensive training datasets and complex algorithms. Our system relies on cameras
strategically positioned along conveyor belts or assembly lines to capture high-quality
images of products in real-time. Through careful image preprocessing and a series of
image analysis techniques, we are able to classify products based on their visual
characteristics, such as color, shape, and texture. These characteristics serve as the
foundation for a rule-based classification system that determines the category to which
each product belongs.
Features:
1. Camera-Based Image Acquisition: The system uses one or more cameras to take high-
resolution pictures of goods as they move along a conveyor belt or assembly line in real
time.
2. Image Preprocessing: To improve image quality, decrease noise, and maintain
consistency, advanced image preprocessing techniques are used, which increases the
accuracy of product recognition.
3. Color-Based Sorting: To categorize products according to their color properties, the
system uses color-based segmentation
4.Shape Analysis: The system can classify products according to their geometric
characteristics by using algorithms for shape detection and analysis. It is possible to
recognize and group various shapes.
5.Texture Analysis: Techniques for texture analysis can be used to classify products with
distinctive textures more accurately.
6.Cost-Effective: The project provides a reasonably priced method for product sorting by
removing the complex and resource-intensive nature of machine learning models.
7.Adaptability: Any industry that needs to automate product sorting can use the system,
including manufacturing, shipping, e-commerce, recycling, and others.

3.2 Estimate Budget:

item Unit price quantity Net price


1. Raspberry Pi 4 17,500 1 17,500
2. Raspberry Pi 4,690 2 9,380
camera Module V2
3. gear motor 850 1 850
4. motor driver 210 1 210
5. wire 100
6. accessories for 1000
conveyor system
total 29,040 tk (around
30,000)

Reference:
1. https://onlinelibrary.wiley.com/doi/epdf/10.1002/cite.201300174
2. https://iopscience.iop.org/article/10.1088/1757-899X/1119/1/012016/pdf.

You might also like