Scribd
Upload
48 views

Teachable Machines Arduino: Seed Sorter Using AND

The document proposes developing a seed sorting machine using computer vision and machine learning techniques to automatically classify seeds based on their visual properties, with the goal of addressing the costly and time-consuming nature of current manual seed labeling processes. It outlines using the Teachable Machine platform to build and deploy a seed classification model on an Arduino microcontroller by collecting seed image data, training a convolutional neural network classifier, and integrating it into the seed sorting machine.

Uploaded by

Amira Said
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
48 views

Teachable Machines Arduino: Seed Sorter Using AND

The document proposes developing a seed sorting machine using computer vision and machine learning techniques to automatically classify seeds based on their visual properties, with the goal of addressing the costly and time-consuming nature of current manual seed labeling processes. It outlines using the Teachable Machine platform to build and deploy a seed classification model on an Arduino microcontroller by collecting seed image data, training a convolutional neural network classifier, and integrating it into the seed sorting machine.

Uploaded by

Amira Said
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

University of Blida 1

SEED SORTER USING


TEACHABLE MACHINES
AND ARDUINO

Prepared By:
Hadjer YKHLEF

Computer Science
Department
[email protected]
The analysis and classification of seeds can
be easily automated using seed separating
ABOUT THE or sorting machines. Such machines perform
operations like determining the visual
PROJECT properties of seeds and identifying seed
categories. They often employ computer
vision to achieve this procedure. Several
machine learning models have been
proposed for computer vision applications.
In particular, Convolutional Neural Networks
have received a great deal of attention due
to their remarkable success in many related
tasks.

SEED IMAGE ANALYSIS has gained an


increasing prominence from the agriculture
research community the last few years.
Many factors can affect the agricultural
production, with seed quality topping the
list. Image seed classification provides
additional knowledge about the quality of
production. The use of guaranteed and
verified seeds expands the quality and the
amount of yield. Traditionally, the process
of analysis and classification of seeds relies
on characteristics like color, shape and
texture. However, these seeds have to be
hand-labeled by specialists, which is a very
costly and time-consuming process since it
involves a lot of manual labor.

ALWAYS WITH
PROJECT
GOAL

The purpose of this work is motivated by


the need of addressing the above needs.
The main thrust consists of devising a
sorting machine for image seed
classification using Arduino. This machine
is capable of capturing the visual
characteristics of each seed category. It
is equipped with an embedded camera
and a recognition module. The camera
takes images in a natural environment
without a complicated laboratory system.
The recognition module uses Teachable
Machine (TM) platform for learning the
classification or decision model.

KEYWORDS
Computer Vision.
Machine Learning.
Deep Learning.
Arduino.
Image Seed Classification.
The students should go through the following steps:
Step 1: Understand the definition of the problem.
Step 2: Cover the state-of-the-art related to:
PROJECT a. Computer vision.

WORKPLAN b. Classification methods (Convolutional Networks).


c. Transfer learning.
Step 3: Implement and compare several solutions:
a. Data collection and preparation using TM platform.
b. Classification.
c. Deploy the detection system on a microcontroller
like Arduino.
Step 4: Proceed with report writing, although it can start
just after step 2.c.

REFERENCES
[1] A. Loddo, M. Loddo, and C. Di Ruberto, “A novel deep learning based approach for seed
image classification and retrieval,” Comput. Electron. Agric., vol. 187, p. 106269, 2021.
[2] A. Ali et al., “Machine learning approach for the classification of corn seed using hybrid
features,” Int. J. Food Prop., vol. 23, no. 1, pp. 1110–1124, 2020.
[3] “Tiny Sorter.” https://experiments.withgoogle.com/tiny-sorter/view
[4] “Teachable Machine.” https://teachablemachine.withgoogle.com/

You might also like