Scribd
Upload
2 views2 pages

Approval

The thesis titled 'Potato Leaf Disease Detection and Classification Using CNN' focuses on developing a custom Convolutional Neural Network to detect and classify potato leaf diseases, achieving an accuracy of 99.31%. The study utilized a curated image dataset and applied data augmentation techniques to enhance model robustness. This automated solution aims to improve early disease detection in potato crops, ensuring better yield and quality.

Uploaded by

Shohanur Rahman
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
2 views2 pages

Approval

The thesis titled 'Potato Leaf Disease Detection and Classification Using CNN' focuses on developing a custom Convolutional Neural Network to detect and classify potato leaf diseases, achieving an accuracy of 99.31%. The study utilized a curated image dataset and applied data augmentation techniques to enhance model robustness. This automated solution aims to improve early disease detection in potato crops, ensuring better yield and quality.

Uploaded by

Shohanur Rahman
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/ 2

Gopalganj Science and Technology University

Department of Computer Science and Engineering


Thesis Approval
“Potato Leaf Disease Detection and Classification Using CNN”
Student Information: Supervisor Information:
Name Md. Mahfuz Ahmed Name Abu Bakar Muhammad
ID No. 19CSE054 Abdullah
Session 2019-20 Designation Assistant Professor
Dept. of CSE, GSTU
Course Title: Thesis/Project Course Code: CSE-478
Abstract

Potatoes, as a vital food crop, are highly susceptible to leaf diseases that threaten yield and quality. This
study aims to develop a custom Convolutional Neural Network (CNN) model to detect and classify potato
leaf diseases—specifically early blight, late blight, and healthy leaves. A carefully curated and preprocessed
image dataset was used, and data augmentation techniques were applied to enhance model robustness. The
model was trained from scratch, focusing on reducing computational complexity while improving accuracy.
Our CNN achieved an outstanding accuracy of 99.31%, surpassing existing methods. Evaluation metrics
like precision, recall, and F1-score confirmed its reliability. The proposed method offers an efficient and
automated solution for early disease detection in potato crops.

. . . . .. . . . . . .. . . . . . . . . . . . .
Supervisor Signature

Signature of the Board Members: (Use for presentation’s Board)

1)... . . . . . . . . . .2)- - - - - - -- - - - -

Comment: i) Accept ii) Contitional Accept iii) Not Accept Recommand for Project Exibition: Yes / No

You might also like