Deep learning for image- based plant disease detection / Mohamad Lokman Zahari

Zahari, Mohamad Lokman (2020) Deep learning for image- based plant disease detection / Mohamad Lokman Zahari. [Student Project] (Unpublished)

Download

[thumbnail of 44324.pdf] Text
44324.pdf

Download (228kB)

Abstract

Deep learning methods that are the Convolution Neural Network can be utilized to classify the plant disease. In addition, Sliding Windows methods also help to create dataset in ease. This research will lead as one of future references in the modern agricultural sector. Plant disease has been identified as a significant threat to food security, as it significantly decreases crop yield and compromises its consistency classification as human in the existence of plant disease is. Manual detection is limited only to small-scale agriculture. Therefore, the automatic detection of crop diseases in the agricultural sector is very important as it will enable farmers to keep track of the underlying diseases from time to time. Therefore, the purpose of this project is sliding window is used to produce a dataset. The sliding window will help the image shifter to generate faster and larger datasets. Deep convolutional neural network is implemented in order to classify diseases through the use of a dataset of images of healthy plant leaves collected under controlled conditions using Matlab platform. In this research, a number of 8554 data of each leaf set with different angles and scales are used to perform the pre-train the dataset by using Convolutional Neural Network platform. The experimental results show a good precision of 94.81 percent of testing average result, suggesting as successful classification rate. This project also can make a farmers easily to classify the disease that affected their plants.

Metadata

Item Type: Student Project
Creators:
Creators
Email
Zahari, Mohamad Lokman
2017668636
Contributors:
Contribution
Name
Email / ID Num.
Thesis advisor
Ismail, Ahmad Puad
UNSPECIFIED
Subjects: T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Electronics
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Electronics > Detectors. Sensors. Sensor networks
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Electronics > Computer engineering. Computer hardware
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Electronics > Computer engineering. Computer hardware > Malaysia
Divisions: Universiti Teknologi MARA, Pulau Pinang > Permatang Pauh Campus > Faculty of Electrical Engineering
Programme: Bachelor of Engineering (Hons) Civil (Infrastructure)
Item ID: 44324
Uncontrolled Keywords: Convolution Neural Network, Sliding Window, Agriculture
URI: https://ir.uitm.edu.my/id/eprint/44324

Fulltext

Fulltext is available at:
  • Library Terminal Workstation (Digital Format) - Accessible via UiTM Libraries
  • ID Number

    44324

    Indexing


    View in Google Scholar

    Edit Item
    Edit Item