Application of Fuzzy C-Means with YCbCr and DenseNet-201 for Automated Corn Leaf Disease Detection

Chyntia Jaby, Entuni (2021) Application of Fuzzy C-Means with YCbCr and DenseNet-201 for Automated Corn Leaf Disease Detection. Masters thesis, Universiti Malaysia Sarawak.

[img] PDF
Chyntia Jaby - 24 pgs.pdf

Download (400kB)
[img] PDF (Please get the password from Digital Collection Development Unit, ext : 3913 / 3914)
Chyntia Jaby.pdf
Restricted to Registered users only

Download (4MB) | Request a copy

Abstract

In agriculture sector, plant leaf diseases detection plays a significant role. Plant leaf detection is important for food security, avoiding economic downturns due to severe plant losses, and avoiding environmental degradation due to inappropriate disease treatment. The image processing consists of image segmentation and image classification are commonly used to extract the infected part from the uninfected part to identify the types of the diseases. Some of the existing methods of segmentation are K-Means, Otsu’s, edge-based segmentation, watershed segmentation, region growing, mean shift, maxflow mincut (MFMC) graph cut and regional colour segmentation. The performance of the previous segmentation methods, on the other hand, is average due to their disadvantages such as sensitive to noise and unable to process image with reflection. The example of the previous classification methods are ResNets, bag of features, artificial neural network (ANN), support vector machine (SVM), AlexNet, probabilistic neural network (PNN), principal component analysis (PCA) and k-nearest neighbour (k-NN) and they also have an average performance. This is due to instability and complexity of the network. Hence, algorithm that performed better is required. Thus, in this study, image segmentation method of Fuzzy C-Means with YCbCr and image classification method of DenseNet-201 to detect plant leaf diseases is proposed. The results show that the proposed method performed better than the previous methods with 96.81% for segmentation as well as 95.11% for classification and it is discovered to be a good fusion of algorithms to detect plant leaf diseases.

Item Type: Thesis (Masters)
Additional Information: Thesis (MSc.) - Universiti Malaysia Sarawak , 2021.
Uncontrolled Keywords: Plant leaf diseases, Fuzzy C-Means, YCbCr, DenseNet-201.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Academic Faculties, Institutes and Centres > Faculty of Engineering
Depositing User: CHYNTIA JABY AK ENTUNI
Date Deposited: 04 Nov 2021 00:54
Last Modified: 04 Nov 2021 00:54
URI: http://ir.unimas.my/id/eprint/36564

Actions (For repository members only: login required)

View Item View Item