Peningkatan Akurasi Pengklasifikasi Citra Penyakit Buah Jeruk Berbasis Squeezenet Dan KNN

NGGAJI, Albinus Yunaldo Alfandi Laki (2023) Peningkatan Akurasi Pengklasifikasi Citra Penyakit Buah Jeruk Berbasis Squeezenet Dan KNN. Undergraduate thesis, Universitas Katolik Widya Mandira Kupang.

	Text ABSTRAK.pdf Download (638kB)
	Text BAB I.pdf Download (303kB)
	Text BAB II.pdf Restricted to Repository staff only Download (294kB)
	Text BAB III.pdf Restricted to Repository staff only Download (213kB)
	Text BAB IV.pdf Restricted to Repository staff only Download (387kB)
	Text BAB V.pdf Download (792kB)

Abstract

This study aims to identify healthy oranges and sick oranges. Improvement of Citrus Fruit Disease Classifier Accuracy was carried out to help improve the accuracy of the traditional k-NN classifier. Improved accuracy is done using images. The images used are sick oranges and healthy oranges, with the use of a canon digital camera as the image capture where the total images taken in this study were 200 samples. The training and classification process uses the KNN method that is already available in the ORANGE application, where the classification is divided into two classes where the first class is sick oranges and the second class is healthy oranges. The purpose of this study is to improve the performance of the traditional k-NN classifier accuracy. The results of this study can distinguish sick and healthy citrus fruits, after testing 200 image samples, the accuracy of the disease identification system for healthy oranges and diseased oranges has a high accuracy rate of 96%, 99% and 99.5%.

Actions (login required)

View Item