IDENTIFIKASI DAUN TANAMAN BUAH MENGGUNAKAN EKSTRAKSI CIRI ZERNIKE MOMENT INVARIANT (ZMI) DAN METODE BACKPROPAGATION NEURAL NETWORK (BNN)

AMIRULLAH, AMIRULLAH and Sukemi, Sukemi (2019) IDENTIFIKASI DAUN TANAMAN BUAH MENGGUNAKAN EKSTRAKSI CIRI ZERNIKE MOMENT INVARIANT (ZMI) DAN METODE BACKPROPAGATION NEURAL NETWORK (BNN). Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281320015.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
Preview	Text RAMA_56201_09011281320015_0003126604_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011281320015_0003126604_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (382kB) | Request a copy
	Text RAMA_56201_09011281320015_0003126604_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (685kB) | Request a copy
	Text RAMA_56201_09011281320015_0003126604_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (957kB) | Request a copy
	Text RAMA_56201_09011281320015_0003126604_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (30kB) | Request a copy
	Text RAMA_56201_09011281320015_0003126604_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (106kB) | Request a copy
	Text RAMA_56201_09011281320015_0003126604_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011281320015_TURNITIIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (11MB) | Request a copy

Abstract

The concept of pattern recognition is often used to identify a wide range of objects. Due to the ability to recognize objects is needed by humans. One of them is for pattern recognition on the leaves as identification in determining the types of leaves. However, in the acquisition, very frequent disturbances, called noise. Noise in the image is a region of pixel image intensity of unwanted or deemed to disturb the segmentation process until the introduction. The impact of noise can degrade the image quality when the segmentation process. Therefore, in this study, the researchers added a preprocessing stage to reduce noise modest invisible when the acquisition using the camera. Gaussian filter used as a technique to tackle the problem at last preprocessing. Aside from the noise, constraints at the time of feature extraction of natural researchers also because the study took shape characteristic based on the area of the image. So if the object changes the coordinates of the start pixel image was unrecognizable. Based on these problems do research to identify the leaves by using Zernike Moment invariant feature extraction (ZMI) and Backpropagation algorithm. Based on the testing that was done on 100 test data success rate Based on these problems do research to identify the leaves by using Zernike Moment invariant feature extraction (ZMI) and Backpropagation algorithm. Based on the testing that was done on 100 test data success rate Based on these problems do research to identify the leaves by using Zernike Moment invariant feature extraction (ZMI) and Backpropagation algorithm. Based on the testing that was done on 75 test data success rate 88%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Feature Extraction, Gaussian filter, Zernike Moment invariant, Backpropagation, Leaf Recognition.
Subjects:	Q Science > Q Science (General) > Q1-295 General Q Science > Q Science (General) > Q350-390 Information theory
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Users 3293 not found.
Date Deposited:	25 Nov 2019 04:47
Last Modified:	25 Nov 2019 04:47
URI:	http://repository.unsri.ac.id/id/eprint/17965

Actions (login required)

View Item