Image Enhancement dengan kombinasi metode Edge Detection, Filtering, dan Morphological Gradient untuk segmentasi objek vegetasi pada citra satelit menggunakan Watershed Transform

Arofa, Vinna Syarifatul (2015) Image Enhancement dengan kombinasi metode Edge Detection, Filtering, dan Morphological Gradient untuk segmentasi objek vegetasi pada citra satelit menggunakan Watershed Transform. Undergraduate thesis, Universitas Islam Negeri Maulana Malik Ibrahim.

[img]
Preview
Text (Fulltext)
08650025.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (1MB) | Preview

Abstract

INDONESIA:

Penelitian di bidang segmentasi citra telah banyak dilakukan, terutama di bidang citra satelit. Proses segmentasi ini dilakukan untuk melakukan deteksi terhadap objek-objek yang terdapat di dalam citra. Pada penelitian ini, diimplementasikan sebuah metode segmentasi citra dengan menggunakan teknik watershed transform untuk mendeteksi objek vegetasi pada citra satelit. Pertama, dilakukan filter terhadap warna hijau yang di asumsikan sebagai objek vegetasi, kemudian citra diubah ke dalam format citra grayscale dan di olah dengan image enhancement dengan kombinasi beberapa metode seperti filtering, sharpening, deteksi tepi, dan morphological gradient. Citra kemudian diproses dengan metode watershed transform untuk memperoleh hasil segmentasi.

Uji coba dilakukan terhadap 10 datas citra satelit yang diambil secara acak. Hasil pengujian dengan menggunakan ROC (receiver operatic charasteristic) menunjukkan bahwa metode yang diusulkan berhasil melakukan segmentasi citra dengan hasil akurasi rata-rata 74,41788%, sensivitas 65,52647%, dan spesifitas 74,99533%.

ENGLISH:

Research about image segmentation has been widely applied, especially in satellite imagery. This segmentation process is done to make detection of the objects contained in the image. In this study, implemented a method of image segmentation using watershed transform techniques to detect objects of vegetation on the satellite image. The first, carried out against the green color filter is assumed as the object of vegetation, and then the image is converted into a grayscale image format and processed with image enhancement with a combination of several methods such as filtering, sharpening, edge detection and morphological gradient. The image is then processed by methods watershed transform to obtain segmentation results.

The tests performed on 10 datas satellite image taken at random. The test results using the ROC (receiver operatic charasteristic) showed that the proposed method successfully perform image segmentation with an average accuracy results 74.41788% 65.52647% sensitivity and specificity of 74.99533%.

Item Type: Thesis (Undergraduate)
Supervisor: Crysdian, Cahyo and Hariyadi, M. Amin
Keywords: Segmentasi; Vegetasi; Image Segmentation; Vegetation; Image Enhancement; Watershed Transform;
Departement: Fakultas Sains dan Teknologi > Jurusan Teknik Informatika
Depositing User: Dian Anesti
Date Deposited: 13 Oct 2017 07:11
Last Modified: 13 Oct 2017 07:11
URI: http://etheses.uin-malang.ac.id/id/eprint/8292

Actions (login required)

View Item View Item