i
PERBANDINGAN METODE STATIC THRESHOLDING DAN
MULTI OTSU THRESHOLDING PADA SEGMENTASI CITRA
AML M0 DAN AML M1
SKRIPSI
Diajukan untuk memenuhi sebagian persyaratan mendapatkan gelar Strata Satu
Program Studi Informatika
Disusun oleh:
Ersi Indah Asmari
NIM. M0513018
PROGRAM STUDI INFORMATIKA
FAKULTAS MATEMATIKA DAN ILMU PENGETAHUAN ALAM UNIVERSITAS SEBELAS MARET
iii
iv 5 MOTTO
“Jangan kamu kehilangan harapan, dan jangan pula kamu bersedih hati.” (Q.S. Ali Imran: 139)
“The best preparation for tomorrow is doing your best today” (H. Jackson Brown, Jr.)
v
6 PERSEMBAHAN
Kupersembahkan karya ini untuk:
Almarhum ayah tercinta, Bapak Kasiyo
Ibu terhebat dan perkasa, Ibu Tarmini
Mas Danny Adityo
Wheny, Dessy, Afifah, Aza, Adit, Dian
vi
7 KATA PENGANTAR
Puji dan syukur penulis panjatkan ke hadirat Allah subhanahu wa ta’ala yang
telah melimpahkan kasih dan sayang-Nya kepada kita, sehingga penulis bisa menyelesaikan skripsi yang berjudul “Perbandingan Metode Static Thresholding Dan Multi Otsu Thresholding pada Segmentasi Citra AML M0 dan AML M1”. Tujuan dari penyusunan skripsi ini guna memenuhi salah satu syarat untuk bisa menempuh ujian sarjana komputer pada Fakultas MatematikA dan Ilmu Pengetahuan Alam (FMIPA) Program Studi Informatika di Universitas Sebelas Maret Surakarta. Didalam pengerjaan skripsi ini telah melibatkan banyak pihak yang sangat membantu dalam banyak hal, disini penulis sampaikan rasa terima kasih sedalam-dalamnya kepada:
1. Orang tua tercinta, Alm Bapak Kasiyo dan Ibu Tarmini yang telah membesarkan penulis dan memberi motivasi.
2. Ibu Esti Suryani selaku pembimbing akademik dan pembimbing I atas nasehat, arahan, dan bimbingannya selama masa kuliah.
3. Bapak Bambang Harjito selaku dosen pembimbing II atas kebaikan dan bimbingan selama penyelesaiaan tugas akhir ini.
4. Ibu pakar leukemia Dr. M.I. Diah yang telah bersedia membagikan ilmu dan waktunya demi kelancaran penulisan tugas akhir ini.
5. Sahabat-sahabat penulis: Wheny, Dessy, Afifah, Azaria, Mutiara, Desti, Laras, Mega, Adit, Dian yang telah memberi semangat kepada penulis.
Penulis berharap skripsi ini dapat bermanfaat untuk berbagai pihak.
Surakarta, 30 Januari 2018 Penulis
vii
PERBANDINGAN METODE STATIC THRESHOLDING DAN MULTI OTSU THRESHOLDING PADA SEGMENTASI CITRA
AML M0 DAN AML M1
ERSI INDAH ASMARI
Program Studi Informatika, Fakultas MIPA, Universitas Sebelas Maret
8 ABSTRAK
Proses diagnosa Acute Myeloid Leukemia (AML) dapat dilakukan dengan memanfaatkan teknologi pengolahan citra yang terdiri dari pre-processing, segmentasi, dan ekstraksi ciri. Segmentasi citra digunakan untuk memisahkan objek dari
background-nya. Salah satu contoh metode segmentasi yaitu Static Thresholding dan
Multi Otsu thresholding. Penelitian ini bertujuan untuk membandingkan metode segmentasi static thresholding dan multi otsu thresholding dalam proses diagnosis awal AML M0 dan M1. Metode pengolahan citra yang digunakan meliputi median filtering, konversi warna YCbCr, static thresholding, multi otsu thresholding, operasi morfologi, sedangkan identifikasi diterapkan menggunakan metode Naïve Bayes Classifier
dengan data uji berupa diameter WBC, rasio nukleus, dan putaran nukleus. Proses pengujian menggunakan 29 Citra AML M0 dan 30 citra AML M1. Hasil pengujian menunjukkan multi otsu thresholding menghasilkan akurasi 83.81% sedangkan static thresholding menghasilkan akurasi 75.35%. Berdasarkan akurasinya, segmentasi multi otsu thresholding memberikan hasil klasifikasi yang lebih baik dibandingkan metode
static thresholding.
viii
A COMPARISON OF SEGMENTATION METHODS BETWEEN
STATIC THRESHOLDING AND MULTI OTSU THRESHOLDING
IN THE PROCESS OF AML M0 AND AML M1
ERSI INDAH ASMARI
Program Studi Informatika, Fakultas MIPA, Universitas Sebelas Maret
9 ABSTRACT
The process of diagnosing Acute Myeloid Leukemia (AML) can be done by utilizing
image processing techniques consisting of pre-processing, segmentation, and feature
extraction. Image segmentation is used to separate objects from the background. One
example of the segmentation method is static thresholding and multi otsu
threshholding. This study aims to compare segmentation methods between static
thresholding and multi otsu thresholding in the process of AML M0 and M1 as the
initial diagnosis.Image processing methods that are used in this research are YCbCr
color space, median filtering, static thresholding, multi otsu thresholding,
morphological operation. The process of identificating cell uses Naïve Bayes Classifier
with test data in the form of WBC diameter, ratio of nukleus, and roundness of nukleus. Data to test process are 29 AML M1 images and 30 AML M2 images. It was shown
that segmentation with multi otsu thresholding method give a better classification
result with an accuracy of 83.81% whereas on static thresholding method only 75.34%.
Keywords: Acute Myeloid Leukemia (AML), image segmentation, multi otsu thresholding, static thresholding
ix BAB I PENDAHULUAN ... Error! Bookmark not defined. Latar Belakang ... Error! Bookmark not defined. Rumusan Masalah ... Error! Bookmark not defined. Batasan Masalah ... Error! Bookmark not defined. Tujuan Penelitian ... Error! Bookmark not defined. Manfaat Penelitian ... Error! Bookmark not defined. Sistematika Penulisan ... Error! Bookmark not defined. BAB II LANDASAN TEORI ... Error! Bookmark not defined. Landasan Teori ... Error! Bookmark not defined. Leukemia ... Error! Bookmark not defined. Acute Myeloid Leukemia (AML) ... Error! Bookmark not defined. Citra Digital ... Error! Bookmark not defined. Pengolahan Citra Digital ... Error! Bookmark not defined.
x
YcbCr ... Error! Bookmark not defined.
Median Filter ... Error! Bookmark not defined.
Grayscale ... Error! Bookmark not defined. Segmentasi Citra ... Error! Bookmark not defined.
Thresholding ... Error! Bookmark not defined.
Multi Otsu Thresholding ... Error! Bookmark not defined. Operasi Morfologi ... Error! Bookmark not defined. Klasifikasi ... Error! Bookmark not defined.
Naïve bayes ... Error! Bookmark not defined.
Confusion Matrix ... Error! Bookmark not defined. Penelitian Terkait ... Error! Bookmark not defined. Rancangan Penelitian ... Error! Bookmark not defined. BAB III METODOLOGI PENELITIAN... Error! Bookmark not defined. Pengumpulan Data dan Akuisisi Citra ... Error! Bookmark not defined. Penerapan StaticThresholding ... Error! Bookmark not defined.
Pre-processing ... Error! Bookmark not defined. Segmentasi StaticThresholding ... Error! Bookmark not defined. Ekstraksi Ciri ... Error! Bookmark not defined. Klasifikasi ... Error! Bookmark not defined. Penerapan MultiOtsuThresholding ... Error! Bookmark not defined.
Pre-processing ... Error! Bookmark not defined. Segmentasi MultiOtsuThresholding .... Error! Bookmark not defined. Ekstraksi Ciri MultiOtsuThresholding Error! Bookmark not defined. Klasifikasi MultiOtsuThresholding ... Error! Bookmark not defined. Membandingkan StaticThresholding dan MultiOtsuThresholding .... Error! Bookmark not defined.
xi
Pre-processing ... Error! Bookmark not defined. Segmentasi Static Thresholding ... Error! Bookmark not defined. Ekstraksi Ciri ... Error! Bookmark not defined. Klasifikasi Static Thresholding ... Error! Bookmark not defined. Penerapan Multi Otsu Thresholding ... Error! Bookmark not defined.
Pre-processing ... Error! Bookmark not defined. Segmentasi Multi Otsu Thresholding .... Error! Bookmark not defined. Ekstraksi Ciri ... Error! Bookmark not defined. Klasifikasi Multi Otsu Thresholding ... Error! Bookmark not defined. Perbandingan Static Thresholding dan Multi Otsu Thresholding ... Error! Bookmark not defined.
xii
12 DAFTAR TABEL
Tabel 2.1 Confusion Matriks Dua Kelas ... Error! Bookmark not defined. Tabel 2.2 Keterkaitan Penelitian Penulis dengan Penelitian Sebelumnya ... Error! Bookmark not defined.
Tabel 3.1 Tabel Confusion Matrix AML M0 dan AML M1 ... Error! Bookmark not defined.
Tabel 4.1 Data Maksimal dan Minimal dari Identifikasi Dokter ... Error! Bookmark not defined.
Tabel 4.2 Hasil Ekstraksi Ciri Citra AML M1_3 Segmentasi Static Thresholding
... Error! Bookmark not defined. Tabel 4.3 Pencarian Threshold dari Gambar 4.17... Error! Bookmark not defined. Tabel 4.4 Hasil Ekstraksi Ciri Metode Multi Otsu Thresholding Citra AML M1_3 ... Error! Bookmark not defined. Tabel 4.5 Confusion Matrix Static Thresholding AML M1_3.... Error! Bookmark not defined.
Tabel 4.6 Confusion Matrix Multi Otsu Thresholding AML M1_3 . Error! Bookmark not defined.
Tabel 4.7 Perbandingan Akurasi, Specificity, Sensivity Pada Identifikasi Sel
Myeloblast. ... Error! Bookmark not defined. Tabel 4.8 Perbandingan Akurasi, Specificity, Sensivity Pada Identifikasi Sel
Promyelocyte ... Error! Bookmark not defined. Tabel 4.9 Perbandingan Akurasi, Specificity, Sensivity Pada Identifikasi Sel
xiii
xiii
xiv
13
DAFTAR GAMBARGambar 2.1 Ilustrasi Darah yang Terindikasi (a) Leukemia Akut (b) Leukemia
Kronik (Bain et al., 2008) ... Error! Bookmark not defined. Gambar 2.2 (a) Myeloblast (b) Promyelocyte (c) Myelocyte (Bain et al., 2008) . Error! Bookmark not defined.
Gambar 2.3 Citra AML M0 (Antica, 2011) ... Error! Bookmark not defined. Gambar 2.4 Citra AML M1 (Bain et al., 2008) ... Error! Bookmark not defined. Gambar 2.5 Ilustrasi Citra Digital (Zhou et al., 2010) Error! Bookmark not defined. Gambar 2.6 Ilustrasi Citra RGB antara Kolom Matriksnya dan Kompenen Red,
Green, Blue (Zhou et al., 2010)... Error! Bookmark not defined. Gambar 2.7 Median Filter 3x3 (a) Citra X-Ray Sebelum di Smoothing (b) Citra X-Ray Sesudah di Smoothing (Zhou et al., 2010) ... Error! Bookmark not defined. Gambar 2.8 Ilustrasi Citra Grayscale (Jayaraman, 2011) ... Error! Bookmark not defined.
Gambar 2.9 (a) Citra Input (b) Citra Biner dengan Nilai Threshold T = 90 (c) Citra Biner dengan Nilai Threshold T = 124 (Zhou et al., 2010) ... Error! Bookmark not defined.
Gambar 2.10 (a) Citra A (b) Struktur Elemen (c) Hasil Dilasi A oleh B ... Error! Bookmark not defined.
Gambar 2.11 (a) Citra A (b) Struktur Elemen (c) Hasil Dilasi A oleh B ... Error! Bookmark not defined.
Gambar 2.12 Ilustrasi Closing (a) Citra Awal (b) Struktur Elemen (c) Hasil Closing
oleh Struktur Elemen (Gonzalez and Woods, 2010) ... Error! Bookmark not defined. Gambar 3.1 Tahapan Penerapan StaticThresholding . Error! Bookmark not defined. Gambar 3.2 Tahapan Penerapan Multi Otsu Thresholding ... Error! Bookmark not defined.
Gambar 3.3 Tahap Membandingkan Static Thresholding dan Multi Otsu Thresholding
xv
xv
Gambar 3.4 Identifikasi Sel pada AML M1 (a) Myeloblast (b) Promyelocyte .... Error! Bookmark not defined.
Gambar 3.5 Nukleoli pada Myeloblast... Error! Bookmark not defined. Gambar 3.6 Flowchart Pre-processing Static Thresholding ... Error! Bookmark not defined.
Gambar 3.7 Flowchart Segmentasi Static Thresholding ... Error! Bookmark not defined.
Gambar 3.8 Flowchart Ekstraksi Ciri Static Thresholding dan Multi Otsu
Thresholding ... Error! Bookmark not defined. Gambar 3.9 FlowchartPre-processingMulti Otsu Thresholding ... Error! Bookmark not defined.
Gambar 3.10 Flowchart Segmentasi Multi Otsu Thresholding . Error! Bookmark not defined.
Gambar 4.1 Citra Terindikasi AML M0 ... Error! Bookmark not defined. Gambar 4.2 Citra Terindikasi AML M1 ... Error! Bookmark not defined. Gambar 4.3 Proses Median Filter ... Error! Bookmark not defined. Gambar 4.4 Hasil Proses Pre-Processing (a) Median Filter (b) Konversi Warna YCBCr ... Error! Bookmark not defined. Gambar 4.5 Hasil Segmentasi (a) Hasil Static Thresholding Nukleus (a) Sel sebelum dilakukan proses Closing (c) Sel setelah dilakukan Proses Closing Error! Bookmark not defined.
Gambar 4.6 Hasil Closing pada Static Thresholding Nukleus ... Error! Bookmark not defined.
Gambar 4.7 Hasil Segmenasi Static Thresholding pada Citra AML_M11 ... Error! Bookmark not defined.
xvi
xvi
Gambar 4.10 Ilustrasi Selesi Nukleus pada Segmentasi Stastic Thresholding (a) Nukleus sebelum Diseleksi (b) Nukleus setelah Diseleksi ... Error! Bookmark not defined.
Gambar 4.11 Luas dan Keliling Sel Nukleus Nomor 14 ... Error! Bookmark not defined.
Gambar 4.12 (a) Overlapping WBC Dari Sel Nukleus No.14 (b) Luasan Baru WBC setelah dihitung ulang ... Error! Bookmark not defined. Gambar 4.13 Hasil Ekstraksi Ciri Citra AML M1_3 Segmentasi Static Thresholding
... Error! Bookmark not defined. Gambar 4.14 Sel Nomor 14 pada Citra AML M1_3 .. Error! Bookmark not defined. Gambar 4.15 Citra Hasil Grayscaling ... Error! Bookmark not defined. Gambar 4.16 Algoritma Multi Otsu Thresholding ... Error! Bookmark not defined. Gambar 4.17 Citra Grayscale dengan Intensitas Warna 0 - 5 beserta Histogramnya ... Error! Bookmark not defined. Gambar 4.18 Ilustrasi Multi Otsu Thresholding ... Error! Bookmark not defined. Gambar 4.19 (a) Hasil Segmentasi Multi Otsu Thresholding Nukleus (b) Operasi
Closing ... Error! Bookmark not defined. Gambar 4.20 (a) Hasil Segmentasi Multi Otsu Thresholding WBC (b) Operasi
Closing ... Error! Bookmark not defined. Gambar 4.21 Hasil Pelabelan Sel pada Multi Otsu Thresholding (a) Nukleus (b) WBC ... Error! Bookmark not defined. Gambar 4.22 Ilustrasi Seleksi Nukleus pada Segmentasi Multi Otsu Threshold (a) Sebelum Seleksi (b) Sesudah Seleksi ... Error! Bookmark not defined. Gambar 4.23 Ilustrasi Pencarian Luas WBC (a) Citra Nukleus (b) Pencocokan Posisi Nukleus Dan WBC (c) Luasan WBC Setelah Dihilangkan Overlapping-nya ... Error! Bookmark not defined.
Gambar 4.24 Hasil Ekstraksi Ciri AML M1_3 Segmentasi Multi Otsu Threshold
xvii
xvii
18
18
14 DAFTAR LAMPIRAN
LAMPIRAN A ………... 68
LAMPIRAN A.1: Analisa AML M0….………...68
LAMPIRAN A.2: Analisa AML M2….………...69
