Deteksi Defisiensi Unsur Hara Makro pada Tanaman Kopi …eprints.umm.ac.id/64988/1/PENDAHULUAN.pdf · 2020. 8. 21. · Defisiensi Unsur Hara Makro pada Tanaman Kopi berdasarkan Karakteristik

Deteksi Defisiensi Unsur Hara Makro pada Tanaman Kopi

berdasarkan Karakteristik Gejala Visual Daun menggunakan

MTCD dan JST

Tugas Akhir

Diajukan Untuk Memenuhi

Persyaratan Guna Meraih Gelar Sarjana Strata 1

Teknik Informatika Universitas Muhammadiyah Malang

Ahmad Annas Al Hakim

(201310370311182)

Bidang Minat

Data Science

PROGRAM STUDI INFORMATIKA

FAKULTAS TEKNIK

UNIVERSITAS MUHAMMADIYAH MALANG

2020

iii

LEMBAR PERSETUJUAN

iv

LEMBAR PENGESAHAN

v

LEMBAR PERNYATAAN

vi

LEMBAR PERSEMBAHAN

Puji syukur kepada Allah SWT atas Rahmat dan Karunia-Nya sehingga

penulis dapat menyelesaikan tugas akhir ini. Penulis menyampaikan ucapan terima

kasih yang sebesar-besarnya kepada :

1. Allah SWT yang selalu memberikan nikmat iman dan Islam, serta

telah memberikan kesehatan dan petunjuk dalam pengerjaan tugas

akhir ini;

2. Rasulullah Muhammad SAW. Tauladan kita dalam segala aspek

kehidupan;

3. Kedua orang tua yang selalu sabar dan tiada henti mendoakan demi

kesuksesan anaknya;

4. Bapak Agus Eko Minarno, M.Kom., selaku Dosen Pembimbing 1

dan Bapak Yufis Azhar, M.Kom., selaku Dosen Pembimbing 2 yang

selalu bersedia meluangkan waktu dan tenaga untuk memberikan

arahan petunjuk, serta saran dengan sabar karena terkadang penulis

menyadari perlu beberapa kali penjelasan agar penulis dapat

memahami.

5. Ibu Gita Indah Marthasari, M.Kom., selaku Ketua Jurusan Teknik

Informatika Universitas Muhammadiyah Malang;

6. Semua staf Pusat Penelitian Kopi dan Kakao Indonesia yang telah

bersedia memberikan tempat untuk mendapatkan data penelitian;

7. Semua dosen pengajar di Jurusan Teknik Informatika Universitas

Muhammadiyah Malang yang telah memberikan ilmu yang sangat

bermanfaat;

8. Seluruh teman-teman yang tidak bisa penulis sebutkan satu per satu,

terima kasih atas dukungan, bantuan dan doa kalian selama ini.

vii

KATA PENGANTAR

Segala puji bagi Allah SWT, yang telah memberikan Rahmat dan Karunia-

Nya, sehingga penulis dapat menyelesaikan tugas akhir yang berjudul “Deteksi

Defisiensi Unsur Hara Makro pada Tanaman Kopi berdasarkan Karakteristik

Gejala Visual Daun menggunakan MTCD dan JST”

Penyusunan tugas akhir ini diajukan untuk memenuhi syarat akademis

dalam rangka menyelesaikan studi Strata 1 Program Studi Teknik Informatika di

Fakultas Teknik Universitas Muhammadiyah Malang.

Peneliti menyadari masih banyak kekurangan dan keterbatasan dalam

penulisan tugas akhir ini. Untuk itu, penulis sangat mengharapkan saran yang

sangat membangun agar tulisan ini dapat berguna untuk perkembangan ilmu

pengetahuan ke depan.

Malang, 20 Juli 2020

Penulis

Ahmad Annas Al Hakim

viii

DAFTAR ISI

ABSTRAK .............................................................................................................. i

ABSTRACT ............................................................................................................ ii

LEMBAR PERSETUJUAN ................................................................................ iii

LEMBAR PENGESAHAN ................................................................................. iv

LEMBAR PERNYATAAN .................................................................................. v

LEMBAR PERSEMBAHAN .............................................................................. vi

KATA PENGANTAR ......................................................................................... vii

DAFTAR ISI ....................................................................................................... viii

DAFTAR GAMBAR ............................................................................................ xi

DAFTAR TABEL ............................................................................................... xii

DAFTAR LAMPIRAN ...................................................................................... xiii

BAB I PEDAHULUAN ......................................................................................... 1

1.1 Latar Belakang .................................................................................... 1

1.2 Rumusan Masalah .............................................................................. 4

1.3 Tujuan Penelitian ................................................................................ 4

1.4 Cakupan Masalah ............................................................................... 4

1.5 Metodologi ........................................................................................... 5

1.6 Sistematika Penulisan ......................................................................... 5

BAB II LANDASAN TEORI ............................................................................... 7

2.1 Gejala Defisiensi Hara Makro pada Daun Kopi .............................. 7

2.2 Color Feature ....................................................................................... 8

2.3 Edge Feature ........................................................................................ 9

2.3.1 Operator Sobel ................................................................................. 9

2.3.2 Deteksi Texron ............................................................................... 11

2.4 Gray Level Co-Occurrence Matrix (GLCM).................................... 12

ix

2.5 Jaringan Saraf Tiruan (JST) ........................................................... 13

BAB III METODE PENELITIAN .................................................................... 16

3.1 Metodologi ......................................................................................... 16

3.2 Waktu dan Tempat Penelitian ......................................................... 16

3.3 Tahap Pengumpulan Data ............................................................... 16

3.4 Tahap Analisis Data ......................................................................... 17

3.5 Perencanaan Pengolahan Citra ....................................................... 18

3.6 Multi Texton Histogram .................................................................... 19

3.6.1 Color Feature ................................................................................. 19

3.6.2 Edge Feature .................................................................................. 20

3.6.2.1 Operator Sobel ....................................................................... 20

3.6.3 Gray Level Co-Occurrence Matrix (GLCM) ................................ 22

3.7 Representasi Fitur MTCD ............................................................... 26

3.8 Database ............................................................................................. 27

3.9 Jaringan Saraf Tiruan (JST) ........................................................... 27

3.9.1 Fungsi Aktivasi .............................................................................. 30

3.9.2 Algoritma Optimasi ...................................................................... 30

3.9.3 Epoch .............................................................................................. 30

3.10 Dataset ................................................................................................ 31

3.11 Pengujian ........................................................................................... 31

3.12 Lingkungan Kerja............................................................................. 32

BAB IV HASIL DAN PEMBAHASAN ............................................................ 33

4.1 Implementasi Ekstraksi Fitur MTCD ............................................ 33

4.1.1 Import Library ................................................................................ 33

4.1.2 Fungsi Color Feature ..................................................................... 34

4.1.3 Fungsi Edge Feature ...................................................................... 35

x

4.1.4 Fungsi Deteksi Texton ................................................................... 37

4.1.5 Fungsi GLCM ................................................................................ 38

4.1.6 Fungsi Indexing ............................................................................. 40

4.2 Implementasi Jaringan Saraf Tiruan ............................................. 41

4.2.1 Workflows Neural Network ........................................................... 41

4.2.1.1 Widget CSV File Import ......................................................... 42

4.2.1.2 Widget Data Table................................................................... 42

4.2.1.3 Widget Create Class ................................................................ 43

4.2.1.4 Widget Neural Network .......................................................... 44

4.2.1.5 Widget Predictions .................................................................. 45

4.3 Pengujian ........................................................................................... 45

BAB V KESIMPULAN ...................................................................................... 48

5.1 Kesimpulan ........................................................................................ 48

5.2 Saran .................................................................................................. 49

DAFTAR PUSTAKA .......................................................................................... 50

LAMPIRAN ......................................................................................................... 53

xi

DAFTAR GAMBAR

Gambar 2.1 Grid dan MTH Texton. Grid (Kiri); (T1-T4) MTH Texton ............. 11

Gambar 2.2 MTCD Texton .................................................................................. 11

Gambar 2.3 Perbedaan Deteksi Texton pada MTH dan MTCD. (a-d) Deteksi

Texton MTH; (e-h) Deteksi Texton MTCD ..................................... 12

Gambar 2.4 Arsitektur Multi Layer Perceptron (MLP) ...................................... 14

Gambar 3.1 Diagram Alir Tahapan Penelitian .................................................... 16

Gambar 3.2 Flowchart Perencanaan Pengolahan Citra ....................................... 18

Gambar 3.3 Citra Kuantisasi ............................................................................... 19

Gambar 3.4 Deteksi Texton MTCD pada Kuantisasi Warna .............................. 20

Gambar 3.5 Rancangan Arsitektur Jaringan Saraf Tiruan ................................... 27

Gambar 3.6 Contoh Citra Daun Kopi .................................................................. 31

Gambar 4.1 Source Code Import Library ............................................................ 33

Gambar 4.2 Source Code Fungsi Level Warna Citra .......................................... 34

Gambar 4.3 Source Code Fungsi Kuantisasi Warna ........................................... 34

Gambar 4.4 Source Code Fungsi Edge Feature .................................................. 36

Gambar 4.5 Source Code Fungsi Deteksi Texton ................................................ 38

Gambar 4.6 Source Code Fungsi GLCM ............................................................ 38

Gambar 4.7 Source Code Fungsi Indexing .......................................................... 40

Gambar 4.8 Workflows Neural Network ............................................................. 41

Gambar 4.9 Widget CSV File Import................................................................... 42

Gambar 4.10 Widget Data Table ......................................................................... 43

Gambar 4.11 Widget Create Class ...................................................................... 43

Gambar 4.12 Widget Neural Network ................................................................. 44

Gambar 4.13 Widget Predictions......................................................................... 45

xii

DAFTAR TABEL

Tabel 2.1 Karakteristik Gejala Visual Defisiensi Hara Makro .............................. 7

Tabel 2.2 Kuantisasi Warna ................................................................................... 9

Tabel 2.3 Kuantisasi Tepi ..................................................................................... 10

Tabel 3.1 Kuantisasi Warna ................................................................................. 19

Tabel 3.2 Kuantisasi Tepi ..................................................................................... 21

Tabel 4.1 Potongan Hasil Ekstraksi Color Feature ............................................. 35

Tabel 4.2 Potongan Hasil Ekstraksi Edge Feature ............................................... 36

Tabel 4.3 Potongan Hasil Ekstraksi GLCM ......................................................... 39

Tabel 4.4 Rangkuman Nilai Akurasi Tertinggi dengan Tuning Parameter ......... 46

xiii

DAFTAR LAMPIRAN

Lampiran 1 Sampel Pengambilan Data ............................................................... 53

Lampiran 2 Pengujian Nilai Akurasi dengan Tuning Parameter ........................ 58

50

DAFTAR PUSTAKA

[1] P. dan M. Teguh Wahyudi, Ed., “Pengelolaan Hara Tanaman,” in Kopi:

Sejarah, Botani, Proses Produksi, Pengolahan, Produksi Hilir, dan Sistem

Kemitraan, Pertama., Gadjah Mada University Press, 2016, pp. 235–252.

[2] K. N. Setiawan and I. M. S. Putra, “Klasifikasi Citra Mammogram

Menggunakan Metode K-Means , GLCM , dan Support Vector Machine (

SVM ),” vol. 6, no. 1, pp. 13–24, 2018.

[3] N. Ulinnuha and H. Sa’dyah, “Sistem temu kembali citra untuk e-

commerce,” vol. 1, no. 1, pp. 35–41, 2015.

[4] G. H. Liu and J. Y. Yang, “Image retrieval based on the texton co-occurrence

matrix,” Pattern Recognit., vol. 41, no. 12, pp. 3521–3527, 2008.

[5] G. Liu, L. Zhang, Y. Hou, Z. Li, and J. Yang, “Image retrieval based on

multi-texton histogram,” Pattern Recognit., vol. 43, no. 7, pp. 2380–2389,

2010.

[6] A. E. Minarno, Y. Munarko, A. Kurniawardhani, and F. Bimantoro,

“Classification of Texture Using Multi Texton Histogram and Probabilistic

Neural Network,” IOP Conf. Ser. Mater. Sci. Eng., vol. 105, no. 1, 2016.

[7] M. Y. Qazi and M. S. Farid, “Content based image retrieval using localized

multi-texton histogram,” Proc. - 11th Int. Conf. Front. Inf. Technol. FIT

2013, pp. 107–112, 2013.

[8] X. Wang and Z. Wang, “A novel method for image retrieval based on

structure elements’ descriptor,” J. Vis. Commun. Image Represent., vol. 24,

no. 1, pp. 63–74, 2013.

[9] S. Mohan and S. Suresh Kumar, “A New Shape Feature Extraction Method

for Leaf Image Retrieval,” Lect. Notes Electr. Eng., vol. 221 LNEE, no.

VOL. 1, 2013.

[10] A. E. Minarno and N. Suciati, “IMAGE RETRIEVAL USING MULTI

TEXTON CO-,” vol. 67, no. 1, pp. 103–110, 2014.

51

[11] A. Mozaffari, M. Emami, and A. Fathi, A comprehensive investigation into

the performance, robustness, scalability and convergence of chaos-

enhanced evolutionary algorithms with boundary constraints, vol. 52, no. 4.

Springer Netherlands, 2019.

[12] D. Wang, H. He, and D. Liu, “Intelligent Optimal Control with Critic

Learning for a Nonlinear Overhead Crane System,” IEEE Trans. Ind.

Informatics, vol. 14, no. 7, pp. 2932–2940, 2018.

[13] D. Cho, Y. W. Tai, and I. S. Kweon, “Deep Convolutional Neural Network

for Natural Image Matting Using Initial Alpha Mattes,” IEEE Trans. Image

Process., vol. 28, no. 3, pp. 1054–1067, 2019.

[14] A. Samsudin and R. Budiarto, “Lightweight and Cost-Effective,” pp. 525–

526.

[15] Y. Lecun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no.

7553, pp. 436–444, 2015.

[16] R. Toufiq and M. R. Islam, “Face recognition system using PCA-ANN

technique with feature fusion method,” 1st Int. Conf. Electr. Eng. Inf.

Commun. Technol. ICEEICT 2014, 2014.

[17] W. Yue, Z. Wang, H. Chen, A. Payne, and X. Liu, “Machine Learning with

Applications in Breast Cancer Diagnosis and Prognosis,” Designs, vol. 2, no.

2, p. 13, 2018.

[18] A. E. Minarno, A. S. Maulani, A. Kurniawardhani, and F. Bimantoro,

“Comparison of Methods for Batik Classification Using Multi Texton

Histogram,” vol. 16, no. 3, pp. 1358–1366, 2018.

[19] S. E. Indraani, I. D. Jumaddina, S. Ridha, and S. Sinaga, “Implementasi Edge

Detection Pada Citra Grayscale dengan Metode Operator Prewitt dan

Operator Sobel,” pp. 1–5, 2014.

[20] A. E. Minarno and N. Suciati, “Batik image retrieval based on color

difference histogram and gray level co-occurrence matrix,” Telkomnika

(Telecommunication Comput. Electron. Control., vol. 12, no. 3, pp. 597–

52

604, 2014.

[21] R. Widodo, A. W. Widodo, and A. Supriyanto, “Pemanfaatan Ciri Gray

Level Co-Occurrence Matrix ( GLCM ) Citra Buah Jeruk Keprok ( Citrus

reticulata Blanco ) untuk Klasifikasi Mutu,” J. Pengemb. Teknol. Inf. dan

Ilmu Komput., vol. 2, no. 11, pp. 5769–5776, 2018.

[22] A. A. Kasim and A. Harjoko, “Klasifikasi Citra Batik Menggunakan

Jaringan Syaraf Tiruan Berdasarkan Gray Level Co- Occurrence Matrices (

GLCM ),” Semin. Nas. Apl. Teknol. Inf. Yogyakarta, 21 Juni 2014, pp. 7–13,

2014.

[23] O. I. Abiodun, A. Jantan, A. E. Omolara, K. V. Dada, N. A. E. Mohamed,

and H. Arshad, “State-of-the-art in artificial neural network applications: A

survey,” Heliyon, vol. 4, no. 11, p. e00938, 2018.

[24] W. S. Eka Putra, “Klasifikasi Citra Menggunakan Convolutional Neural

Network (CNN) pada Caltech 101,” J. Tek. ITS, vol. 5, no. 1, 2016.

[25] N. G. A. . H. Saptarini and R. Y. Dillak, “Content Based Image Retrieval

Menggunakan Moment Invariant , Tekstur Dan Backpropagation,” vol.

2012, no. semnasIF, pp. 86–91, 2012.