Klasifikasi Jenis Kayu Menggunakan Esktrasi Fitur Gray Level Co-Occurence Matrix dan Multilayer Perceptron
Main Article Content
Keywords
Abstract
The type of wood is generally characterized by color, pattern and fiber because wood physically has almost the same characteristics. To determine the type of wood, experience and knowledge about wood are needed. This study applies digital image processing technology using the GLCM (gray level co-occurrence matrix) feature extraction method to produce feature extraction values on wood texture. The parameter values generated in the GLCM feature extraction are correlation, contrast, energy and homogeneity. The results from feature extraction are then used as a data classification of types of wood using MLP (multilayer perceptron) method. There are 4 wood types going to be involved in this research as datasets i.e., teak, sengon, mahogany, and mindi. The results of this study, obtained the best level of accuracy in validation data of 88.75%. The output of this research is softmax data using MLP method with an error value in the training neared target of data by 0.029421 with the epoch 1.000 iterations.
Keywords : Digital Image Processing, Feature Extraction, GLCM and MLP
Abstrak
Jenis kayu umumnya dicirikan dari warna, corak dan serat karena kayu secara fisik memiliki ciri yang hampir sama. Untuk menentukan jenis kayu, diperlukan pengalaman dan pengetahuan tentang kayu. Penelitian ini menerapkan teknologi pengolahan citra digital menggunakan metode ekstraksi fitur GLCM (gray level co-occourrence matrix) untuk menghasilkan nilai ekstraksi fitur pada tesktur kayu. Parameter nilai dihasilkan pada ekstraksi fitur GLCM adalah correlation, contrast, energy dan homogeneity. Hasil dari parameter GLCM kemudian digunakan sebagai data untuk klasifikasi jenis kayu menggunakan metode MLP (multilayer perceptron). Dalam penelitian ini digunakan 4 jenis kayu sebagai pengujian dan datasheet, yaitu kayu jati, sengon, mahoni dan mindi. Hasil dari penelitian ini, diperoleh tingkat akurasi terbaik pada data validasi sebesar 88,75 %. Keluaran dari penelitian ini berupa data softmax dengan menggunakan metode MLP dengan nilai error pada data training yang mendekati target sebesar 0.029421 dengan epoch 1.000 iterasi.
Kata Kunci : Pengolahan Citra Digital, Ekstraksi Fitur, GLCM dan MLP
References
I. Gunawan, J. Halomoan, and R. D. Atmaja, “Perancangan Sistem Identifikasi Kualitas Kayu Untuk Quality Kontrol Berbasis Pengolahan Citra Digital,” eProceedings Eng., vol. 2, no. 1, 2015.
A. Fahrurozi, S. Madenda, D. Kerami, and others, “Wood texture features extraction by using GLCM combined with various edge detection methods,” in Journal of Physics: Conference Series, 2016, vol. 725, no. 1, p. 12005.
M. I. Fathurrahman, J. Jondri, and A. A. Rohmawati, “Sistem Klasifikasi Kualitas Kayu Jati Berdasarkan Jenis Tekstur Dengan Jaringan Syaraf Tiruan Menggunakan Gray-level-co-occurence Matrix,” eProceedings Eng., vol. 6, no. 2, 2019.
A. W. Sanjaya, “Deteksi Penyakit Kulit Menggunakan Analisis Fitur Warna dan Tekstur Dengan Metode Color Moment, Gray Level Cooccurence Matrix dan Jaringan Saraf Tiruan Backpropagation,” Inst. Teknol. Telkom, 2011.
J. F. Dumanauw, Mengenal Kayu
R. A. Pramunendar, D. P. Prabowo, D. Pergiwati, and K. Latifa, “KLASIFIKASI JENIS KAYU MENGGUNAKAN BACK-PROPAGATION NEURAL NETWORK BERDASARKAN FITUR GRAY LEVEL COOCCURRENCE MATRIX,” Sens 3, vol. 1, no. 1, 2017.
D. Putra, Pengolahan citra digital. Penerbit Andi, 2010.
M. A. Afandi, S. I. Purnama, and R. F. Crisianti, “Implementasi Metode Deteksi Tepi Laplacian dan Jarak Euclidean untuk Identifikasi Tanda Tangan,” J. Nas. Tek. Elektro, vol. 9, no. 1, pp. 34–43, 2020.
S. Santosa, M. Martono, M. B. Utomo, and B. S. Budi, “Seleksi Arah Sudut Komputasi Dan Fitur Glcm Pada Kstraksi Citra Kayu Jati, Mahoni, Mindi, Dan Sengon,” Wahana Tek. Sipil J. Pengemb. Tek. Sipil, vol. 23, no. 2, pp. 77–87, 2019.
K. Lloyd, P. L. Rosin, D. Marshall, and S. C. Moore, “Detecting violent and abnormal crowd activity using temporal analysis of grey level co-occurrence matrix (GLCM)-based texture measures,” Mach. Vis. Appl., vol. 28, no. 3–4, pp. 361–371, 2017.
O. R. Indriani, E. J. Kusuma, C. A. Sari, E. H. Rachmawanto, and others, “Tomatoes classification using K-NN based on GLCM and HSV color space,” in 2017 international conference on innovative and creative information technology (ICITech), 2017, pp. 1–6.
S. Han, J. Pool, J. Tran, and W. Dally, “Learning both weights and connections for efficient neural network,” in Advances in neural information processing systems, 2015, pp. 1135–1143.
N. Purwaningsih, “Penerapan Multilayer Perceptron Untuk Klasifikasi Jenis Kulit Sapi Tersamak,” J. TeknoIf, vol. 4, no. 1, 2016.
K. Kwon, D. Kim, and H. Park, “A parallel MR imaging method using multilayer perceptron,” Med. Phys., vol. 44, no. 12, pp. 6209–6224, 2017.
Article Sidebar
Article Details
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
The authors declare that:
1. This paper has not been published in the same form elsewhere.
2. It will not be submitted anywhere else for publication prior to acceptance/rejection by this Journal.
3. A copyright permission is obtained for materials published elsewhere and which require this permission for reproduction.