CONTENT-BASED IMAGE RETRIEVAL UNTUK MENGIDENTIFIKASI JENIS KAYU BERDASARKAN CITRA DIGITAL MENGGUNAKAN ALGORITMA EIGENIMAGE
DOI:
https://doi.org/10.61805/fahma.v17i1.80Kata Kunci:
pattern recognition, wood, CBIR, eigenimageAbstrak
Indonesia is a tropical country that has no less than 4,000 types of trees. Potential tree species estimated 400 botanical species (species), included in 198 genera (genus) of the 68 tribes (families). Anatomical features include composition, shape, and size of cell or tissue intruders, which can only be observed clearly by using the aid of a magnifying glass like a magnifying glass or microscope. Along with the development of computerized technology, pattern recognition has much to do with a variety of applications and algorithms. One technique to identify an image is to distinguish the texture are the basic components forming the image. This study developed a computer-based technologies to perform pattern recognition (image). The system uses image recognition wood type pore structure of the wood. The introduction of wood types to apply the concept of content-based image retrieval (CBIR) using the algorithm Eigenimage. Identification is done by pattern matching. The test results by using 129 sample, showed the percentage of the system's ability to identify the image timber correctly by 97% (sensitivity), the percentage of the system's ability to recognize the type of wood does not match the sample, 58% (specificity), positive predictive value of 90% (PPV), a negative predictive value of 83% (NPV), and accuracy rate of 89% with an error rate of 11%.
Unduhan
Referensi
Al Fatta, H., 2006, Sistem Presensi Karyawan Berbasis Pengenalan Wajah dengan Algoritma Eigenface, Seminar Nasional Sistem dan Informatika (SNSI), Bali. Halaman 164-170
Akobeng, A.K., 2007, Understanding diagnostic tests 1: sensitivity, specificity and predictive values, Acta Pædiatrica, Vol. 96 No. 3, ISSN:1651-2227, Halaman 338-341.
Damayanti, R. dan Mandang, Y.I., 2007, Pedoman Identifikasi Kayu Kurang Dikenal, Pusat Penelitian Hasil Hutan, Bogor.
Han, J., dan Kamber, M., 2006, Data Mining: Concepts and Techniques Second Edition, Morgan Kauffman, ISBN 978-92-4-156437-3, San Fransisco.
Kurniawan, C., 2009, Pengenalan Citra Wajah dengan Metode Eigenface, Tugas Akhir-S1, Departemen Fisika ITB, bandung.
Mandang, Y.I. dan Pandit, I.K.N., 2002, Pedoman Identifikasi Kayu di Lapangan, Prosea, Bogor.
Mandang, Y. I., Damayanti, R., Komar, T. E., dan Nurjanah, S., 2008, Pedoman Identifikasi Kayu Ramin dan Kayu Mirip Ramin : Departemen Kehutanan Badan Penelitian dan Pengembangan Kehutanan Bekerja Sama dengan International Tropical Timber Organization, CV. Biografika, Bogor, ISBN 978-979-8542-14-7
Pratama, Y. S. A., 2012, Temu Kenali Citra Berbasis Konten Bentuk dan Warna untuk Pengenalan Rambu Lalu-Lintas, Teknik Informatika, Univ. Gunadarma, Jakarta. http://hdl.handle.net/123456789/5249 diakses tanggal 15 April 2015.
Santoso, I., Christyono, Y., dan Indriani, M., 2007, Kinerja Pengenalan Citra Tekstur Menggunakan Analisis Tekstur Metode Run Length, Seminar Nasional Aplikasi Teknologi Informasi (SNATI), Yogyakarta, ISSN: 1907-5022, Halaman F-19 - F-25.
Setiono, T., 2009, Metode Pengenalan Sidik Jari Parsial dengan Menggunakan Delaunay Triangulation dan Algoritma Genetika, Tugas Akhir, Teknik Informatika ITS, Surabaya.
Schalkoff, R., 1992, Pattern Recognition Statistical Structural and Neural Approaches, John Wiley & Sons, New York.
Tomar, P.P.S., Singh, R., Saxena, P.K., dan Sharma, B.K., 2012, A Medical Multimedia Based DSS for Heart Diseases Diagnosis and Training, Canadian Journal on Biomedical Engineering & Technology Vol. 3 No. 2.
Zainal, A., Fauzi, A., Sigit, R. dan Huda, M., 2002, Aplikasi Neural Network pada Pengenalan Pola Tanda Tangan, Makalah Proyek Akhir, Politeknik Elektronika Negeri, Surabaya.
