Analisis Support Vector Machine (SVM) dalam Pengenalan Citra Bunga Menggunakan Fitur Warna dan Bentuk
Keywords:
SVM, Image Analysis, Color and Shape Features, ClassificationAbstract
This research discusses object recognition in images, with a focus on flower recognition. Automatic flower identification has many practical applications, such as in agriculture, nature conservation, and botanical gardens. However, flower recognition remains a complex challenge because flowers come in a variety of shapes and colors. To overcome this problem, this research proposes the use of the Support Vector Machine (SVM) method in recognizing flower images based on color and shape features. SVM is a powerful classification algorithm and can perform well in cases where the features are in a high dimensional space. This research involves several stages, including image data collection, color and shape feature extraction, as well as training and testing of the SVM model. The SVM method was chosen because of its ability to handle high dimensional data and efficient memory usage. The experimental results show an SVM accuracy rate of 74.29%, indicating significant potential in flower image recognition using SVM with color and shape features.
References
D. H. Apriyanti, “Identification of Orchid Species Using,” pp. 53–57, 2013.
P. A. Dias, A. Tabb, and H. Medeiros, “Apple flower detection using deep convolutional networks,” Comput. Ind., vol. 99, pp. 17–28, 2018.
F. Y. Bisilisin, Y. Herdiyeni, and B. P. Silalahi, “Optimasi K-Means Clustering Menggunakan Particle Swarm Optimization pada Sistem Identifikasi Tumbuhan Obat Berbasis Citra,” J. Ilmu Komput. dan Agri-Informatika, vol. 3, no. 1, p. 37, 2017.
F. Y. Manik and K. S. Saragih, “Klasifikasi Belimbing Menggunakan Support vector machine Berdasarkan Fitur Warna RGB,” IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 11, no. 1, p. 99, 2017.
M.A Bustomi, A.Faricha, A.Ramdhan and Faridawati, “Integrated Image Processing Analysis And Support vector machine Classifier Method For Lungs X-Ray Image Classification”, ARPN Journal of Engineering and Applied Sciences, Vol.13, No.2, p.718, 2018
Fansyuri, M., & Yunita, D. (2023). Implementasi K-Nearest Neighbor Untuk Klasifikasi Jenis Kelamin Berdasarkan Analisis Citra Wajah. Klik, 3(6), 1208–1216.
P. Rosyani, M. Taufik, A. A. Waskita, and D. H. Apriyanti, “Comparison of color model for flower recognition,” 2018 3rd Int. Conf. Inf. Technol. Inf. Syst. Electr. Eng., pp. 10–14, 2019.
D.Rohpandi, A.Sugiharto dan M.Y.Sukma, “Klasifikasi Citra Digital Berbasis Ekstraksi Ciri Berdasarkan Tekstur Menggunakan GLCM Dengan Algoritma K-Nearest Neighbor”, Jurnal Voice Of Informatics, Vol.7, No.2, p.79, 2018
R. Rulaningtyas, A B. Suksmono, T. L. R. Mengko dan G. A. P. Saptawati, “Segmentasi Citra Berwarna dengan Menggunakan Metode Clustering Berbasis Patch untuk Identifikasi Mycobacterium Tuberculosis”, Jurnal Biosains Pascasarjana, Vol. 17, No.1, 2015
I.Setiawan, W. Dewanta, H.A.Nugroho dan H.Supriyono, “Pengolah Citra Dengan Metode Thresholding Dengan Matlab R2014A”, Jurnal Media Infotama Vol.15 No. 2, September 2019
A.A.Arifiyanti, R.M.Pradana dan I.F.Novian, “Klasifikasi Produk Retur dengan Algoritma Pohon Keputusan C4.5”, Jurnal Iptekmedia Komunikasi Teknologi, Volume 22Nomer 1, Mei 2018
E. Pudjiarti, “Prediksi Spam Email Menggunakan Metode Support Vector Machine Dan Particle Swarm Optimization”, Jurnal Pilar Nusa Mandiri, Vol.XII, No.2 September 2016
