PENGUKURAN KEMIRIPAN FITUR PADA SISTEM TEMU KEMBALI CITRA BERBASIS KONTEN MENGGUNAKAN EUCLIDIAN DISTANCE
Abstract
Sistem Temu Kembali Citra berbasis Konten atau sistem, sudah diterapkan pada beberapa mesin pencari seperti Google dan Bing, tetapi citra hasil pencarian yang diberikan masih ada yang tidak relevan dengan citra permintaan. Membangun Temu Kembali Citra berbasis Konten yang dapat memberikan hasil pencarian yang relevan tergantung pada penarikan informasi dari konten citra yang dimasukan. Proses penarikan informasi terhadap konten suatu citra dapat dilakukan dengan menggunakan metode ekstraksi fitur berdasarkan konten warna, bentuk atau tekstur. Penelitian ini, mengukur jarak kesamaan atau kemiripan antara citra query dengan citra pada database menggunakan Euclidian Distance pada Sistem Temu Kembali Citra berbasis Konten berdasarkan warna dan tekstur. Ekstraksi fitur warna dilakukan menggunakan metode Momen Warna, dan fitur tekstur menggunakan Filter Gabor. Persentase presisi tingkat keberhasilan Sistem yang diuji pada setiap kategori menggunakan pengujian secara visual dengan memperhatikan citra groundtruth. Hasil terendah memiliki presisi sejumlah 50% pada kategori gunung dan presisi tertinggi sejumlah 100% pada kategori dinosaurus. Rata-rata persentase presisi tingkat keberhasilan Sistem Temu Kembali Citra berbasis Konten sejumlah 84% dari 10 data uji yang diambil dari database. Hasil yang diharapkan dari penelitian, aplikasi dapat mengidentifikasi citra berdasarkan ekstraksi fitur yang digunakan dan dapat menampilkan 10 citra yang mirip dengan citra query pada perangkat desktop.
References
M. K. Ahirwal, A. Kumar, and G. K. Singh, “An approach to design self assisted CBIR systemâ€, Proc. Int. Conf. Graph. Signal Process. – ICGSP, Vol. 17, pp.21–25, 2017.
K. T. Ahmed, S. Ummesafi, and A. Iqbal, “Content based image retrieval using image features information fusionâ€, Information Fusion, vol. 51, pp.76–99, 2019.
M. K. Alsmadi, “An efficient similarity measure for content based image retrieval using memetic algorithmâ€, Egyptian Journal of Basic and Applied Sciences, vol. 4, no. 2, pp.112–122, 2017.
M. K. Alsmadi, “Query-sensitive similarity measure for content-based image retrieval using meta-heuristic algorithmâ€, Journal of King Saud University-Computer and Inf. Sci., vol. 30, no. 3, pp.373–381, 2018.
M. Bouchakwa, Y. Ayadi, and I. Amous “Multi-level diversification approach of semantic-based image retrieval resultsâ€, Progress in Artificial Intelligence, vol. 9, no. 1, pp.1–30, 2020.
A. Du, L. Wang, and J. Qin, “Image retrieval based on colour and improved NMI texture featuresâ€, Automatika, vol. 60, no. 4, pp.491–499, 2019.
M. A. Aziz, A. A. Ewees, and A. E. Hassanien, “Multi-objective whale optimization algorithm for content-based image retrievalâ€, Multimed. Tools Appl., vol. 77, no. 19, pp.26135–26172, 2018.
D. A. Makandar, R. Somshekhar, and N. Jadav, “Content based image retrievalâ€, World Applied Sciences Journal, 19(3), 404–412. https://doi.org/10.5829/idosi.wasj.2012.19.03.1506, 2019.
R. Rajkumar, and M. V. Sudhamani, “Content based Image Retrieval System using Combination of Color and Shape Features, and Siamese Neural Networkâ€, International Journal of Innovative Technology and Exploring Engineering, 9(2S), 71–77. https://doi.org/10.35940/ijitee.b1053.1292s19, 2019.
T. N. Phalke, and A.Patil, “Content Based Image Retrieval Using Color And Textureâ€, 9(1), 992–1000. https://doi.org/10.5121/sipij.2012.3104, 2017.
N. Varish, and A. K. Pal, “A content based image retrieval using color and texture featuresâ€, ACM International Conference Proceeding Series, 12-13. https://doi.org/10.1145/2979779.2979787, 2016.
B. Babu, R. Vanitha, and K. S. Anish, “Content based image retrieval using color, texture, shape and active re-ranking methodâ€, Indian Journal of Science and Technology, 9(17). https://doi.org/10.17485/ijst/2016/v9i17/93107, 2016.
J. Li, and J. Z. Wang, “Automatic linguistic indexing of pictures by a statistical modeling approachâ€, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 9, pp. 1075-1088, 2003.
A. Amelio, “A new axiomatic methodology for the image similarityâ€, Applied Soft Computing, vol. 81, p. 105474, 2019
Z. Yu, and W. Wang, “Learning DALTS for cross-modal retrieval,†CAAI Transactions on Intelligence Technology, vol. 4, no. 1, pp. 9–16, 2019.
B. Zafar, R. Ashraf, N. Ali, and M. Ahmed., “Intelligent image classification-based on spatial weighted histograms of concentric circlesâ€, Computer Science and Information Systems, vol. 15, no. 3, pp. 615–633, 2018.
S. Fadaei, R. Amirfattahi, and M. R. Ahmadzadeh, “Local derivative radial patterns: a new texture descriptor for content-based image retrievalâ€, Signal Processing, vol. 137, pp. 274–286, 2017.
A. Singla, M. Garg “CBIR Approach Based On Combined HSV, Auto Correlogram, Color Moments And Gabor Waveletâ€, International Journal Of Engineering And Computer Science, ISSN:2319-7242, vol. 3, pp. 9007–9012, Oct, 2014.
M. Kuse, “Filter Gabor Libraryâ€, sumber: https://www.mathworks.com/matlabcentral/fileexchange/38844-gabor-image-features, 1 Februari 2021.
P. Pakutharivu, and M. V. Srinath, "Analysis of Fingerprint Image Enhancement Using Gabor Filtering with Different Orientation Field Values", Indonesian Journal of Electrical Engineering and Computer Science, vol. 5, pp. 427- 432, Feb, 2017.
D. T. Susetianingtias, H.S. Suryadi, S. Madenda, Rodiah, and Fitrianingsih, "Blood vessel extraction and bifurcations detection using hessian matrix of gaussian and euclidian distance", Journal of Theoretical and Applied Information Technology 95(15):3471-3478, Aug, 2017.
M. Kuse, V. Kalasannavar, N. Rajpoot, Y. Wang, and M. Khan, “Local isotropic phase symmetry measure for detection of beta cells and lymphocytesâ€, Journal of Pathology Informatics, 2(2), 2. https://doi.org/10.4103/2153-3539.92028, 2011.
