Pembelajaran Supervised SVM Untuk Identifikasi Obyek Pisau Pada Mesin X-Ray Bandara Juanda
Abstract
The detection process is started changing RGB image to YCbCr and then the canal Cb is chosen followed by 3
processes consisting of making binary image, filtration and segmentation. The binary image aims to change
image to white black, filtration is used to abolish noise, and segmentation is used to float object and dimension
calculation consisting of RV and Σ pixel. After having its value, the process of SVM classification is done by
using data training and testing. The result of SVM process is graphic which will be used to identify a knife object
or not.
Full Text:
PDF (Bahasa Indonesia)References
Pinaki Pratim Acharjya, Ritaban Das &
Dibyendu Ghoshal (2012). Study and
Comparison of Different Edge Detectors for
Image Segmentation. Global Journal of
Computer Science and Technology Graphics &
Vision Volume 12 Issue 13 Version 1.0 Year
Publisher: Global Journals Inc. (USA).
Ade Zulkarnain Hasibuan, Penerapan Edge
Detection Pada Citra Digital Menggunakan
Operator Laplacian Of Gaussian, Seminar
Nasional Teknologi Informasi dan Komunikasi
(SNASTIKOM 2013).
Adrian Schwaninger,“Why do Airport Security
Screeners Sometimes Fail in Convert Tests”.
-1-4244-4170-9/09 $25.00@2009 IEEE
R.H. Sianipar, Herry S. Mangiri, I.K. Wiryajati,
Matlab Untuk Pemrosesan Citra Digital,
Penerbit Informatika Bandung, Oktober 2013.
Eko Prasetyo, Pengolahan Citra Digital dan
Aplikasinya Menggunakan Matlab, Penerbit
Andi Jogjakarta, 2011.
Northern Eclipse Help Reference, Object
Parameter, Morphometric & Densitometric
Parameter.http://www.empix.com/NE%20HELP
/functions/glossary/morphometric_param.htm, 15
Juni 2015.
N. Cristianini and J. Shawe-Taylor. An
Introduction to Support Vector Machines.
Cambridge University Press, 2000.
DOI: http://dx.doi.org/10.36564/njca.v1i1.2
DOI (PDF (Bahasa Indonesia)): http://dx.doi.org/10.36564/njca.v1i1.2.g2
Refbacks
- There are currently no refbacks.
Copyright (c) 2017 Agung Santoso, Isturom Arif, M Hatta
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.