Dewanto Harjunowibowo, Anif Jamaluddin, Sri Hartati, Rosihan Ari Yuana, Aris Budianto, Farid Ahmadi
The aim of this research is to distinguish the authenticity of paper notes using detection system based on algorithm of Linear Vector Quantization (LVQ) Neural Network. The object image “dancer” of the paper currency Rp. 50.000.00 fluorescent by ultraviolet light used as the input for the system. The coding was built using visual programming language. The size of the feature of the dancer tested object is 114×90 pixels and its Red-Green- Blue-Hue-Saturation-Intensity (RGBHSI) values were extracted as the input for LVQ. The experimental result shows that the system can distinguish the authenticity of original paper notes fairly satisfy. It has accuracy up to 100% of detecting 20 real test case data, and 96% of detecting 22 simulated test case data. © 2015 American Scientific Publishers. All rights reserved.
Physics Education Department, Sebelas Maret University, Surakarta, Indonesia; Electronics and Computer Science Department, Gadjah Mada University, Jogjakarta, Indonesia; IT Education Department, Sebelas Maret University, Surakarta, Indonesia; Electronics Engineering Department, Gadjah Mada University, Jogjakarta, Indonesia; Semarang State University, Semarang, Indonesia
