Sistem Klasifikasi Kendaraan Berbasis Pengolahan Citra Digital dengan Metode Multilayer Perceptron

Abstract

The evolution of video sensors and hardware can be used for developing traffic monitoring system vision based. It can provide information about vehicle passing by utilizing the camera, so that monitoring can be done automatically. It is needed for the processing systems to provide some information regarding traffic conditions. One such approach is to utilize digital image processing.This research consisted of two phases image processing, namely the process of detection and classification. The process of detection using Haar Cascade Classifier with the training data image form the vehicle and data test form the image state of toll road drawn at random. While, Multilayer Perceptron classification process uses by utilizing the result of the detection process. Vehicle classification is divided into three types, namely car, bus and truck. Then the classification parameters were evaluated by accuracy. The test results vehicle detection indicate the value of accuracy is 92.67. Meanwhile, the classification process is done with phase trial and error to evaluate the parameters that have been determined. Results of the study show the classification system has an average value of the accuracy is 87.60%.