Indonesia ancient temple classification using convolutional neural network

Danukusumo, Kefin Pudi and Pranowo, . and Maslim, Martinus (2017) Indonesia ancient temple classification using convolutional neural network. In: The 2017 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC), 26-28 September 2017, Hotel Tentrem Yogyakarta, Indonesia.

Preview

Text 4 Indonesia Ancient Temple.pdf Download (1MB) | Preview

Abstract

This paper describes the use of convolutional neural network(CNN) method to classify various image and photo of Indonesia ancient temple. The method itself implements Deep Learning technique designed for Computer Vision task. The idea behind CNN is image pre-processing through a stack of convolution layers to create many patterns that can be easily recognized. The result shows that the learning model has an accuracy of 98,99% on the training set and accuracy of 85.57% on the test set. With GPU performance, the time used to train the model is 389.14 seconds.

Actions (login required)

View Item