Advertisement billboard detection and geotagging system with inductive transfer learning in deep convolutional neural network

Romi Fadillah Rahmat, Dennis Dennis, Opim Salim Sitompul, Sarah Purnamawati, Rahmat Budiarto

Abstract


In this paper, we propose an approach to detect and geotag advertisement billboard in real-time condition. Our approach is using AlexNet’s Deep Convolutional Neural Network (DCNN) as a pre-trained neural network with 1000 categories for image classification. To improve the performance of the pre-trained neural network, we retrain the network by adding more advertisement billboard images using inductive transfer learning approach. Then, we fine-tuned the output layer into advertisement billboard related categories. Furthermore, the detected advertisement billboard images will be geotagged by inserting Exif metadata into the image file. Experimental results show that the approach achieves 92.7% training accuracy for advertisement billboard detection, while for overall testing results it will give 71,86% testing accuracy.

Keywords


advertisement billboard detection; advertisement billboard geotagging; deep convolutional neural network; image classification; transfer learning;



DOI: http://dx.doi.org/10.12928/telkomnika.v17i5.11276

Article Metrics

Abstract view : 11 times

Refbacks

  • There are currently no refbacks.


Copyright (c) 2019 Universitas Ahmad Dahlan

TELKOMNIKA Telecommunication, Computing, Electronics and Control
ISSN: 1693-6930, e-ISSN: 2302-9293
Universitas Ahmad Dahlan, 4th Campus, 9th Floor, LPPI Room
Jl. Ringroad Selatan, Kragilan, Tamanan, Banguntapan, Bantul, Yogyakarta, Indonesia 55191
Phone: +62 (274) 563515, 511830, 379418, 371120 ext. 4902, Fax: +62 274 564604

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

View TELKOMNIKA Stats