학술논문

Finding location of a photograph with deep learning
Document Type
Conference
Source
2018 26th Signal Processing and Communications Applications Conference (SIU) Signal Processing and Communications Applications Conference (SIU), 2018 26th. :1-4 May, 2018
Subject
Bioengineering
Communication, Networking and Broadcast Technologies
Computing and Processing
Signal Processing and Analysis
Dogs
Urban areas
Planets
Machine learning
Computational modeling
Predictive models
Computer vision
deep learning
image geo-localization
transfer learning
Language
Abstract
Finding location of a photograph is a challenging computer vision problem. In this paper, different deep learning models which finds the city where a photo was taken were studied for the cities of Turkey first time. For this purpose, a new dataset in which there are photos from 15 cities of Turkey was collected and transfer learning was performed using pre-trained deep convolutional neural network(CNN) models for image recognition on big visual datasets and those pre-trained models are compared according to their prediction performances on proposed dataset.