Towards accurate building recognition using convolutional neural networks

Building recognition from images is a challenging task since pictures can be taken from different angles and under different illumination conditions. Most of the building recognition methods use local and global handcrafted image features and do not consider the rejection scenario, where the method...

Full description

Saved in:
Bibliographic Details
Published in2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON) pp. 1 - 4
Main Authors Farfan-Escobedo, Jeanfranco D., Enciso-Rodas, Lauro, Vargas-Munoz, John E.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2017
Subjects
Artificial neural networks
building recognition
Buildings
classification with rejection
Computational modeling
convolutional neural networks
Feature extraction
Image recognition
Support vector machines
Online AccessGet full text

Cover

More Information
Summary:Building recognition from images is a challenging task since pictures can be taken from different angles and under different illumination conditions. Most of the building recognition methods use local and global handcrafted image features and do not consider the rejection scenario, where the method have to be capable of identifying if a given image does not belong to any of the classes of interest. We propose a method based on convolutional neural networks that obtain effective feature vectors to perform accurate classification of buildings. Additionally, we analyze and propose methods for the problem of classification with rejection.
DOI:10.1109/INTERCON.2017.8079686