Towards accurate building recognition using convolutional neural networks
Jeanfranco Farfan, Lauro Enciso-Rodas, John E. Vargas-Muñoz · 2017
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.