19 December 2016 Architectural style classification of Mexican historical buildings using deep convolutional neural networks and sparse features
Author Affiliations +
Abstract
We propose a convolutional neural network to classify images of buildings using sparse features at the network’s input in conjunction with primary color pixel values. As a result, a trained neuronal model is obtained to classify Mexican buildings in three classes according to the architectural styles: prehispanic, colonial, and modern with an accuracy of 88.01%. The problem of poor information in a training dataset is faced due to the unequal availability of cultural material. We propose a data augmentation and oversampling method to solve this problem. The results are encouraging and allow for prefiltering of the content in the search tasks.
© 2016 SPIE and IS&T
Abraham Montoya Obeso, Jenny Benois-Pineau, Alejandro Álvaro Ramirez Acosta, Mireya Saraí García Vázquez, "Architectural style classification of Mexican historical buildings using deep convolutional neural networks and sparse features," Journal of Electronic Imaging 26(1), 011016 (19 December 2016). https://doi.org/10.1117/1.JEI.26.1.011016 . Submission: Received: 2 July 2016; Accepted: 18 November 2016
Received: 2 July 2016; Accepted: 18 November 2016; Published: 19 December 2016
JOURNAL ARTICLE
11 PAGES


SHARE
Back to Top