Comparative study between deep learning and bag of visual words for wild-animal recognition

Emmanuel Okafor, Pornntiwa Pawara, Mahir Karaaba, Olarik Surinta, Valeriu Codreanu, Lambert Schomaker, Marco Wiering

OnderzoeksoutputAcademicpeer review

38 Citaten (Scopus)
237 Downloads (Pure)

Samenvatting

© 2016 IEEE.Most research in image classification has focused on applications such as face, object, scene and character recognition. This paper examines a comparative study between deep convolutional neural networks (CNNs) and bag of visual words (BOW) variants for recognizing animals. We developed two variants of the bag of visual words (BOW and HOG-BOW) and examine the use of gray and color information as well as different spatial pooling approaches. We combined the final feature vectors extracted from these BOW variants with a regularized L2 support vector machine (L2-SVM) to distinguish between classes within our datasets. We modified existing deep CNN architectures: AlexNet and GoogleNet, by reducing the number of neurons in each layer of the fully connected layers and last inception layer for both scratch and pre-trained versions. Finally, we compared the existing CNN methods, our modified CNN architectures and the proposed BOW variants on our novel wild-animal dataset (Wild-Anim). The results show that the CNN methods significantly outperform the BOW techniques.
Originele taal-2English
Titel2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016
UitgeverijInstitute of Electrical and Electronics Engineers Inc.
ISBN van geprinte versie9781509042401
DOI's
StatusPublished - 9-feb.-2017

Publicatie series

Naam2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016

Vingerafdruk

Duik in de onderzoeksthema's van 'Comparative study between deep learning and bag of visual words for wild-animal recognition'. Samen vormen ze een unieke vingerafdruk.

Citeer dit