TY - GEN
T1 - Material classification on symmetric positive definite manifolds
AU - Faraki, Masoud
AU - Harandi, Mehrtash T.
AU - Porikli, Fatih
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/2/19
Y1 - 2015/2/19
N2 - This paper tackles the problem of categorizing materials and textures by exploiting the second order statistics. To this end, we introduce the Extrinsic Vector of Locally Aggregated Descriptors (E-VLAD), a method to combine local and structured descriptors into a unified vector representation where each local descriptor is a Covariance Descriptor (CovD). In doing so, we make use of an accelerated method of obtaining a visual codebook where each atom is itself a CovD. We will then introduce an efficient way of aggregating local CovDs into a vector representation. Our method could be understood as an extrinsic extension of the highly acclaimed method of Vector of Locally Aggregated Descriptors [17] (or VLAD) to CovDs. We will show that the proposed method is extremely powerful in classifying materials/ textures and can outperform complex machineries even with simple classifiers.
AB - This paper tackles the problem of categorizing materials and textures by exploiting the second order statistics. To this end, we introduce the Extrinsic Vector of Locally Aggregated Descriptors (E-VLAD), a method to combine local and structured descriptors into a unified vector representation where each local descriptor is a Covariance Descriptor (CovD). In doing so, we make use of an accelerated method of obtaining a visual codebook where each atom is itself a CovD. We will then introduce an efficient way of aggregating local CovDs into a vector representation. Our method could be understood as an extrinsic extension of the highly acclaimed method of Vector of Locally Aggregated Descriptors [17] (or VLAD) to CovDs. We will show that the proposed method is extremely powerful in classifying materials/ textures and can outperform complex machineries even with simple classifiers.
KW - Material classification
KW - Region covariance descriptor
KW - Riemannian manifolds
KW - Texture recognition
KW - Vector of locally aggregated descriptors
UR - http://www.scopus.com/inward/record.url?scp=84925424789&partnerID=8YFLogxK
U2 - 10.1109/WACV.2015.105
DO - 10.1109/WACV.2015.105
M3 - Conference contribution
T3 - Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015
SP - 749
EP - 756
BT - Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015
Y2 - 5 January 2015 through 9 January 2015
ER -