TY - GEN
T1 - Hierarchical Gaussianization for image classification
AU - Zhou, Xi
AU - Cui, Na
AU - Li, Zhen
AU - Liang, Feng
AU - Huang, Thomas S.
PY - 2009
Y1 - 2009
N2 - In this paper, we propose a new image representation to capture both the appearance and spatial information for image classification applications. First, we model the feature vectors, from the whole corpus, from each image and at each individual patch, in a Bayesian hierarchical framework using mixtures of Gaussians. After such a hierarchical Gaussianization, each image is represented by a Gaussian mixture model (GMM) for its appearance, and several Gaussian maps for its spatial layout. Then we extract the appearance information from the GMM parameters, and the spatial information from global and local statistics over Gaussian maps. Finally, we employ a supervised dimension reduction technique called DAP (discriminant attribute projection) to remove noise directions and to further enhance the discriminating power of our representation. We justify that the traditional histogram representation and the spatial pyramid matching are special cases of our hierarchical Gaussianization. We compare our new representation with other approaches in scene classification, object recognition and face recognition, and our performance ranks among the top in all three tasks.
AB - In this paper, we propose a new image representation to capture both the appearance and spatial information for image classification applications. First, we model the feature vectors, from the whole corpus, from each image and at each individual patch, in a Bayesian hierarchical framework using mixtures of Gaussians. After such a hierarchical Gaussianization, each image is represented by a Gaussian mixture model (GMM) for its appearance, and several Gaussian maps for its spatial layout. Then we extract the appearance information from the GMM parameters, and the spatial information from global and local statistics over Gaussian maps. Finally, we employ a supervised dimension reduction technique called DAP (discriminant attribute projection) to remove noise directions and to further enhance the discriminating power of our representation. We justify that the traditional histogram representation and the spatial pyramid matching are special cases of our hierarchical Gaussianization. We compare our new representation with other approaches in scene classification, object recognition and face recognition, and our performance ranks among the top in all three tasks.
UR - http://www.scopus.com/inward/record.url?scp=77953214508&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77953214508&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2009.5459435
DO - 10.1109/ICCV.2009.5459435
M3 - Conference contribution
AN - SCOPUS:77953214508
SN - 9781424444205
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 1971
EP - 1977
BT - 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009
T2 - 12th International Conference on Computer Vision, ICCV 2009
Y2 - 29 September 2009 through 2 October 2009
ER -