Image Classification with Multivariate Gaussian Descriptors

Abstract: Techniques based on Bag Of Words approach represent images by quantizing local descriptors and summarizing their distribution in a histogram. Dierently, in this paper we describe an image as multivariate Gaussian distribution, estimated over the extracted local descriptors. The estimated distribution is mapped to a high-dimensional descriptor, by concatenating the mean vector and the projection of the covariance matrix on the Euclidean space tangent to the Riemannian manifold. To deal with large scale datasets and high dimensional feature spaces the Stochastic Gradient Descent solver is adopted. The experimental results on Caltech-101 and ImageCLEF2011 show that the method obtains competitive performance with state-of-the art approaches.

Citation:

Grana, Costantino; Serra, Giuseppe; Manfredi, Marco; Cucchiara, Rita "Image Classification with Multivariate Gaussian Descriptors" 17th International Conference on Image Analysis and Processing (ICIAP 2013), vol. 8157, Naples, ita, pp. 111 -120 , Sep 11-13, 2013 DOI: 10.1007/978-3-642-41184-7_12

 not available

Paper download:

• Author version:
• DOI: 10.1007/978-3-642-41184-7_12