Image classification based on log-Euclidean Fisher Vectors for covariance matrix descriptors

Abstract : This paper introduces an image classification method based on the encoding of a set of covariance matrices. This encoding relies on Fisher vectors adapted to the log-Euclidean metric: the log-Euclidean Fisher vectors (LE FV). This approach is next extended to full local Gaussian descriptors composed by a set of local mean vectors and local covariance matrices. For that, the local Gaussian model is transformed to a zero-mean Gaussian model with an augmented covariance matrix. All these approaches are used to encode handcrafted or deep learning features. Finally, they are applied in a remote sensing application on the UC Merced dataset which consists in classifying land cover images. A sensitivity analysis is carried out to evaluate the potential of the proposed LE FV.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01930156
Contributor : Lionel Bombrun <>
Submitted on : Wednesday, November 21, 2018 - 4:18:13 PM
Last modification on : Saturday, September 28, 2019 - 9:44:36 PM
Long-term archiving on : Friday, February 22, 2019 - 3:14:53 PM

File

Akodad18_IPTA.pdf
Files produced by the author(s)

Identifiers

Citation

Sara Akodad, Lionel Bombrun, Charles Yaacoub, Yannick Berthoumieu, Christian Germain. Image classification based on log-Euclidean Fisher Vectors for covariance matrix descriptors. International Conference on Image Processing Theory, Tools and Applications (IPTA), Nov 2018, Xi'an, China. ⟨10.1109/IPTA.2018.8608154⟩. ⟨hal-01930156⟩

Share

Metrics

Record views

93

Files downloads

228