Image classification based on log-Euclidean Fisher Vectors for covariance matrix descriptors
| Autor: | Sara Akodad, Charles Yaacoub, Yannick Berthoumieu, Christian Germain, Lionel Bombrun |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Contextual image classification
business.industry Computer science Covariance matrix Deep learning Gaussian Feature extraction MathematicsofComputing_NUMERICALANALYSIS 0211 other engineering and technologies Pattern recognition Fisher vector 02 engineering and technology Covariance Set (abstract data type) symbols.namesake Matrix (mathematics) ComputingMethodologies_PATTERNRECOGNITION Metric (mathematics) 0202 electrical engineering electronic engineering information engineering symbols 020201 artificial intelligence & image processing Artificial intelligence business Gaussian network model 021101 geological & geomatics engineering |
| Zdroj: | IPTA |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|