HOG active appearance models
We propose the combination of dense Histogram of Oriented Gradients (HOG) features with Active Appearance Models (AAMs). We employ the efficient Inverse Compositional optimization technique and show results for the task of face fitting. By taking advantage of the descriptive characteristics of HOG f...
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2014
|
| Online Access: | http://eprints.nottingham.ac.uk/31441/ http://eprints.nottingham.ac.uk/31441/ http://eprints.nottingham.ac.uk/31441/1/tzimiroICIP14b.pdf |
| Summary: | We propose the combination of dense Histogram of Oriented Gradients (HOG) features with Active Appearance Models (AAMs). We employ the efficient Inverse Compositional optimization technique and show results for the task of face fitting. By taking advantage of the descriptive characteristics of HOG features, we build robust and accurate AAMs that generalize well to unseen faces with illumination, identity, pose and occlusion variations. Our experiments on challenging in-the-wild databases show that HOG AAMs significantly outperform current state-of-the-art results of discriminative methods trained on larger databases. |
|---|