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 |
| Published: |
2014
|
| Online Access: | https://eprints.nottingham.ac.uk/31435/ |
| _version_ | 1848794201285722112 |
|---|---|
| author | Antonakos, Epameinondas Alabort-i-Medina, Joan Tzimiropoulos, Georgios Zafeiriou, Stefanos |
| author_facet | Antonakos, Epameinondas Alabort-i-Medina, Joan Tzimiropoulos, Georgios Zafeiriou, Stefanos |
| author_sort | Antonakos, Epameinondas |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | 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 outperfrom current state-of-the-art results of discriminative methods trained on larger databases. |
| first_indexed | 2025-11-14T19:12:26Z |
| format | Conference or Workshop Item |
| id | nottingham-31435 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T19:12:26Z |
| publishDate | 2014 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-314352020-05-04T20:16:04Z https://eprints.nottingham.ac.uk/31435/ Hog active appearance models Antonakos, Epameinondas Alabort-i-Medina, Joan Tzimiropoulos, Georgios Zafeiriou, Stefanos 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 outperfrom current state-of-the-art results of discriminative methods trained on larger databases. 2014 Conference or Workshop Item PeerReviewed Antonakos, Epameinondas, Alabort-i-Medina, Joan, Tzimiropoulos, Georgios and Zafeiriou, Stefanos (2014) Hog active appearance models. In: IEEE International Conference on Image Processing, 2014 (ICIP 2014), 27-30 October 2014, Paris, France. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7025044 |
| spellingShingle | Antonakos, Epameinondas Alabort-i-Medina, Joan Tzimiropoulos, Georgios Zafeiriou, Stefanos Hog active appearance models |
| title | Hog active appearance models |
| title_full | Hog active appearance models |
| title_fullStr | Hog active appearance models |
| title_full_unstemmed | Hog active appearance models |
| title_short | Hog active appearance models |
| title_sort | hog active appearance models |
| url | https://eprints.nottingham.ac.uk/31435/ https://eprints.nottingham.ac.uk/31435/ |