Face Recognition via AAM and Multi-features Fusion on Riemannian Manifolds

Huo, Hongwen; Feng, Jufu

doi:10.1007/978-3-642-12297-2_57

Cited by 2 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Region covariances have also been used extensively for object tracking [9,10] and for image retrieval and recognition in a surveillance setting [11,12]. [13,14] use Gabor-based region covariances for face recognition, and in [2,15] Guo et al use derivatives of optical flow for action recognition.…”

Section: Related Workmentioning

confidence: 99%

Positive definite dictionary learning for region covariances

Sivalingam

Boley

Morellas

et al. 2011

2011 International Conference on Computer Vision

View full text Add to dashboard Cite

Sparse models have proven to be extremely successful in image processing and computer vision, and most efforts have been focused on sparse representation of vectors. The success of sparse modeling and the popularity of region covariances have inspired the development of sparse coding approaches for positive definite matrices. While in earlier work [1], the dictionary was pre-determined, it is clearly advantageous to learn a concise dictionary adaptively from the data at hand. In this paper, we propose a novel approach for dictionary learning over positive definite matrices. The dictionary is learned by alternating minimization between the sparse coding and dictionary update stages, and two different atom update methods are described. The online versions of the dictionary update techniques are also outlined. Experimental results demonstrate that the proposed learning methods yield better dictionaries for positive definite sparse coding. The learned dictionaries are applied to texture and face data, leading to improved classification accuracy and strong detection performance, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Positive definite dictionary learning for region covariances

Sivalingam

Boley

Morellas

et al. 2011

2011 International Conference on Computer Vision

View full text Add to dashboard Cite

show abstract

“…Furthermore, Porikli et al [28] showed that it can be constructed for arbitrary-sized windows in constant time using integral images. Hence, it has become a popular descriptor for face recognition [24,11,39], human detection [34], tracking [34], object detection [8,32], action recognition [38,7] and pedestrian detection [35].…”

Section: Introductionmentioning

confidence: 99%

Parameterizing Region Covariance: An Efficient Way To Apply Sparse Codes On Second Order Statistics

Dai,

Khamis,

Zhang

et al. 2016

Preprint

View full text Add to dashboard Cite

Sparse representations have been successfully applied to signal processing, computer vision and machine learning. Currently there is a trend to learn sparse models directly on structure data, such as region covariance. However, such methods when combined with region covariance often require complex computation. We present an approach to transform a structured sparse model learning problem to a traditional vectorized sparse modeling problem by constructing a Euclidean space representation for region covariance matrices. Our new representation has multiple advantages. Experiments on several vision tasks demonstrate competitive performance with the state-ofthe-art methods.

show abstract

Face Recognition via AAM and Multi-features Fusion on Riemannian Manifolds

Cited by 2 publications

References 17 publications

Positive definite dictionary learning for region covariances

Positive definite dictionary learning for region covariances

Parameterizing Region Covariance: An Efficient Way To Apply Sparse Codes On Second Order Statistics

Contact Info

Product

Resources

About