Strategies and Benefits of Fusion of 2D and 3D Face Recognition

Hüsken, Michael; Brauckmann, Michael; Gehlen, Stefan; Malsburg, Christoph von der

doi:10.1109/cvpr.2005.584

Cited by 79 publications

(64 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proportion of human contribution to these fusions is given in column 3. The human contribution varies from a minimum of .0439 for Viisage [6] to almost complete dominance for anonymous algorithms A and C. Notably, the man-machine balance varies widely with the algorithm.…”

Section: Fusing Individual Humans and Individual Algorithmsmentioning

confidence: 99%

“…It bears noting, however, that even with the large error rate reductions, the average performance of a human alone is only slightly worse than the paired fusions for the lesser performing algorithms. Given that the paired fusions are worthwhile only when they better the error rates of the algorithm or human operating alone, the pairwise fusions of CMU [6] and NJIT [4] are the most promising candidates for fusion.…”

Section: Fusing Individual Humans and Individual Algorithmsmentioning

confidence: 99%

“…These weights emerge from the PLS as a recipe for optimally combining algorithm and human similarity estimates to predict match status. Averaged across the 49 subject-based fusions, the strongest contributor to the fusion was the algorithm from Viisage Corporation [6]. This was followed by the algorithm from the New Jersey Institute of Technology (NJIT) [4].…”

Section: Fusing Individual Humans With All Algorithmsmentioning

confidence: 99%

“…Human subjects rated the likelihood that the pairs of face images were of the same person. ROC curves computed for the humans and for the algorithms revealed that three algorithms [4][5][6] performed more accurately than humans on the difficult face pairs. Nearly all algorithms performed more accurately than humans on the easy face pairs.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fusing Individual Algorithms and Humans Improves Face Recognition Accuracy

O’Toole

Jiang

Abdi

et al. 2006

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. Recent work indicates that state-of-the-art face recognition algorithms can surpass humans matching identity in pairs of face images taken under different illumination conditions. It has been demonstrated further that fusing algorithm-and human-derived face similarity estimates cuts error rates substantially over the performance of the best algorithms. Here we employed a pattern-based classification procedure to fuse individual human subjects and algorithms with the goal of determining whether strategy differences among humans are strong enough to suggest particular man-machine combinations. The results showed that error rates for the pairwise man-machine fusions were reduced an average of 47 percent when compared to the performance of the algorithms individually. The performance of the best pairwise combinations of individual humans and algorithms was only slightly less accurate than the combination of individual humans with all seven algorithms. The balance of man and machine contributions to the pairwise fusions varied widely, indicating that a one-size-fits-all weighting of human and machine face recognition estimates is not appropriate. . . .

show abstract

Section: Fusing Individual Humans and Individual Algorithmsmentioning

confidence: 99%

Section: Fusing Individual Humans and Individual Algorithmsmentioning

confidence: 99%

Section: Fusing Individual Humans With All Algorithmsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fusing Individual Algorithms and Humans Improves Face Recognition Accuracy

O’Toole

Jiang

Abdi

et al. 2006

Advances in Visual Computing

View full text Add to dashboard Cite

show abstract

“…The most successful feature-based method is graph matching [6], which is based on Dynamic Link Architecture (DLA). It's also extended to 3D recognition [7]. Point signature method proposed by Chua et al [8] belongs to this category.…”

Section: Introductionmentioning

confidence: 99%

Faceprint: Fusion of Local Features for 3D Face Recognition

Zhang

Wang

2009

Advances in Biometrics

View full text Add to dashboard Cite

Abstract. 3D face recognition is a very active biometric research field. Due to the 3D data's insensitivity to illumination and pose variations, 3D face recognition has the potential to perform better than 2D face recognition. In this paper, we focus on local feature based 3D face recognition, and propose a novel Faceprint method. SIFT features are extracted from texture and range images and matched, the matching number of key points together with geodesic distance ratios between models are used as three kinds of matching scores, likelihood ratio based score level fusion is conducted to calculate the final matching score. Thanks to the robustness of SIFT, shape index, and geodesic distance against various changes of geometric transformation, illumination, pose and expression, the Faceprint method is inherently insensitive to these variations. Experimental results indicate that Faceprint method achieves consistently high performance comparing with commonly used SIFT on texture images.

show abstract

A Survey on 3D Modeling of Human Faces for Face Recognition

Huq

Abidi

Kong

et al.

Computational Imaging and Vision

View full text Add to dashboard Cite

In its quest for more reliability and higher recognition rates the face recognition community has been focusing more and more on 3D based recognition. Depth information adds another dimension to facial features and provides ways to minimize the effects of pose and illumination variations for achieving greater recognition accuracy. This chapter reviews, therefore, the major techniques for 3D face modeling, the first step in any 3D assisted face recognition system. The reviewed techniques are laser range scans, 3D from structured light projection, stereo vision, morphing, shape from motion, shape from space carving, and shape from shading. Concepts, accuracy, feasibility, and limitations of these techniques and their effectiveness for 3D face recognition are discussed.

show abstract

Strategies and Benefits of Fusion of 2D and 3D Face Recognition

Cited by 79 publications

References 9 publications

Fusing Individual Algorithms and Humans Improves Face Recognition Accuracy

Fusing Individual Algorithms and Humans Improves Face Recognition Accuracy

Faceprint: Fusion of Local Features for 3D Face Recognition

A Survey on 3D Modeling of Human Faces for Face Recognition

Contact Info

Product

Resources

About