A Methodology for Evaluating Robustness of Face Recognition Algorithms with Respect to Variations in Pose Angle and Illumination Angle

Little, Greg; Krishna, Sreekar; Black, John A.; Panchanathan, Sethuraman

doi:10.1109/icassp.2005.1415348

Cited by 72 publications

(61 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We tested the accuracy of our pose estimation system on the USF Human ID 3D database [4] and FacePix(30) database [17]. Since our SVR was trained using the USF 3D data, our USF pose estimation tests use a 5-fold crossvalidation scheme.…”

Section: Pose Estimation Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Fully automatic pose-invariant face recognition via 3D pose normalization

Asthana

Marks

Jones

et al. 2011

2011 International Conference on Computer Vision

195

168

View full text Add to dashboard Cite

An ideal approach to the problem of pose-invariant face recognition would handle continuous pose variations, would not be database specific, and would achieve high accuracy without any manual intervention. Most of the existing approaches fail to match one or more of these goals. In this paper, we present a fully automatic system for pose-invariant face recognition that not only meets these requirements but also outperforms other comparable methods. We propose a 3D pose normalization method that is completely automatic and leverages the accurate 2D facial feature points found by the system. The current system can handle 3D pose variation up to +-45 in yaw and +-30 in pitch angles. Recognition experiments were conducted on the USF 3D, Multi-PIE, CMU-PIE, FERET, and FacePix databases. Our system not only shows excellent generalization by achieving high accuracy on all 5 databases but also outperforms other methods convincingly. International Conference on Computer Vision (ICCV)This work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted for nonprofit educational and research purposes provided that all such whole or partial copies include the following: a notice that such copying is by permission of Mitsubishi Electric Research Laboratories, Inc.; an acknowledgment of the authors and individual contributions to the work; and all applicable portions of the copyright notice. Copying, reproduction, or republishing for any other purpose shall require a license with payment of fee to Mitsubishi Electric Research Laboratories, Inc. All rights reserved. AbstractAn ideal approach to the problem of pose-invariant face recognition would handle continuous pose variations, would not be database specific, and would achieve high accuracy without any manual intervention. Most of the existing approaches fail to match one or more of these goals. In this paper, we present a fully automatic system for poseinvariant face recognition that not only meets these requirements but also outperforms other comparable methods. We propose a 3D pose normalization method that is completely automatic and leverages the accurate 2D facial feature points found by the system. The current system can handle 3D pose variation up to ±45• in yaw and ±30• in pitch angles. Recognition experiments were conducted on the USF 3D, Multi-PIE, CMU-PIE, FERET, and FacePix databases. Our system not only shows excellent generalization by achieving high accuracy on all 5 databases but also outperforms other methods convincingly.

show abstract

Section: Pose Estimation Resultsmentioning

confidence: 99%

“…We conducted face recognition experiments on the USF Human ID 3D [4], Multi-PIE [14], CMU-PIE [23], FERET [19], and FacePix(30) [17] databases. The CMU-PIE and FERET databases are the most commonly used databases for face recognition across pose variation, so they are best for comparison with previous approaches.…”

Section: Recognition Experiments and Resultsmentioning

confidence: 99%

Fully automatic pose-invariant face recognition via 3D pose normalization

Asthana

Marks

Jones

et al. 2011

2011 International Conference on Computer Vision

195

168

View full text Add to dashboard Cite

show abstract

“…Experimental results obtained by the proposed method performing on the database of FacePix [25] and MIT-CBCL [31] show big improvements compared with other state-of-the-art algorithms [23,26] in Stage 3 and Stages 1+2+3 .This means that this method is more robust for identity and illumination variations.…”

Section: Head Pose Estimation By Supervised Manifold Learningmentioning

confidence: 63%

“…For the head pose estimation stage, the generalized regression neural network (GRNN) [24] is applied to learn the nonlinear mapping for the unseen data points, and linear multivariate regression is applied to estimate the head pose angle. This idea can be easily extended to the classical algorithms, e.g., Isomap, LLE, and LE, among which the biased LE achieves the lowest error rate on the data set of FacePix [25].…”

Section: The Biased Manifold Embedding (Bme)mentioning

confidence: 99%

Head Pose Estimation via Manifold Learning

Wang¹,

Guo²,

Song³

2017

Manifolds - Current Research Areas

View full text Add to dashboard Cite

For the last decades, manifold learning has shown its advantage of efficient non-linear dimensionality reduction in data analysis. Based on the assumption that informative and discriminative representation of the data lies on a low-dimensional smooth manifold which implicitly embedded in the original high-dimensional space, manifold learning aims to learn the low-dimensional representation following some geometrical protocols, such as preserving piecewise local structure of the original data. Manifold learning also plays an important role in the applications of computer vision, i.e., face image analysis. According to the observations that many face-related research is benefitted by the head pose estimation, and the continuous variation of head pose can be modelled and interpreted as a low-dimensional smooth manifold, we will focus on the head pose estimation via manifold learning in this chapter. Generally, head pose is hard to directly explore from the high-dimensional space interpreted as face images, which is, however, can be efficiently represented in low-dimensional manifold. Therefore, in this chapter, classical manifold learning algorithms are introduced and the corresponding application on head pose estimation are elaborated. Several extensions of manifold learning algorithms which are developed especially for head pose estimation are also discussed and compared.

show abstract

“…• FacePix [24]: This database has been developed to precisely measure the robustness of face analysis algorithms using incremental variations in pose angles. The entire FacePix database contains 16290 images (30 people × 3 sets × 181 images per set).…”

Section: Experimental Setup and Datamentioning

confidence: 99%