On the Use of SIFT Features for Face Authentication

Bicego, Manuele; Lagorio, Andrea; Grosso, Enrico; Tistarelli, Mássimo

doi:10.1109/cvprw.2006.149

Cited by 279 publications

(182 citation statements)

References 21 publications

Supporting

Mentioning

178

Contrasting

Unclassified

Order By: Relevance

“…Because object recognition requires only coarse features while face recognition needs much more subtle and refined discriminative features. An investigation of SIFT features on face representation has ever been done as the first attempt to analyze the SIFT approach in face analysis context [7]. In their experiment, the performance of SIFT feature was evaluated on a database of 52 persons with 5 training images and 7 testing images per person.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, we propose to apply SIFT features on face recognition with only one training sample per person and evaluate its performance under various conditions. Meanwhile, as SIFT can detect person-specific features in different images, we use a Kmeans method instead of overlapping sub-windows in [7] to construct stable effective sub-regions on images and compute the matching similarity of all corresponding region pairs. Moreover, as different sub-regions having different discriminative power we propose a weighting scheme when computing the final average similarity value.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Person-Specific SIFT Features for Face Recognition

Luo

Takikawa

et al. 2007

2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07

159

View full text Add to dashboard Cite

Scale Invariant Feature Transform (SIFT) proposed by Lowe has been widely and successfully applied to object detection and recognition. However, the representation ability of SIFT features in face recognition has rarely been investigated systematically. In this paper, we proposed to use the person-specific SIFT features and a simple nonstatistical matching strategy combined with local and global similarity on key-points clusters to solve face recognition problems. Large scale experiments on FERET and CAS-PEAL face databases using only one training sample per person have been carried out to compare it with other non person-specific features such as Gabor wavelet feature and Local Binary Pattern feature. The experimental results demonstrate the robustness of SIFT features to expression, accessory and pose variations.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Person-Specific SIFT Features for Face Recognition

Luo

Takikawa

et al. 2007

2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07

159

View full text Add to dashboard Cite

show abstract

“…In [4], Bicego et al compare three different matching schemes using SIFT descriptors, namely minimum pair distance matching, matching features around the eyes and the mouth, and matching on a regular grid with overlapping subregions. Only test and training features of corresponding subregions are matched.…”

Section: B Face Identificationmentioning

confidence: 99%

A new method for combined face detection and identification using interest point descriptors

Stein

Fink

2011

Face and Gesture 2011

View full text Add to dashboard Cite

Abstract-Although face recognition has been an active research area for decades, the general problem is still unsolved. While many methods addressing either face detection or face identification emerged, little attention has been paid to the combination or integration of detection and identification.In this paper we propose a combined method for face detection and identification using SIFT descriptors. This combined method includes an existing detection model and a new identification method based on object class invariants (OCIs), which is invariant to translation, scale, in-plane rotation and small 3D viewpoint changes. These models are combined using a bounding box around the OCI to filter face features for identification. We show the highly competitive performance of the newly developed identification method and the effectiveness of the proposed combination scheme.

show abstract

“…HOG features, which have been previously used in applications such as pedestrian detection [7] and face recognition [1], are closely related to the Scale Invariant Feature Transform (SIFT) [18]. SIFT features have emerged as a cutting edge technology for extracting distinctive features from images, to be used in algorithms for tasks like matching different views of an object or scene and face authentication [4]. One of the essential parts of SIFT is that local keypoints are represented using histograms of image gradients which are normalized to be invariant to changes in scale and rotation.…”

Section: Introductionmentioning

confidence: 99%

Precise eye localization using HOG descriptors

Monzo

Albiol

Sastre

et al. 2010

Machine Vision and Applications

View full text Add to dashboard Cite

Precise eye localization using HOG descriptors * David MonzoAlberto Albiol Jorge Sastre Antonio Albiol December 9, 2015 AbstractIn this paper, we present a novel algorithm for precise eye detection. First, a couple of AdaBoost classifiers trained with Haar-like features are used to preselect possible eye locations. Then, a SVM machine that uses HOG descriptors is used to obtain the best pair of eyes among all possible combinations of preselected eyes. Finally, we compare the eye detection results with three state of the art works and a commercial software. The results show that our algorithm achieves the highest accuracy on the FERET and FRGCv1 databases, which is the most complete comparative presented so far.

show abstract

On the Use of SIFT Features for Face Authentication

Abstract: Abstract

Cited by 279 publications

References 21 publications

Person-Specific SIFT Features for Face Recognition

Person-Specific SIFT Features for Face Recognition

A new method for combined face detection and identification using interest point descriptors

Precise eye localization using HOG descriptors

Contact Info

Product

Resources

About