Local feature analysis: a general statistical theory for object representation

Penev, P.S.; Atick, Joseph J.

doi:10.1088/0954-898x_7_3_002

Cited by 325 publications

(166 citation statements)

References 62 publications

(60 reference statements)

Supporting

Mentioning

164

Contrasting

Unclassified

Order By: Relevance

“…For example, in [12], in the experiments on the AR face database [13], eigenfaces algorithm [9] obtained 48%, Fisherfaces [10] 45%, and FaceIt [14] 10% correct recognition rate when they were tested on the face images that contain upper face occlusion caused by sunglasses, whereas they attained 27%, 44%, and 81% respectively when they were tested on the face images that contain lower face occlusion caused by scarf.…”

Section: How Much Performance Loss Does Occlusion Cause?mentioning

confidence: 99%

Why Is Facial Occlusion a Challenging Problem?

Ekenel¹,

Stiefelhagen²

2009

Advances in Biometrics

View full text Add to dashboard Cite

Abstract. This paper investigates the main reason for the obtained low performance when the face recognition algorithms are tested on partially occluded face images. It has been observed that in the case of upper face occlusion, missing discriminative information due to occlusion only accounts for a very small part of the performance drop. The main factor is found to be the registration errors due to erroneous facial feature localization. It has been shown that by solving the misalignment problem, very high correct recognition rates can be achieved with a generic local appearance-based face recognition algorithm. In the case of a lower face occlusion, only a slight decrease in the performance is observed, when a local appearance-based face representation approach is used. This indicates the importance of local processing when dealing with partial face occlusion. Moreover, improved alignment increases the correct recognition rate also in the experiments against the lower face occlusion, which shows that face registration plays a key role on face recognition performance.

show abstract

Section: How Much Performance Loss Does Occlusion Cause?mentioning

confidence: 99%

Why Is Facial Occlusion a Challenging Problem?

Ekenel¹,

Stiefelhagen²

2009

Advances in Biometrics

View full text Add to dashboard Cite

show abstract

“…Many face recognition methods based on image appearance have been developed over the past few decades [6][7][8]. Most of these are based on a single face pattern and recognize a face using the model for the expected change.…”

Section: Introductionmentioning

confidence: 99%

Face Recognition Using Multi-viewpoint Patterns for Robot Vision

Fukui

Yamaguchi

2005

Springer Tracts in Advanced Robotics

156

173

View full text Add to dashboard Cite

Abstract. This paper introduces a novel approach for face recognition using multiple face patterns obtained in various views for robot vision. A face pattern may change dramatically due to changes in the relation between the positions of a robot, a subject and light sources. As a robot is not generally able to ascertain such changes by itself, face recognition in robot vision must be robust against variations caused by the changes. Conventional methods using a single face pattern are not capable of dealing with the variations of face pattern. In order to overcome the problem, we have developed a face recognition method based on the constrained mutual subspace method (CMSM) using multi-viewpoint face patterns attributable to the movement of a robot or a subject. The effectiveness of our method for robot vision is demonstrated by means of a preliminary experiment.

show abstract

“…This "recognition by parts" paradigm [11] has been popular in the object recognition research because the approach can be successfully applied to the problem of object recognition with occlusion. Among representative part-based local representations are Local Feature Analysis (LFA) [6] and Local Non-negative Matrix Factorization (LNMF) [13] methods. The LFA method extracts local features based on second-order statistics.…”

Section: Introductionmentioning

confidence: 99%

Robust Face Recognition Based on Part-Based Localized Basis Images

Kim

2005

Image Analysis and Processing – ICIAP 2005

View full text Add to dashboard Cite

Abstract. In order for a subspace projection based method to be robust to local distortion and partial occlusion, the basis images generated by the method should exhibit a part-based local representation. We propose an effective partbased local representation method using ICA architecture I basis images that is robust to local distortion and partial occlusion. The proposed representation only employs locally salient information from important facial parts in order to maximize the benefit of applying the idea of "recognition by parts." We have contrasted our representation with other part-based representations such as LNMF (Localized Non-negative Matrix Factorization) and LFA (Local Feature Analysis). Experimental results show that our representation performs better than PCA, ICA architectureⅠ, ICA architectureⅡ, LFA, and LNMF methods, especially in the cases of partial occlusions and local distortions.

show abstract

Local feature analysis: a general statistical theory for object representation

Cited by 325 publications

References 62 publications

Why Is Facial Occlusion a Challenging Problem?

Why Is Facial Occlusion a Challenging Problem?

Face Recognition Using Multi-viewpoint Patterns for Robot Vision

Robust Face Recognition Based on Part-Based Localized Basis Images

Contact Info

Product

Resources

About