Recognizing Imprecisely Localized, Partially Occluded, and Expression Variant Faces from a Single Sample per Class

@article{Martinez2002RecognizingIL,
  title={Recognizing Imprecisely Localized, Partially Occluded, and Expression Variant Faces from a Single Sample per Class},
  author={Aleix M. Martinez},
  journal={IEEE Trans. Pattern Anal. Mach. Intell.},
  year={2002},
  volume={24},
  pages={748-763}
}
  • Aleix M. Martinez
  • Published 1 June 2002
  • Computer Science
  • IEEE Trans. Pattern Anal. Mach. Intell.
The classical way of attempting to solve the face (or object) recognition problem is by using large and representative data sets. In many applications, though, only one sample per class is available to the system. In this contribution, we describe a probabilistic approach that is able to compensate for imprecisely localized, partially occluded, and expression-variant faces even when only one single training sample per class is available to the system. To solve the localization problem, we find… 

Figures from this paper

Recognizing Partially Occluded Faces from a Single Sample Per Class Using String-Based Matching

TLDR
Experimental results demonstrate, for the first time, the feasibility and effectiveness of a high-level syntactic method in face recognition, showing a new strategy for face representation and recognition.

Recognizing partially occluded, expression variant faces from single training image per person with SOM and soft k-NN ensemble

TLDR
This paper addresses problems of classical template-based frontal face recognition techniques by extending a previous local probabilistic approach, using the self-organizing map (SOM) instead of a mixture of Gaussians to learn the subspace that represented each individual.

Robust face recognition with partially occluded images based on a single or a small number of training samples

  • Jie LinJ. MingD. Crookes
  • Computer Science
    2009 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2009
TLDR
The results indicate that the new system is able to perform as well as an oracle model for dealing with various simulated and realistic partial distortions/occlusions without requiring prior information.

Recognizing expression variant faces from a single sample image per class

  • Aleix M. Martinez
  • Computer Science
    2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
  • 2003
TLDR
The experimental results show that the method proposed in this contribution outperforms the classical Euclidean distance (correlation) measure and the PCA (principal component analysis) approach.

Subset Modelling of Face Localization Error , Occlusion , and Expression

Recognition of expression variant faces using weighted subspaces

TLDR
The deformation of the face is shown to be used to solve the posed by images bearing different expressions problem and the superiority of the weighted LDA algorithm over the rest is shown.

Projection into Expression Subspaces for Face Recognition from Single Sample per Person

TLDR
By projecting an image with an arbitrary expression into the expression subspaces, by means of the synthesized images for subjects with one image sample, this paper can obtain more accurate estimation of the within-subject variability and achieve significant improvement in recognition.

Multiple Subcategories Parts-Based Representation for One Sample Face Identification

TLDR
A novel hierarchical probabilistic generative model is proposed, which is capable of achieving an efficient parts-based representation for robust face identification and has the capabilities to deal with small sample set, occlusions, and illumination variances.

Recognizing Partially Occluded Faces from a Single Exemplar Image Per Person

TLDR
This paper proposes a new approach to recognize partially occluded faces when only one exemplar image per person is available, and uses an adaptive weighting technique to assign proper weights to PPCA features.
...

References

SHOWING 1-10 OF 99 REFERENCES

Recognition of partially occluded and/or imprecisely localized faces using a probabilistic approach

  • Aleix M. Martinez
  • Computer Science
    Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)
  • 2000
TLDR
This paper presents a probabilistic approach that attempts to solve both occlusion and localization of faces while using an eigenspace representation and has proven to be superior to a local voting PCA on a set of 2600 face images.

Semantic access of frontal face images: the expression-invariant problem

  • A. Martínez
  • Computer Science
    2000 Proceedings Workshop on Content-based Access of Image and Video Libraries
  • 2000
TLDR
This paper presents a new local, probabilistic approach that accounts for how to robustly identify a person's face for which its learning and testing face images differ in facial expression.

Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

TLDR
A face recognition algorithm which is insensitive to large variation in lighting direction and facial expression is developed, based on Fisher's linear discriminant and produces well separated classes in a low-dimensional subspace, even under severe variations in lighting and facial expressions.

Detecting Faces in Images: A Survey

Images containing faces are essential to intelligent vision-based human-computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation and

Beyond eigenfaces: probabilistic matching for face recognition

TLDR
The performance advantage of this probabilistic technique over nearest-neighbor eigenface matching is demonstrated using results front ARPA's 1996 "FERET" face recognition competition, in which this algorithm was found to be the top performer.

SFS based view synthesis for robust face recognition

  • Wenyi ZhaoR. Chellappa
  • Computer Science
    Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580)
  • 2000
TLDR
This method, based on shape-from-shading (SFS), improves the performance of a face recognition system in handling variations due to pose and illumination via image synthesis.

Face Recognition: The Problem of Compensating for Changes in Illumination Direction

TLDR
Evaluating the sensitivity of image representations to changes in illumination, as well as viewpoint and facial expression, indicated that none of the representations considered is sufficient by itself to overcome image variations because of a change in the direction of illumination.

Automatic Interpretation and Coding of Face Images Using Flexible Models

TLDR
A compact parametrized model of facial appearance which takes into account all sources of variability and can be used for tasks such as image coding, person identification, 3D pose recovery, gender recognition, and expression recognition is described.

The global dimensionality of face space

  • P. S. PenevL. Sirovich
  • Computer Science
    Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580)
  • 2000
TLDR
It is argued that, even with large statistics, the dimensionality of the PCA subspace necessary for adequate representation of the identity information in relatively tightly cropped faces is in the 400-700 range, and it is shown that a dimensionality in the range of 200 is inadequate.

Face recognition from one example view

  • D. BeymerT. Poggio
  • Computer Science
    Proceedings of IEEE International Conference on Computer Vision
  • 1995
TLDR
Oar experiments suggest that among the techniques for expressing prior knowledge of faces, 2D example-based approaches should be considered alongside the more standard 3D modeling techniques.
...