Locating Human Faces in a Cluttered Scene

@article{Rajagopalan2000LocatingHF,
  title={Locating Human Faces in a Cluttered Scene},
  author={A. N. Rajagopalan and K. Sunil Kumar and Jayashree Karlekar and Rathinam Manivasakan and M. Milind Patil and Uday B. Desai and P. G. Poonacha and Subhasis Chaudhuri},
  journal={Graph. Model.},
  year={2000},
  volume={62},
  pages={323-342}
}
In this paper, we present two new schemes for finding human faces in a photograph. The first scheme adopts a distribution-based model approach to face-finding. Distributions of the face and the face-like manifolds are approximated using higher order statistics (HOS) by deriving a series expansion of the density function in terms of the multivariate Gaussian and the Hermite polynomials in an attempt to get a better approximation to the unknown original density function. An HOS-based data… 

Figures and Tables from this paper

Background learning for robust face recognition with PCA in the presence of clutter

TLDR
A new method within the framework of principal component analysis (PCA) to robustly recognize faces in the presence of clutter by learning the distribution of background patterns and it is shown how this can be done for a given test image.

A Probabilistic Fusion Methodology for Face Recognition

TLDR
A novel probabilistic framework that combines information acquired from different facial features for robust face recognition and is more reliable than a recognition system which uses only one feature, trained individually is proposed.

A Probabilistic FusionMethodology for Face Recognition

TLDR
A novel probabilistic framework that combines information acquired from different facial features for robust face recognition and is more reliable than a recognition system which uses only one feature, trained individually is proposed.

Background learning for robust face recognition

  • R. SinghA. Rajagopalan
  • Computer Science
    Object recognition supported by user interaction for service robots
  • 2002
TLDR
The proposed method outperforms the traditional EFR technique and gives very good results even on complicated scenes, and argues in favor of learning the distribution of background patterns.

Face Recognition Based on Principal Component Analysis

TLDR
The main focus is on frontal two dimensional images that are taken in a controlled environment i.e. the illumination and the background will be constant to find the most efficient approach for developing a facial recognition system.

Face Recognition Based on Principal Component Analysis

TLDR
Principal Component Analysis technique has been used in the proposed system of face recognition and the purpose is to compare the results of the technique under the different conditions and to find the most efficient approach for developing a facial recognition system.

Face Recognition Methodologies Using Component Analysis: The Contemporary Affirmation of the Recent Literature

- This paper explored the contemporary affirmation of the recent literature in the context of face recognition systems, a review motivated by contradictory claims in the literature. This paper shows

Face recognition using multiple facial features

Some conditional and unconditional expectation identities for the multivariate normal with non-zero mean

We give formulas for the conditional and unconditional expectations of products of multivariate Hermite and modified Hermite polynomials, each with a multivariate normal argument. A unified approach

References

SHOWING 1-10 OF 21 REFERENCES

Finding faces in photographs

TLDR
Two new schemes for finding human faces in a photograph are presented, one of which approximates the unknown distributions of the face and the face-like manifolds wing higher order statistics (HOS).

HMM-based architecture for face identification

An original approach for the localization of objects in images

TLDR
An algorithm for the detection of faces in images using shared-weight replicated neural networks, trained to be insensitive to the precise orientation of the face by following an approach similar to the one used for the scale problem.

Example-Based Learning for View-Based Human Face Detection

TLDR
An example-based learning approach for locating vertical frontal views of human faces in complex scenes and shows empirically that the distance metric adopted for computing difference feature vectors, and the "nonface" clusters included in the distribution-based model, are both critical for the success of the system.

Finding Human Faces with a Gaussian Mixture Distribution-Based Face Model

TLDR
A 2-Value metric is proposed for computing distance features between test patterns and the distribution-based model during classification, and empirical results comparing the discriminative power of feature sets based on this metric, versus similar feature setsbased on other classical distribution dependent distance measures.

Human face detection in a scene

TLDR
The problem of scale is solved, and the system is made more practical, so that it can locate unknown human faces spanning a wide range of sizes in a complex black-white picture.

Probabilistic visual learning for object detection

TLDR
An unsupervised technique for visual learning which is based on density estimation in high-dimensional spaces using an eigenspace decomposition and a multivariate Mixture-of-Gaussians model is presented.

Neural network-based face detection

  • H. RowleyS. BalujaT. Kanade
  • Computer Science
    Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1996
TLDR
A neural network-based face detection system that arbitrates between multiple networks to improve performance over a single network using a bootstrap algorithm, which eliminates the difficult task of manually selecting non-face training examples.

Using local orientation and hierarchical spatial feature matching for the robust recognition of objects

TLDR
A new approach to the robust recognition of objects is presented, based on the accumulation of evidence in binary channels followed by a weighted non- linear sum of the evidence accumulators (matched filters, similar to those used in neural networks).