Face recognition using LDA-based algorithms

Question

1. What have the authors contributed in "Face recognition using lda-based algorithms" ?

2. What is the way to avoid the problem?

3. What is the objective of the problem of low-dimensional feature representation in FR systems?

4. What is the optimal discriminant subspace in the FR system?

Accepted Answer

In this short paper, the authors propose a new algorithm that deals with both of the shortcomings in an efficient and cost effective manner.

Accepted Answer

To avoid the problem, a kind of “automatic gain control” is introduced to the weighting procedure in F-LDA [7], where dimensionality is reduced from to atfractional steps instead of one step directly.

Accepted Answer

Given a set of training face images , each of which is represented as a vector of length , i.e., belonging to one of classes , where is the image size and denotes a -dimensional real space, the objective is to find a transformation , based on optimization of certain separability criteria, to produce a representation , where with .

Accepted Answer

Assuming that and represent the null space of and , while and are the complement spaces of and , respectively, the optimal discriminant subspace sought by D-LDA is the intersection space .

Accepted Answer

For different feature extraction tasks, appropriate values for the weighting exponent function should be determined through experimentation using the available training set.

Accepted Answer

According to [12], the matrix that satisfies the above condition is positive definite, i.e., .Similar to , can be expressed as , and then .

Accepted Answer

Based on the analysis given above, it can be known that the most significant discriminant information exist in the intersection subspace , which is usually low-dimensional so that it becomes possible to further apply some sophisticated techniques, such as the rotation strategy of the LDA subspace used in F-LDA, to derive the optimal discriminant features from the intersection subspace.

Accepted Answer

In each step, and its eigenvectors are recomputed based on the changes of in the output space, so that the -dimensional subspace is reoriented and severe overlap between classes in the output space is avoided.

Accepted Answer

The lowest error rate on the ORL database is approximately 4.0% and it is obtained using a weighting function of and a set of feature basis vectors, a result comparable to the best results reported previously in the literatures [14], [15].

Accepted Answer

the rank of is determined by rank , with the number of image classes, which is usually a small value in most of FR tasks, e.g.,in the ORL database, resulting in rank .

Accepted Answer

the weighted between-class scatter matrix can be expressed as:(2)where , is the mean of class , is the number of elements in , andis the Euclidean distance between the means of class and class .

Accepted Answer

The PCA-based representation shown in Fig. 3(a) is optimal in terms of image reconstruction, thereby provides some insight on the original structure of image distribution, which is highly complex and nonseparable.

Accepted Answer

To the best of the author’s knowledge the work reported here constitutes the first attempt to introduce fractional reorientationin a realistic application involving large dimensionality spaces.

Accepted Answer

It is worthy to mention here that both experimental setups introduce SSS conditions since the number of training samples are in both cases much smaller than the dimensionality of the input space.

Face recognition using LDA-based algorithms

Chat with Paper

AI Agents for this Paper

Most frequently asked questions

1. What have the authors contributed in "Face recognition using lda-based algorithms" ?

2. What is the way to avoid the problem?

3. What is the objective of the problem of low-dimensional feature representation in FR systems?

4. What is the optimal discriminant subspace in the FR system?

5. How should the weighting exponent function be determined?

6. What is the heuristic threshold for a real matrix?

7. What is the rank of the intersection subspace?

8. What is the eigenvector of the dimensional subspace?

9. What is the lowest error rate on the ORL database?

10. How many image classes are in the rank of a FR task?

11. What is the weighted between class scatter matrix?

12. What is the representation of the D-LDA subspace?

13. What is the description of the work?

14. What is the difference between the two sets of experiments?

Figures

Citations

2D and 3D face recognition: A survey

Linear discriminant analysis: A detailed tutorial

A Survey of Face Recognition Techniques

Template Matching Techniques in Computer Vision: Theory and Practice

Recent advances in visual and infrared face recognition: a review

References

Eigenfaces for recognition

Eigenfaces vs. Fisherfaces: recognition using class specific linear projection

PCA versus LDA

Face recognition: a convolutional neural-network approach

Human and machine recognition of faces: a survey

Related Papers (5)

Eigenfaces vs. Fisherfaces: recognition using class specific linear projection

Eigenfaces for recognition

Face recognition: A literature survey

PCA versus LDA

The FERET evaluation methodology for face-recognition algorithms