age prediction using pca, lda and hybrid

14
Age Prediction using PCA, LDA and Hybrid Methods Mahdi Roozbahani and Shankar Vishwanath CSE 6730 - Data and Visual analytics

Upload: mahdi-roozbahani

Post on 02-Dec-2014

121 views

Category:

Data & Analytics


4 download

DESCRIPTION

It is about PCA on Age prediction via Face.

TRANSCRIPT

Page 1: Age prediction using pca, lda and hybrid

Age Prediction using PCA, LDA and Hybrid MethodsMahdi Roozbahani and Shankar VishwanathCSE 6730 - Data and Visual analytics

Page 2: Age prediction using pca, lda and hybrid

Agenda• 1. Objective

• 2. Applications and Use

• 3. Current Technologies

• 4. Methodology

• 5. Challenges

• 6. Results

• 7. Conclusion

Page 3: Age prediction using pca, lda and hybrid

Objective• 1. Given an image, classify it to a certain age group.

• Using different methods (non-explicit)• 1. PCA• 2. LDA• 3. PCA + LDA Combination

• Cross Validate Results

• Study effects of leaving out ‘first n’ Eigenvectors, to negate shadow/light, camera effects,

Page 4: Age prediction using pca, lda and hybrid

Where Used?• 1. Online Marketing and Advertisement

• 2. Security and Information Purposes

• 3. Age based Content Censorship.

Page 5: Age prediction using pca, lda and hybrid

Current Technologies/Papers • 1. Belhumeur et al. seminal paper on ‘Recognition Using Class

Specific Linear Projection’.

• 2. They experimented with Fishers Linear Discriminant model and Eigenface to project image to low dimensional subspace.

• 3. Gao and Ai studied classification based on Fuzzy LDA method and Gabor features.

• 4. Still a lot to be explored.

Page 6: Age prediction using pca, lda and hybrid

Current Technologies• Face.com has implemented age detection to its photo

scanning API.

• Crime department in Bristol experimented with Age Classification – result not too encouraging.

Page 7: Age prediction using pca, lda and hybrid

Methodology: Idea

• Main idea: Use PCA and other approaches to find vectors that best account for variation of face images in image space.

• Images of faces being similar, will not be randomly distributed in space.

• Can be described by low dimensional subspace.

• We are looking at using PCA as a pre-processor and then use LDA.

Page 8: Age prediction using pca, lda and hybrid

Methodology : Preprocessing

• 1. Data Acquisition and Preprocessing

• Obtain training data and sort them according to age groups

• Trim and resize the images to 61 X 49 pixels.

• Convert to grayscale.

Page 9: Age prediction using pca, lda and hybrid

Methodology: FaceSpace• FaceSpace – PCA Approach

Normalize Data

• Center data by subtracting mean of all images

Build Covariance

Matrix

• Cov matrix is just multiplication of centered data with its transpose

Find Eigenvectors

• mutiply back by original matrix to get the eigen vectors.

Page 10: Age prediction using pca, lda and hybrid

Methodology: FisherSpace• FisherSpace – PCA+LDA Approach

PCA Calc

Sb & Sw

Inv(Sb*Sw)Calc

Eigenvalues

Page 11: Age prediction using pca, lda and hybrid

Methodology: Test Data• Multiply eigenvectors with the original training data to get

class training data.

• Project test data to training data and apply Classifier to determine age group.

• Use l2 Norm distance metric for classification• KNN classifier works too.

Page 12: Age prediction using pca, lda and hybrid

Results

Page 13: Age prediction using pca, lda and hybrid

Challenges• Accuracy highly dependent on data.

• Very difficult to obtain standard data with uniform lighting conditions, camera angles, facial expressions.

• Research papers used subjects with previous age tracked photos under controlled conditions.

• Addition of accessories, spectacles, hairstyles also affected results/accuracy.

• Perceived age not the same as actual age.

Page 14: Age prediction using pca, lda and hybrid

Conclusions• Why PCA is Better than LDA at times?

• When would LDA+PCA work?

• How does leaving first few eigenvectors help?