The research described in this chapter indicates the need to provide better models for both short-time and long-time ageing to either predict the age or to compensate for photometric changes in the images due to the time lapse. At the same time it is expected that research in template adaptation and flexible face representations will lead to the development of subject-specific models which take into account the peculiar variabilities of face areas due to transient or permanent changes over time.

Chapter Contents:

• 14.1 Introduction
• 14.2 Analysis of short-time ageing effects
• 14.2.1 Computing differences between faces
• 14.2.2 How faces change over time
• 14.2.3 Temporal evolution of facial features
• 14.2.4 Experimental evaluation
• 14.2.5 Discussion
• 14.3 Analysis of long-time ageing effects
• 14.3.1 Age estimation
• 14.3.2 Computational models for age progression
• 14.3.3 Face recognition across age progression
• 14.4 A novel face database to analyze long-time ageing effects
• 14.4.1 Database collection
• 14.4.2 Database annotation
• 14.4.3 Image preprocessing
• 14.5 Experimental validation and data statistics
• 14.5.1 LBP feature analysis
• 14.5.2 Baseline PCA
• 14.5.3 Sparse representation
• 14.5.4 Results and analysis
• 14.6 Discussion and conclusion
• References

Inspec keywords: photometry; face recognition; image representation; compensation

Other keywords: flexible face representation; face recognition; ageing effect; photometric change compensation; template adaptation; subject specific model development; image processing

Subjects: Computer vision and image processing techniques; Image recognition