Uwechue / Pandya Human Face Recognition Using Third-Order Synthetic Neural Networks

Erscheinungsjahr 2012
ISBN: 978-1-4615-4092-2
Verlag: Springer US
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 410, 123 Seiten, eBook

Reihe: The Springer International Series in Engineering and Computer Science

Human Face Recognition Using Third-Order Synthetic Neural Networks explores the viability of the application of High-order synthetic neural network technology to transformation-invariant recognition of complex visual patterns. High-order networks require little training data (hence, short training times) and have been used to perform transformation-invariant recognition of relatively simple visual patterns, achieving very high recognition rates. The successful results of these methods provided inspiration to address more practical problems which have grayscale as opposed to binary patterns (e.g., alphanumeric characters, aircraft silhouettes) and are also more complex in nature as opposed to purely edge-extracted images - human face recognition is such a problem. Human Face Recognition Using Third-Order Synthetic Neural Networks serves as an excellent reference for researchers and professionals working on applying neural network technology to the recognition of complex visual patterns.

Zielgruppe

Research

Autoren/Hrsg.

Uwechue, Okechukwu A.

Pandya, Abhijit S.

Inhaltsverzeichnis

1. Introduction.- 1.1 Objective.- 1.2 Background to Neural Networks.- 1.3 Organization of book.- 2. Face Recognition.- 2.1 Background.- 2.2 Various methods.- 2.3 Neural Net Approach.- 3. Implementation of Invariances.- 3.1 Matching of similar triplets.- 3.2 Software implementation.- 4. Simple Pattern Recognition.- 4.1 Procedure.- 4.2 Results.- 5. Facial Pattern Recognition.- 5.1 Two-dimensional moment invariants.- 5.2 Face Segmentation.- 5.3 Isodensity regions.- 5.4 Reducing sensitivity to lighting conditions.- 5.5 Image encoding algorithm.- 5.6 The use of gradient images.- 6. Network Training.- 6.1 Training algorithms.- 6.2 Modifications to training algorithms.- 6.3 Training image data.- 6.4 Results.- 7. Conclusions amp; Contributions 111.- 8. Future Work.- 8.1 Simultaneous Training on all four Isodensity Images.- 8.2 Higher-resolution coarse image size.- 8.3 Automatic face recognition.- 8.4 MIMO third-order networks.- 8.5 Zernike and Complex moments.- 8.6 Recognition of facial expressions (moods).- Index 119.