Face Image Analysis by Unsupervised Learning

Name: Face Image Analysis by Unsupervised Learning
Brand: Springer-Verlag New York Inc.
SKU: 9781461356530
Price: 553.26 RON
Availability: InStock

Autor: Marian Stewart Bartlett

Limbă:

Legare: Carte broșată

Editura: Springer-Verlag New York Inc.

Disponibilitate: În depozitul extern

Expediem în 5-8 zile

553.26 lei

Face Image Analysis by Unsupervised Learning explores adaptive approaches to image analysis. It draw...

Informații despre carte

Autor

Marian Stewart Bartlett

Limbă

engleză

Legare

Carte - Carte broșată

Publicat

2012

Pagini

173

EAN

9781461356530

ISBN

1461356539

Enbook ID

06796455

Editura

Springer-Verlag New York Inc.

Greutate

302

Dimensiuni

155 x 235 x 11

Descriere completă

Face Image Analysis by Unsupervised Learning explores adaptive approaches to image analysis. It draws upon principles of unsupervised learning and information theory to adapt processing to the immediate task environment. In contrast to more traditional approaches to image analysis in which relevant structure is determined in advance and extracted using hand-engineered techniques, Face Image Analysis by Unsupervised Learning explores methods that have roots in biological vision and/or learn about the image structure directly from the image ensemble. Particular attention is paid to unsupervised learning techniques for encoding the statistical dependencies in the image ensemble. §The first part of this volume reviews unsupervised learning, information theory, independent component analysis, and their relation to biological vision. Next, a face image representation using independent component analysis (ICA) is developed, which is an unsupervised learning technique based on optimal information transfer between neurons. The ICA representation is compared to a number of other face representations including eigenfaces and Gabor wavelets on tasks of identity recognition and expression analysis. Finally, methods for learning features that are robust to changes in viewpoint and lighting are presented. These studies provide evidence that encoding input dependencies through unsupervised learning is an effective strategy for face recognition. §Face Image Analysis by Unsupervised Learning is suitable as a secondary text for a graduate-level course, and as a reference for researchers and practitioners in industry.

S-ar putea să te intereseze

Clienții care au cumpărat această carte au mai cumpărat și

Cele mai căutate

Categories

Authors

Publishers

Produse

Produse

Cele mai căutate

Categories

Authors

Publishers

Produse

Produse

Face Image Analysis by Unsupervised Learning

Informații despre carte

Descriere completă

S-ar putea să te intereseze

Clienții care au cumpărat această carte au mai cumpărat și