Abstract
Human faces have to be represented before recognition can take place. The role played by representation is most important, and it probably exceeds that played by recognition, known also as classification or identification. Kant described the problem of how anything in the mind can be a “representation” of anything outside the mind as the most difficult riddle in philosophy. We can recognize transformed and dimensionally-reduced as well as original human faces in their “raw” form. Gerald Edelman (1987) has described innate neural architectures that generically implement what is referred to as neural Darwinism. The representations, learned through visual experience, are directly related to the context they operate within and the tasks they have to accomplish. The non-accidental properties of human faces are the particular dimensions the human face representations become tuned for. Such properties eventually induce the features extracted to represent human faces. The features correspond to coordinate axes and they define the face space.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Rights and permissions
Copyright information
© 2007 Springer Science+Buseness Media, LLC
About this chapter
Cite this chapter
(2007). Face Representation. In: Reliable Face Recognition Methods. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-38464-1_5
Download citation
DOI: https://doi.org/10.1007/978-0-387-38464-1_5
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-22372-8
Online ISBN: 978-0-387-38464-1
eBook Packages: Computer ScienceComputer Science (R0)