explores the viability of the application of 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 as opposed to patterns (e.g., alphanumeric characters, aircraft silhouettes) and are also more complex in nature as opposed to purely edge-extracted images - human face recognition such a problem.
serves as an excellent reference for researchers and professionals working on applying neural network technology to the recognition of complex visual patterns.
Produkteigenschaften
- Artikelnummer: 9781461368328
- Medium: Buch
- ISBN: 978-1-4613-6832-8
- Verlag: Springer US
- Erscheinungstermin: 12.10.2012
- Sprache(n): Englisch
- Auflage: Softcover Nachdruck of the original 1. Auflage 1997
- Serie: The Springer International Series in Engineering and Computer Science
- Produktform: Kartoniert
- Gewicht: 230 g
- Seiten: 123
- Format (B x H x T): 155 x 235 x 9 mm
- Ausgabetyp: Kein, Unbekannt
Themen
- Naturwissenschaften
- Physik
- Physik Allgemein
- Theoretische Physik, Mathematische Physik, Computerphysik
- Naturwissenschaften
- Physik
- Physik Allgemein
- Theoretische Physik, Mathematische Physik, Computerphysik