Documents disponibles écrits par cet auteur

Hierarchical Neural Networks for Image Interpretation / Sven Behnke

Public ISBD Titre : Hierarchical Neural Networks for Image Interpretation Type de document : texte imprimé Auteurs : Sven Behnke, Auteur Editeur : Berlin Heidelberg : Springer-Verlag Année de publication : 2003 Collection : Lecture Notes in Computational Science and Engineering Importance : 224 p. Présentation : couv. ill. en coul., ill. Format : 23,4 cm. ISBN/ISSN/EAN : 978-3-540-40722-5 Langues : Anglais (eng) Catégories : AUTOMATISME Index. décimale : 25-05 Application du traitement numérique du signal Résumé : Human performance in visual perception by far exceeds the performance of contemporary computer vision systems. While humans are able to perceive their environment almost instantly and reliably under a wide range of conditions, computer vision systems work well only under controlled conditions in limited domains. This book sets out to reproduce the robustness and speed of human perception by proposing a hierarchical neural network architecture for iterative image interpretation. The proposed architecture can be trained using unsupervised and supervised learning techniques. Applications of the proposed architecture are illustrated using small networks. Furthermore, several larger networks were trained to perform various nontrivial computer vision tasks. Note de contenu : Table of contents I. Theory 2. Neurobiological Background 3. Related Work 4. Neural Abstraction Pyramid Architecture 5. Unsupervised Learning 6. Supervised Learning II. Applications 7. Recognition of Meter Values 8. Binarization of Matrix Codes 9. Learning Iterative Image Reconstruction 10. Face Localization 11. Summary and Conclusions Index Hierarchical Neural Networks for Image Interpretation [texte imprimé] / Sven Behnke, Auteur . - Berlin Heidelberg : Springer-Verlag, 2003 . - 224 p. : couv. ill. en coul., ill. ; 23,4 cm.. - (Lecture Notes in Computational Science and Engineering) . ISBN : 978-3-540-40722-5 Langues : Anglais (eng) Catégories : AUTOMATISME Index. décimale : 25-05 Application du traitement numérique du signal Résumé : Human performance in visual perception by far exceeds the performance of contemporary computer vision systems. While humans are able to perceive their environment almost instantly and reliably under a wide range of conditions, computer vision systems work well only under controlled conditions in limited domains. This book sets out to reproduce the robustness and speed of human perception by proposing a hierarchical neural network architecture for iterative image interpretation. The proposed architecture can be trained using unsupervised and supervised learning techniques. Applications of the proposed architecture are illustrated using small networks. Furthermore, several larger networks were trained to perform various nontrivial computer vision tasks. Note de contenu : Table of contents I. Theory 2. Neurobiological Background 3. Related Work 4. Neural Abstraction Pyramid Architecture 5. Unsupervised Learning 6. Supervised Learning II. Applications 7. Recognition of Meter Values 8. Binarization of Matrix Codes 9. Learning Iterative Image Reconstruction 10. Face Localization 11. Summary and Conclusions Index

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité	N.Inventaire
401	25-05-02	Livre	Bibliothèque de Génie Electrique- USTO	Documentaires	Exclu du prêt	401