Vision: Signals, Images and Neural Networks - Archive ouverte HAL Accéder directement au contenu
Ouvrages Année : 2010

Vision: Signals, Images and Neural Networks

Résumé

At the fascinating frontiers of Neurobiology, Mathematics and Psychophysics, this book addresses the problem of human and computer vision on the basis of cognitive modeling. After recalling the physics of light, its transformation through media and optics, the principles of the primate's visual system is presented in terms of anatomy and functionality. Then, the neuronal circuitry of the retina is analyzed in terms of spatio-temporal filtering. This basic model is extended to the concept of Neuromorphic circuits for motion processing and to the processing of color in the retina. More in-depth, the adaptive non-linear properties of the photoreceptors and of ganglion cells are addressed, exhibiting all the power of the retinal pre-processing of images as a system of information cleaning suitable for a further cortical processing. As a target of retinal information, the primary visual area is presented as a bank of filters able to extract valuable descriptors of images, suitable for categorization and recognition and also for local information extraction such as saliency and perspective. All along the book, many comparisons between the models and human perception are discussed as well as detailed applications to computer vision.
Fichier non déposé

Dates et versions

hal-00366132 , version 1 (05-03-2009)

Identifiants

Citer

Jeanny Hérault. Vision: Signals, Images and Neural Networks. Allan Murray. World Scientific Publishers, 320 p., 2010, Progress in Neural Processing: Volume 19, 978-981-4273-68-8. ⟨10.1142/7311⟩. ⟨hal-00366132⟩
200 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More