A Scale-Changeable Image Analysis Method - Engineering Applications of Neural Networks - Part I Access content directly
Conference Papers Year : 2011

A Scale-Changeable Image Analysis Method

Hui Wei
  • Function : Author
  • PersonId : 1014102
Bo Lang
  • Function : Author
  • PersonId : 1014103
Qing-Song Zuo
  • Function : Author
  • PersonId : 1014104


The biological vision system is far more efficient than machine vision system. This is due to the former has rich neural layers for representation and process. In order to obtain a non-task-dependent image representation schema, the early phase of neural vision mechanism is worth simulating. We design a neural model to simulate non-classical receptive field of ganglion cell and its local feedback control circuit, and find it can represent image, beyond pixel level, self-adaptively and regularly. The experimental results prove this method can represent image faithfully with low cost, and can produce a com-pact and abstract approximation to facilitate successive image segmentation as well as integration operation. This representation schema is good at extracting spatial relationship from different components of image, thus it can be applied to formalize image semantics. Further it can be applied to object recognition or image classification tasks in future.
Fichier principal
Vignette du fichier
978-3-642-23957-1_7_Chapter.pdf (384.99 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-01571358 , version 1 (02-08-2017)




Hui Wei, Bo Lang, Qing-Song Zuo. A Scale-Changeable Image Analysis Method. 12th Engineering Applications of Neural Networks (EANN 2011) and 7th Artificial Intelligence Applications and Innovations (AIAI), Sep 2011, Corfu, Greece. pp.63-68, ⟨10.1007/978-3-642-23957-1_7⟩. ⟨hal-01571358⟩
204 View
49 Download



Gmail Mastodon Facebook X LinkedIn More