Image and Video Retrieval

Volume 4071 of the series Lecture Notes in Computer Science pp 92-101

A Cascade of Unsupervised and Supervised Neural Networks for Natural Image Classification

  • Julien RosAffiliated withTECH/IRIS/CIM, France Télécom R&D
  • , Christophe LaurentAffiliated withTECH/IRIS/CIM, France Télécom R&D
  • , Grégoire LefebvreAffiliated withTECH/IRIS/CIM, France Télécom R&D


This paper presents an architecture well suited for natural image classification or visual object recognition applications. The image content is described by a distribution of local prototype features obtained by projecting local signatures on a self-organizing map. The local signatures describe singularities around interest points detected by a wavelet-based salient points detector. Finally, images are classified by using a multilayer perceptron receiving local prototypes distribution as input. This architecture obtains good results both in terms of global classification rates and computing times on different well known datasets.