PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Use of image regions in context adaptive image classification
Ville Viitaniemi and Jorma Laaksonen
In: 1st International Conference on Semantics and Digital Media Technology, 6-8 Dec 2006, Athens, Greece.


In this paper we describe and discuss our existing PicSOM software framework from the point of view of context-adaptive analysis of image contents, especially its method for using automatic image segmentation. We describe and experimentally validate a modification to the segment-using procedure that both essentially reduces the computational cost and slightly improves classification accuracy. Finally, we apply the segment-using methodology in qualitatively investigating the roles of primary objects and their context in classifying the images of the Pascal VOC Challenge 2006 database.

EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:2556
Deposited By:Ville Viitaniemi
Deposited On:22 November 2006