Semantic Adaptation of Neural Network Classifiers in Image Segmentation

Nikos Simou, Thanos Athanasiadis, Stefanos D. Kollias, Giorgos B. Stamou, Andreas StafylopatisICANN 2008 · OpenReview

Abstract

Semantic analysis of multimedia content is an on going research area that has gained a lot of attention over the last few years. Additionally, machine learning techniques are widely used for multimedia analysis with great success. This work presents a combined approach to semantic adaptation of neural network classifiers in multimedia framework. It is based on a fuzzy reasoning engine which is able to evaluate the outputs and the confidence levels of the neural network classifier, using a knowledge base. Improved image segmentation results are obtained, which are used for adaptation of the network classifier, further increasing its ability to provide accurate classification of the specific content.
BibTeX
@inproceedings{simou2008semantic,
  author = {Nikos Simou and Thanos Athanasiadis and Stefanos D. Kollias and Giorgos B. Stamou and Andreas Stafylopatis},
  title = {{Semantic Adaptation of Neural Network Classifiers in Image Segmentation}},
  booktitle = {ICANN},
  year = {2008},
  url = {https://openreview.net/forum?id=0-ABBpsrcGK},
}

Loading related content...

Figure