Visual Keyword Image Retrieval Based on Synergetic Neural Network for Web-Based Image Search

Feature extraction and similarity measure are two basickey issues in image retrieval. Combining the advantages of SNNin image recognition and selective attention for image retrieval,a novel visual keywords-driven image retrieval approach basedon these properties has been proposed. By using a predefinedset of visual keywords as prototype patterns stored with theSNN and then measuring the degree of similiarity of the storedimages to the visual keywords, we show that such a visual keyworddriven SNN can provide the framework for image indexing or retrievalwhich is scalable, robust and efficient for web-based search.