Comparing Dissimilarity Measures for Content-Based Image Retrieval Rui Hu
This event took place on 7th January 2008 at 1:30pm (13:30 GMT)
Knowledge Media Institute, Berrill Building, The Open University, Milton Keynes, United Kingdom, MK7 6AA
Dissimilarity measurement plays a crucial role in content-based image retrieval, where data objects and queries are represented as vectors in high-dimensional content feature spaces. Given the large number of dissimilarity measures that exist, a crucial research question arises: Is there a dependency, if yes, what is the dependency, of a dissimilarity measure?s retrieval performance, on different feature spaces? In this report, we summarize fourteen core dissimilarity measures and classify them into three categories. A systematic performance comparison is carried out to test the e?ectiveness of these dissimilarity measures with six different feature spaces. Based on the experimental results, we recommend some dissimilarity measures for future use.
Dissimilarity measurement plays a crucial role in content-based image retrieval, where data objects and queries are represented as vectors in high-dimensional content feature spaces. Given the large number of dissimilarity measures that exist, a crucial research question arises: Is there a dependency, if yes, what is the dependency, of a dissimilarity measure?s retrieval performance, on different feature spaces? In this report, we summarize fourteen core dissimilarity measures and classify them into three categories. A systematic performance comparison is carried out to test the e?ectiveness of these dissimilarity measures with six different feature spaces. Based on the experimental results, we recommend some dissimilarity measures for future use.
Click below to play the event (29 minutes)