Comparison of Feature Sets Using Multimedia Translation

Feature selection is very important for many computer vision applications. However, it is hard to find a good measure for the comparison. In this study, feature sets are compared using the translation model of object recognition which is motivated by the availablity of large annotated data sets. Image regions are linked to words using a model which is inspired from the machine translation. The word prediction performance is used to evaluate large number of images.

• Type: Conference
• Year: 2003
• Where: ISCIS
• Authors: Pinar Duygulu, Özge Can Özcanli, Norman Papernick
• Keywords: Feature Selection, ISCIS 2003, Large Annotated Data, Word Prediction Performance