Web Image Search depending on the Query Approach and re-ranking algorithm

Computer Engineering

Image search re-ranking is an productive way to filter dependant on the text & image dependant search result. Most existing re-ranking approaches are dependant on low graded graphical features. In this project, we implement to explore acceptable attributes for image search re-ranking. Dependant on the classifiers for all the pre defined attributes, each image is represented by an attribute feature consisting of the responses from these classifiers. A hyper-graph is then used to architecture the relationship between images by consolidate low-level graphical features and image attribute features. Hyper-graph rearranging is then performed for ordering the images.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.