This project aims to design and develop new BOF-based approaches for medical image search on large-scale imaging databases.
Content representation and management of medical imaging data is a critical step towards image-based decision support systems such as disease tracking and differential diagnosis. Standard text-based descriptive fields are insufficient for describing rich image properties, and hence more intelligent methods to represent image features are desired. Currently many different ways of feature description and similarity measure have been proposed in the literature, and the bag-of-feature (BOF) approach and its numerous variations have become widely popular.
The opportunity ID for this research opportunity is 1880