We describe the development of novel and efficient approaches and algorithms for a medical image content-based retrieval system capable of extracting and indexing key information about region shape. First, the general structure and the main components of the system are discussed. For grayscale segmentation to locate regions, we have explored a fast active contour approach based on the geometric heat differential equation. Region representation involves a set of extracted shape-based features. A technique for feature organization using N-dimensional feature vectors is employed. The image retrieval process compares similarity of query vectors to the indexed feature vectors. A convex hull model using the heat differential equation is used to organize the index of features to reduce the search space. Some experiments have been performed to test and validate certain portions of our approach. Finally; advantages and disadvantages together with the computational complexity of this system are discussed.
Intelligent shape feature extraction and indexing for efficient content-based medical image retrieval
2004-01-01
316115 byte
Conference paper
Electronic Resource
English
Viewpoint-Invariant Indexing for Content-Based Image Retrieval
British Library Conference Proceedings | 1998
|ABI: analogy-based indexing for content image retrieval
British Library Online Contents | 2004
|Content-based image retrieval by viewpoint-invariant color indexing
British Library Online Contents | 1999
|Efficient Content-Based Image Retrieval Using Automatic Feature Selection
British Library Conference Proceedings | 1995
|Efficient color image indexing and retrieval using color and spatial feature [4551-32]
British Library Conference Proceedings | 2001
|