A Framework for Object-Based Image Retrieval at the Semantic Level
VISUAL '99 Proceedings of the Third International Conference on Visual Information and Information Systems
Hi-index | 0.00 |
This paper describes an approach for object-based image retrieval based on classes of objects in images. In this approach, contours of objects are extracted from images and are represented under a scheme which satisfies scale, rotation, and translation invariance. Classifier learning techniques are used to classify objects in images into different classes. Image similarity calculation is performed based on class information of objects. Experimental results show that the method is effective and efficient.