Shape descriptors have been used frequently as features to characterize an image for classification and image retrieval tasks. The problem of recognizing classes of objects in images is important for annotation and indexing of Satellite image databases. In this paper, a comparison between shape and texture features for classification is presented. The classification is based on Support Vector Machine (SVM) learning. SVM classifier can be learned from training data of relevance images and irrelevance images marked by users. Using the classifier, the system can retrieve more images relevant to the query in the database efficiently. The goal is to build an accurate and fast query-by-example using content based image retrieval based on the information extracted from satellite image data. We have investigated and described various feature extraction methods relevant to our work in this paper. The experimental results demonstrate that using the shape features give a better classification accuracy than that of the texture features.
Structural indexing of satellite images using automatic classification
2011-03-01
624305 byte
Conference paper
Electronic Resource
English
Automatic Classification Video for Person Indexing
IEEE | 2008
|Automatic Segmentation and Indexing in a Database of Bird Images
British Library Conference Proceedings | 2001
|Automatic Detection from a Satellite Using Hyperspectral Images
British Library Conference Proceedings | 1998
|