Towards a system for content-based magnetic image retrieval

Abstract

Image retrieval systems provide an effective tool for signature mapping and retrieval that can be applied to magnetic images to assist with preliminary interpretation of large datasets. Image retrieval is currently a very active field of research, motivated by the significant increase in the size of digital image databases in a wide range of image-based fields. It has emerged as a powerful tool for searching and locating a desired image, or part-image, from a large image database. Most existing image retrieval systems characterise the content of an image using low-level visual features such as colour, shape, texture, and spatial relationships between objects in the image. This approach is known as Content-Based Image Retrieval (CBIR). The objective of CBIR is to efficiently find and retrieve those images from a database that are most similar to the user's query image. The challenge when applying CBIR to new types of images is deciding how best to characterise the content of an image so that the results are useful and meaningful. We have developed a model for content-based magnetic image retrieval (CBMIR) using intensity, texture, and shape descriptors. Region and boundary-based shape information is extracted using various edge detection techniques, and texture content is derived using statistical and wavelet transform-based methods. The model has been incorporated into a MATLAB-based system for image retrieval, and results using an experimental magnetic database are presented. The system is interactive, allowing the user's intentions to be incorporated into the retrieval results. We introduce image retrieval as an analysis tool that has been widely adopted in other image-based fields and that has much scope to be further developed and refined for geophysical applications.