Automatic Image Tagging seeks to assign relevant words (e.g. “jungle”, “boat”, “trees”) to images that describe the actual content found in the images without intermediate manual labelling. Current approaches are largely based on categorization, and treat the tags independently, so an annotation (jungle,trees) is just as plausible as (jungle,snow). The goal of this dissertation was to develop a...

We present an algorithm for automatic image orientation estimation using a Bayesian learning framework. We demonstrate that a small codebook (the optimal size of codebook is selected using a modified MDL criterion) extracted from a learning vector quantizer (LVQ) can be used to estimate the class-conditional densities of the observed features needed for the Bayesian methodology. We further show...

In this paper, different automatic registration schemes based on different optimization techniques in conjunction with different similarity measures are compared in terms of accuracy and efficiency. Results from every optimization procedure are quantitatively evaluated with respect to the manual registration, which is the standard registration method used in clinical practice. The comparison ha...

Today’s digital content is displayed on a diverse set of devices, ranging from large monitors of various aspect ratios, to small screens of cell phones or handheld devices. Existing display standards, such as HTML, support the ability to dynamically resize the composition of the page to enable viewing on different display sizes. During this resizing process, images always remain fixed in size. ...

An automatic multilevel image segmentation method based on sup-star fuzzy reasoning (SSFR) is presented. Using the well-known sup-star fuzzy reasoning technique, the proposed algorithm combines the global statistical information implied in the histogram with the local information represented by the fuzzy sets of gray-levels, and aggregates all the gray-levels into several classes characterized ...