No abstract

No abstract

In this paper, we present a novel identity verification system based on Gabor features extracted from range (3D) representations of faces. Multiple landmarks (fiducials) on a face are automatically detected using these Gabor features. Once the landmarks are identified, the Gabor features on all fiducials of a face are concatenated to form a feature vector for that particular face. Linear discriminant analysis (LDA) is used to reduce the dimensionality of the feature vector while maximizing the discrimination power. These novel features were tested on 1196 range images. The same features were also extracted from portrait images, and the accuracies of both modalities were compared. A superior verification accuracy was obtained using the range data, and a highly competitive accuracy to that of other techniques in the literature was also obtained for the portrait data.

We have developed a novel technique to automatically identify a region of interest (ROI) surrounding a spiculated lesion on a mammogram. Our proposed approach for determining the size of the ROI depends on the response of a set of unique Spiculation Filters (SF). The design of these filters is based on manually annotated physical characteristics of spicules. The accuracy of our algorithm is measured in terms of

The goal of this study is to find features that uniquely characterize the true positive (TP) and false positive (FP) detections identified by our recently developed computer-aided detection (CAD) algorithm. As a first step towards this goal, a two-alternative forced choice observer experiment was conducted in which the TP and the highest-ranked FP locations marked by CAD on 47 cases of spiculated masses were shown to three radiologists. Our primary interest in this experiment was to determine if the FP detections made by our algorithm are easily dismissed by experienced radiologists.