Real-time predictive zoom tracking for digital still cameras

Zoom tracking is becoming a standard feature in digital still cameras (DSCs). It involves keeping an object of interest in focus during the zooming-in or zooming-out operation. Zoom tracking is normally achieved by moving the focus motor in real-time according to the so-called trace curves in response to changes in the zoom motor position. A trace curve denotes in-focus motor positions versus zoom motor positions for a specific object distance. A zoom tracking approach is characterized by the way these trace curves are estimated and followed. In this paper, a new zoom tracking approach, named predictive zoom tracking (PZT), is introduced based on two prediction models: auto-regressive and recurrent neural network. The performance of this approach is compared with the existing zoom tracking approaches commonly used in DSCs. The real-time implementation results obtained on an actual digital camera platform indicate that the developed PZT approach not only achieves higher tracking accuracies but also effectively addresses the key challenge of zoom tracking, namely the one-to-many mapping problem.

A Novel Surface Reconstruction and Display Method for Cardiac PET Imaging

Positron emission tomography (PET) allows the in vivo assessment of biochemical activity in humans. The newer PET cameras can create several imaging planes, or slices, through an organ inside the body. The interpretation of two-dimensional (2-D) slices of an organ is often difficult for the clinician since he or she has to form a three-dimensional (3-D) mental composite of the structure of interest. We have developed a set of algorithms to reconstruct a functional three-dimensional surface model of the cardiac left ventricle from a set of two-dimensional cross-sectional image slices generated by PET. The theoretical techniques for this reconstruction method are applicable to most organs provided that the appropriate models for the organs are considered. An automatic boundary detection algorithm outlines the surface of the left ventricle from the 2-D images and assigns intensity values to the surface points whose level is proportional to the local activity. A 3-D surface of the intensity levels, with pseudocolor enhancement, is then displayed with the long axis of the heart in a vertical position. Such a display allows the 3-D myocardial tracer uptake to be clearly visualized by the clinician for better diagnosis.     

Interactive Selective and Adaptive Clustering for Detection of Microcalcifications in Mammograms

Estevez, L., Kehtarnavaz, N., and Wendt, R. III, Interactive Selective and Adaptive Clustering for Detection of Microcalcifications in Mammograms,Digital Signal Processing6(1996), 224–232.This paper presents a clustering algorithm, called interactive selective and adaptive clustering (Isaac), to assist radiologists in looking for small clusters of microcalcifications in mammograms. Isaac is developed to identify suspicious microcalcification regions which are missed by other classification techniques due to false positive samples in the feature space. It comprises two parts: (i) selective clustering and (ii) interactive adaptation. The first part reduces the number of false positives by identifying the microcalcification subspace or domains in the feature space. The second part allows the radiologist to improve results by interactively identifying additional false positive or true negative samples. Clinical evaluations of mammograms indicate the potential of using this algorithm as an effective tool to bring microcalcification areas to the attention of the radiologist during a routine reading session of mammograms.     

Skin cancer detection by spectroscopic oblique-incidence reflectometry: classification and physiological origins

Data obtained from 102 skin lesions in vivo by spectroscopic oblique-incidence reflectometry were analyzed. The participating physicians initially divided the skin lesions into two visually distinguishable groups based on the lesions' melanocytic conditions. Group 1 consisted of the following two cancerous and benign subgroups: (1) basal cell carcinomas and squamous cell carcinomas and (2) benign actinic keratoses, seborrheic keratoses, and warts. Group 2 consisted of (1) dysplastic nevi and (2) benign common nevi. For each group, a bootstrap-based Bayes classifier was designed to separate the benign from the dysplastic or cancerous tissues. A genetic algorithm was then used to obtain the most effective combination of spatiospectral features for each classifier. The classifiers, tested with prospective blind studies, reached statistical accuracies of 100% and 95% for groups 1 and 2, respectively. Properties that related to cell-nuclear size, to the concentration of oxyhemoglobin, and to the concentration of deoxyhemoglobin as well as the derived concentration of total hemoglobin and oxygen saturation were defined to explain the origins of the classification outcomes.