Abstract: Embodiments of an imaging station and method for repeatable alignment of images are generally described herein. In some embodiments, the imaging station includes a rotatable stage and a monostand. The rotatable stage may include a structure to support sets of handles for positioning of a subject's hands for at least some of the body poses. A camera is positioned on the monostand for capturing images of the subject and is configured to allow the camera to be repeatably positioned with respect to the rotatable stage for each body pose.

Abstract: Embodiments of an image processing system and methods for aligning features suitable for use in early skin-cancer detection systems are described herein. Corresponding skin features between a reference image and a later-captured image are precisely aligned. Curvatures are used to align body outlines of corresponding images using body-background masks. An initial-displacement flowfield map, generated from the aligned body outlines, may be applied to a filtered version of the later-captured image to generate a pre-warped image. The pre-warped image and a filtered version of the reference image are divided into a plurality of overlapping chips and a correlation is performed between corresponding chips. A transformation map may be generated based on the chip correlations.

Abstract: Embodiments of an imaging station and method for repeatable alignment of images are generally described herein. In some embodiments, the imaging station includes a rotatable stage and a monostand. The rotatable stage may include a structure to support sets of handles for positioning of a subject's hands for at least some of the body poses. A camera is positioned on the monostand for capturing images of the subject and is configured to allow the camera to be repeatably positioned with respect to the rotatable stage for each body pose.

Abstract: Embodiments of an image processing system and methods for aligning features suitable for use in early skin-cancer detection systems are described herein. Corresponding skin features between a reference image and a later-captured image are precisely aligned. Curvatures are used to align body outlines of corresponding images using body-background masks. An initial-displacement flowfield map, generated from the aligned body outlines, may be applied to a filtered version of the later-captured image to generate a pre-warped image. The pre-warped image and a filtered version of the reference image are divided into a plurality of overlapping chips and a correlation is performed between corresponding chips. A transformation map may be generated based on the chip correlations.