IEEE SIGNAL PROCESSING LETTERS, cilt.20, sa.10, ss.952-955, 2013 (SCI-Expanded)
This paper presents a novel approach for region of interest (ROI) extraction in infrared images based on the one-bit transform. Potential interest regions in the infrared image are obtained by a target mask that is obtained using the one-bit transform in a local way. The histograms of the original image and the masked image are compared and the histogram region that remains unchanged is used to obtain an automated threshold value that is then utilized to detect the ROI in the infrared image. The proposed approach can be used as an effective pre-process for target detection and tracking algorithms in infrared images.