Kelly R. Debure

Boundary descriptors may be used effectively in various image based recognition problems. However, when images are acquired in uncontrolled conditions, changes in pose and illumination complicate the alignment process that must occur prior to comparison. The alignment is further complicated when the objects of interest are characterized by open contours and when distinct feature points are absent. We present an application that employs an iterative approach to the alignment of open contours and suggest a method for selecting corresponding points along a pair of contours for the purpose of determining similarity. We demonstrate the success of this approach in recognizing individual bottlenose dolphins from the profiles of their dorsal fins.

DARWIN is a computer vision system, which helps researchers identify individual bottlenose dolphins, Tursiops truncatus, by comparing digital images of the dorsal fins of newly photographed dolphins with a database of previously identified dolphin fins. In additional to dorsal fin images, textual information containing sighting data is stored for each of the previously identified dolphins. The software uses a semiautomated process to create an approximation of the fin outline. The outline is used to formulate a sketch- based query of the dolphin database. The system utilizes a variety of image processing and computer vision algorithms to perform the matching process, which is necessary to identify those previously identified fins, which most closely resemble the unknown fin. The program presents the database fin images to the researcher in rank order for comparison with the new fin image.

Transform-based image coders exploit the information packing ability of some mathematical transforms in order to reduce the number of significant transform coefficients needed to accurately represent an image. Large coefficients are often associated with those regions where an image changes a lot, such as the boundaries between objects with differing visual characteristics. One way to reduce the number of significant transform coefficients is to segment an image into regions of similarity and then apply the transform to each region separately. We propose a novel image compression technique which first segments an image into arbitrary regions and then applies a region-adapted wavelet transform to each region.