A simple and advanced match software program has been developed that efficiently combines the accuracy and speed of a computer with the knowledge of the user to recognize important features in the image. The program takes advantage of a user's ability to determine if the match progresses in the wrong direction and overcomes the time-consuming process of parameter tuning and rerunning of the registration algorithm. The user needs to to load the reference and the floating image and the images are overlaid at 50% transparency for simultaneous viewing. The user initiates an affine transformation matrix function that automatically matches the floating image to the reference and the function translates, rotates, zooms, slants, and deforms the floating image, while graphic processor card (GPU) performs the drawing and resampling operations in an average of two to four seconds for 1-megapixel images that can be used in the field of opthalmology.
|Number of pages||4|
|Specialist publication||Laser Focus World|
|Publication status||Published - 1 May 2008|