THE IMAGE STITCHING PERFORMANCE AND QUALITY IMPROVE TECHNIQUES FOR MINIMALLY INVASIVE SURGERY

Abstract

Minimally Invasive Surgery (MIS) is a surgical technique of the present and the future. However, there are two major challenges in the MIS technique: the quality of the stitched image and the speed of the image stitching. Because MIS has very high requirements on the precision of tissue surgery and the time taken by the surgeon. Therefore, this paper proposes a method to improve the quality of the stitched image and speed of the image stitching to provide the surgeon with a good image of the surgical area in the best time. The proposed method is: reduce the time spent to detecting feature points in the small image by using OpenCL and improve the quality of the stiched image by finding the best hemography matrix. Research results show that the time spent to detecting feature points is reduced by seven times compared to the current method, so the stitched speeding will be faster. Moreover, the number of detected feature points is 3 times higher compared to the current method , so the quality of the stitched image is better. This proposed method give promises to improve existing limitations in laparoscopic surgery.