Medical Image Processing Using Xilinx System Generator

Abstract

Although software implementations of different image processing techniques are suitable for general-purpose use, in order to meet the real time requirements, an image processing technique needs to be realized in hardware. Field Programmable Gate Arrays (FPGAs) have many benefits in applications that include digital signal acquisition, but also processing of large data, especially in real time. Mainly due to the ever-decreasing cost and re-configurability, FPGAs have also found its place in digital signal processing (DSP). Xilinx System Generator is a tool from Xilinx that enables the Mathworks Simulink models to be adapted for FPGA design. For comparative study on several levels in edge detection, CT image of a brain with a tumor is used. Performances of gradient based edge detectors - Robert, Prewitt and Sobel were compared. Even from just visual analysis of results, it can be seen that Prewitt and Sobel methods give better results than Robert method. In contrast, the calculation of Robert operator is simpler in comparison to the other operators and occupies less resources, since only adder-subtractor logic is sufficient to detect the edges. As the implemented algorithms could be part of more complex systems for tumor detection, the design architecture used in this paper can be extended to be used in very complex real time image processing techniques.