FPGA Based Implementation of Edge and Corner Detection in MRI Brain Tumor Image

This work presents a flexible feature detectors for image with reduced area, power and memory requirements, supporting a variable input resolution. It focuses on processing an image pixel by pixel and in modification of pixel neighborhoods and the transformation that can be applied to the whole image or only a partial region and identify sudden changes in an image. The proposed work is optimized for feature detection, more specifically, the Canny edge detector and the Harris corner detector. The detector contains neighborhood extractors and threshold operators that can be parameterized at runtime. We implement the feature detection on segmentation of brain tissue in the magnetic resonance imaging for detecting the existence and outlines of tumors. Furthermore, we present the proposed architecture implementation on an FPGA-based platform the results show a clear advantage of the proposed architecture in terms of power consumption and maintain a reliable performance with noisy images. FPGAs are increasingly used in modern imaging applications, image filtering and medical imaging. Keywords—feature detectors, canny edge detector, Harris corner detector, FPGA, medical imaging