An Approach to the Verilog-based System for Medical Image Enhancement

 

Image processing is best suited for FPGAs(field programmable gate array), because of its parallel architectures, the higher logic density and also the generous memory capacity. The FPGAs are capable of improving the performance of all the fast imaging algorithms like image construction and segmentation, enhancement and restoration, image analysis and pattern recognition, image and data compression, color space conversion, etc. several filters are developed at the hardware level for image processing such as edge detection, sharpening operation, to enhance contrast operation and to adjust the brightness in order to improve the quality of images and to help in verification of medical specialists. Using Hardware Description Languages(HDL) for image processing is a new approach extending the sector of digital design on reconfigurable circuits to digital image processing using VLSI technologies. Describing the image enhancement techniques using Verilog HDL enables rapid prototyping of those complex algorithms offering the direct possibility of FPGA implementation. Filtering principles of image enhancement techniques were analyzed mathematically and then reproduced into a source code written in Verilog Hardware Description Language(HDL). The filters were described at Register Transfer Level (RTL) using Verilog continuous assignments. The images were processed by switching the order of filters, using a single command and without the reconfiguration of the FPGA, in order to improve the original image.

Results:

The Verilog based system for image enhancement was simulated and verified using ISIM Simulator, tested on a medical image(dental radiography with 860x740 pixels, 8-bit image, size 621Kb)

The simulation was carried out under different conditions like changing filter parameters and changing the order of the filters, without reconfiguration of the FPGA: - enhance contrast operation, brightness-adjustment, sharpen operation and edges detection (Fig. a); - sharpen operation, edges detection, enhance contrast operation and brightness-adjustment (Fig. b); - enhance contrast operation, edges detection, sharpen operation and brightness-adjustment (Fig. c); - sharpen operation, brightness-adjustment, enhance contrast operation and edges detection (Fig. d).