Real-time Parallelized Hybrid Median Filter for speckle removal in ultrasound images

Abstract

Medical Imaging has historically been very successful to expose the patient's anatomy beyond external visibility; thus, allowing more efficient and accurate treatments. The field of medicine continues to search for new techniques in order to increase accuracy, reduce complications, enable real-time feedback, allow early detection and reduce human errors. Various medical imaging techniques exist but suffer from multiple correlated noise or performance that hinders real-time application; ie, ultrasounds. Our contribution attempts to solve both of these problems efficiently to be enable real-time procedures Our work is based on the hybrid median filter. We implemented Parallelized Hybrid Median Filter on FPGA Virtex6 in order to be able to exploit parallelism and real-time capabilities. We were able to get the desirable visual results for experts at 382MHz frequency with 150µs completion time for full 512x512 ultrasound image to complete despeckle.

Number Plate Recognition (ANR) using Crimmins Complementary Hulling Algorithm

“…To remove the salt and paper noise effect from the image I applied the crimmins complementary hulling algorithm [1], but in order to get the good result the iteration has to increase which leads the performance degradation but for practical purpose these algorithm removes the salt and paper noise optimally.…”

“…This algorithm provides the better result than median filter [1]. It reduces the intensity of salt and paper noise from the image.…”