OpenCL accelerated GPU binary morphology image filters for ITK

Binary morphological operations are fundamental tools in image processing but the processing time scales with the number of pixels thus making them expensive operations on the CPU for larger 3D datasets that typically appear in medical imaging. Since erosion and dilatation are special neighborhood operators, each pixel in the output depends only on the neighborhood region which makes them fit for massive GPU parallelization. This document introduces a new ITK module that implements generic (OpenCL based) GPU accelerated binary morphology image filters for erosion and dilatation. The filter can be executed within the standard ITKGPU pipeline.

Vein Image Segmentation Based on One-Dimentional Gray and Filter Erosion Method

For the low contrast and serious noises, a fast image segmentation method based on one-dimensional gray segmentation, binary morphology erosion and area elimination is proposed. Since veins are thin and long, the vein image can be easily distinguished from background by judging the gray difference from nearby pixels when they are vertically or horizontally scanned. Then the processed image is diposed with erosion and area elimination to filter the noise. According to test results on the hand vein images which got from the equipment constructed by ourselves, it is proved that the method is more suitable for hand vein image segmentation than others and clear vein images can be botained quickly.