Name: Erik Smistad
Type: User
Company: Norwegian University of Science and Technology and SINTEF Digital
Bio: Research scientist working on medical image processing with focus on image segmentation, ultrasound images, deep learning and GPU processing
Twitter: ErikSmistad
Location: Trondheim, Norway
Blog: http://www.eriksmistad.no
Erik Smistad's Projects
An example of Gaussian blur using OpenCL and the built-in Images/textures
A small "getting started" tutorial for OpenCL. See http://www.eriksmistad.no/getting-started-with-opencl-and-gpu-computing/ for more info
An optimized OpenCL implementation of Gradient Vector Flow (GVF) that runs on GPUs and CPUs for both 2D and 3D. For more details about the implementation, see the scientific article Real-time gradient vector flow on GPUs using OpenCL http://www.springerlink.com/content/v0071r27706u5135/
Parallel/GPU level set volume segmentation using OpenCL
A small set of function based on the OpenCL C++ bindings to help set up an OpenCL and OpenCL-GL context as well as compiling OpenCL code
Automatically exported from code.google.com/p/opengles-book-samples
C library for reading virtual slide images
Testing Qt, OpenGL and OpenCL interoperability
Small test of a simple plugin system in C++ for Windows and Linux
The Simple Image Processing Library (SIPL) is a C++ library with the main goal of making it easy to go from an algorithm concept to pictures on the screen.
This is an example of how to use the Simple Image Processing Library (see www.github.com/smistad/SIPL/).
Tutorials and implementations for "Self-normalizing networks"
SWIG is a software development tool that connects programs written in C and C++ with a variety of high-level programming languages.
A test for creating python bindings of a C++ library using SWIG and CMake
Computation using data flow graphs for scalable machine learning
tensorflow implementation of 'YOLO : Real-Time Object Detection'(train and test)
A software for fast segmentation and centerline extraction of tubular structures (e.g. blood vessels and airways) from different modalities and organs using GPUs and OpenCL
Vascular Tree Synthesis Software. You will need CMake and ITK to run VascuSynth. Read the paper in the Insight Journal for instructions.
Some useful python functions for visualizing a caffe network
Simple method for converting the CellSens .vsi format to a pyramidal .tif