Resources Contact Us Home
Accelerated image registration by means of parallel processors

Image Number 3 for United States Patent #8023732.

A method is provided for accelerating non-rigid image registration, using parallel processors. To that end, on a commercially available graphics card, a block-matching algorithm is implemented, which, by histogram-based similarity standards, calculates the motion vectors for individual blocks. All the blocks are processed simultaneously and individually. The complete motion vector field is obtained by bilinear interpolation. Optimized search methods, such as conjugate direction searching, are employed. The algorithm terminates once the optimal displacement has been found for all the blocks. The registration is done completely on the graphics card. The algorithm is fully automatic, precise, and fast. The program may be employed for instance in registration for digital subtraction angiography.

  Recently Added Patents
Minimizing mismatch during compensation
Pet cremation urn
LED string with a capability to maintain a current path and LED unit thereof
Multi-domain dynamic group virtual private networks
Method for designing sunlight-reflection and heat-radiation multilayer film
Closed cell culture system
Modular sport center
  Randomly Featured Patents
Method, system and apparatus for efficiently generating binary numbers for testing storage devices
Translucent polycarbonate composition, method for preparation thereof, and articles derived therefrom
Monitoring apparatus for training devices
Multistage compression type rotary compressor
Method and container for hot isostatic compacting
Video game machine, machine readable storage medium storing a computer program, and event selection method in the video game machine
Providing compartmentalized security in product reviews
Chemically modified oligonucleotides
Method of stabilizing fluorine-containing polymer