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
Device and method for the intermittent impregnation and output of drinking water
Process for producing agglomerates of finely particulate iron carriers
Pressure-regulating valve and liquid droplet ejection apparatus
Angle-resolved spectroscopic instrument
Substrate processing method and substrate processing apparatus for performing a deposition process and calculating a termination time of the deposition process
Pipelined serial ring bus
  Randomly Featured Patents
System and method for producing notification based web services
Dental composition and process for producing dental polymeric shaped articles
Gaming system, gaming device and method for displaying multiple concurrent games using dynamic focal points
Seamless and firm joining of the end and/or lateral areas of photosensitive layers
Diene rubber composition
Client peripheral device-based network resource management method and system
Power saving circuit having a keeper stage to hold a signal line in a weakly held state
Combination beach mat and shoulder bag