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
Recovery of a hot-pluggable serial communication link
Controller for internal combustion engine
Non-intrusive processor tracing
Simulating non power of two texture behavior
Solar power system with communication network utilizing magnetic fields
Push-up bar
Image forming apparatus
  Randomly Featured Patents
Vibration touch button-type animal training device and method of controlling the same
Probe card
Hard disc drive for use in a multiple drive data storage system and method of operation
Variable sensitivity seat belt retractor
Valve control mechanism
Bicyclic prostaglandin analogs and method of synthesis
Data entry method and apparatus
Method for the manufacture of an optically readable disc, and discs obtained by this method
Semiconductor device with trench gate type transistor and method of manufacturing the same
Loading mechanism of disk player