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
Determination of statistical upper bound for estimate of noise power spectral density
Extract of Vanilla planifolia
Storage apparatus and method including page discard processing for primary and secondary volumes configured as a copy pair
System for thermally controlling displays
Nuclear fuel assembly bottom nozzle
Circuitry for measuring and compensating phase and amplitude differences in NDT/NDI operation
Processor and data transfer method
  Randomly Featured Patents
Failure warning for a vehicle information processing system
Method and apparatus for creating a non-uniform index structure for data
Utility knife
Bicycle rider hand attachment and cooperating gear shift actuator and associated methods
Antenna array in an RFID system
Timing signal generator
Metal alloy for medical devices and implants
Crystalline solids of carvedilol and processes for their preparation
Recording apparatus which allows ink amount detection upon exchange of a printhead
Waveguide-binding sensor for use with assays