Resources Contact Us Home
Method and apparatus for recognizing text in an image sequence of scene imagery

Image Number 8 for United States Patent #7620268.

An apparatus and a concomitant method for detecting and recognizing text information in a captured imagery. The present method transforms the image of the text to a normalized coordinate system before performing OCR, thereby yielding more robust recognition performance. The present invention also combines OCR results from multiple frames, in a manner that takes the best recognition results from each frame and forms a single result that can be more accurate than the results from any of the individual frames.

  Recently Added Patents
Frame syncrhonization in orthogonal frequency-division multiplexing systems
Method and device for operating a vehicle having a hybrid drive
Image pickup device with a plurality of pixels and an AD conversion circuit
Polymer bonded fibrous coating on dipped rubber articles skin contacting external surface
Display module
Plural component proportioner
Depth estimation apparatus and method
  Randomly Featured Patents
Light-sensitive material containing silver halide, reducing agent and polymerizable compound
Light projection system for automatic focus detection
Tailgate with integrated and extensible steps for a vehicle having a cargo bed
Controlled pressure butt welding process and apparatus for carrying it out
Alternator for a regenerative feed-back system
Concrete protection sheet with signalling and reflective layer
Low cost, low permeation multi-layer tubing
Therapeutic agents for renal diseases and organ preservatives
Flexible frame and tent
End arm manipulator