Resources Contact Us Home
Image classifier utilizing class distribution maps for character recognition

Image Number 6 for United States Patent #5825925.

An image classifier, which performs character recognition, receives input images and assigns each input image to one of a plurality of image classes. The image classifier includes plural class distribution maps, each based on a plurality of features evaluated on training images, and each representing those feature values that occur at least once among the training images belonging to the corresponding class. The image classifier further includes means for constructing a test map by evaluating the plurality of features on the input image. The image classifier further includes means for comparing the test map to the class distribution maps in order to identify which one of the class distribution maps has the least distance to the test map. At least one of the features is defined according to a rule that relates to the shapes of images of at least one image class.

  Recently Added Patents
Method for implementing dynamic pseudorandom keyboard remapping
Vehicle exterior
Systems and methods for selective text to speech synthesis
Hand-held electronic display device
Method and system for distributing ringback files
Efficient location discovery
Instantaneous single click perpetual date mechanism
  Randomly Featured Patents
Encapsulation methods for organic electrical devices
Scalable and extensible secure rendering of digital content
Butterfly valve
Unpowered twisted pair loopback circuit for differential mode signaling
Alkoxy anilides and pharmaceutical compositions
Backrest adjusting mechanism used in high chair for infants, toddlers, and small children
Casting tire including continuous circumferential sidewall indentations
Pickup unit for a stringed musical instrument
Acceleration-insensitive hydrophone
Laser oscillator control method for changing a currently executing command program