System and method for multi-view face detection

A system for detecting an object in an input image, the system comprising:

• a general purpose computing device;
• and
• a computer program comprising program modules executable by the computing device, wherein the computing device is directed by the program modules of the computer program to
• create a database comprising a plurality of training feature characterizations, each of which characterizes an object being sought at a known orientation or a an object not being sought;
• train a plurality of detectors arranged in a pyramidal architecture to determine whether a portion of an input image depicts an object being sought having an orientation within an orientation associated with one of the detectors using the training feature characterizations;
• and wherein
• said detectors using a greater number of feature characterizations are arranged at the bottom of the pyramid, and wherein
• said detectors arranged to detect finer ranges of object orientation are arranged at the bottom of the pyramid;
• input a portion of an input image into the plurality of detectors arranged in a pyramid architecture;
• and
• interpret the output of the plurality of detectors to determine whether the portion of the input image contains an object being sought and if so to identify the orientation associated with each detected object being sought.

A computer-readable medium having computer-executable instructions for detecting a person's face in an input image, said computer executable instructions comprising:

• creating a database comprising a plurality of training feature characterizations, each of which characterizes the face of a person at a known face pose or a non-face;
• training a plurality of detectors arranged in a pyramidal architecture to determine whether a portion of an input image depicts a person's face having a face pose falling within a face pose range associated with one of the detectors using the training feature characterizations, said plurality of detectors when trained being capable of determining whether a portion of an input image depicts a person's face;
• and wherein
• said detectors using a greater number of feature characterizations are arranged at the bottom of the pyramid, and wherein
• said detectors arranged to detect finer ranges of face pose are arranged at the bottom of the pyramid.

A face detection system for detecting a person's face depicted in an input image and identifying a face pose range, among a set of pose ranges, into which the pose associated with the detected face falls, comprising:

• a database comprising a plurality of training feature characterizations, each of which characterizes the face of a person at a known face pose or a non-face;
• a plurality of detectors arranged in a pyramidal architecture to determine whether a portion of an input image depicts a person's face having a face pose falling within a face pose range associated with one of the detectors using said training feature characterizations;
• and wherein
• said detectors using a greater number of feature characterizations are arranged at the bottom of the pyramid, and wherein
• said detectors arranged to detect finer ranges of face pose are arranged at the bottom of the pyramid.