Image processing apparatus and image processing method

An image processing apparatus which is configured to execute processing by allocating a plurality of weak discriminators to form a tree structure having branches corresponding to types of objects so as to detect objects included in image data, wherein each weak discriminator comprises:

• a calculation unit configured to calculate a feature amount to be used in a calculation of an evaluation value of the image data;
• and
• a discrimination unit configured to discriminate whether or not the object is included in the image data based on the evaluation value,
• wherein the weak discriminator allocated to a branch point in the tree structure further comprises a selection unit configured to select a branch destination based on the accumulated evaluation values calculated by head weak discriminators of the weak discriminators included in the respective branch destinations.

An image processing apparatus which is configured to execute processing by allocating a plurality of weak discriminators to form a tree structure having branches corresponding to types of objects so as to detect objects included in image data, wherein each weak discriminator comprises:

• a calculation unit configured to calculate a feature amount to be used in a calculation of an evaluation value of the image data;
• and
• a discrimination unit configured to discriminate whether or not the object is included in the image data based on the evaluation value,
• wherein the weak discriminator allocated to a branch point in the tree structure further comprises a selection unit configured to select a branch destination in which the accumulated evaluation value calculated by executing a predetermined number of weak discriminators of the plurality of weak discriminators included in the respective branch destinations is largest.

An image processing apparatus which is configured to execute processing by allocating a plurality of weak discriminators to form a tree structure having branches corresponding to types of objects so as to detect objects included in image data, wherein each weak discriminator comprises:

• a calculation unit configured to calculate a feature amount;
• and
• a discrimination unit configured to discriminate whether or not the object is included in the image data based on the feature amount,
• wherein the weak discriminator allocated to a branch point in the tree structure further comprises a selection unit configured to select a branch destination based on the feature amount for a predetermined number of weak discriminators included in respective branch destinations.

An image processing method in an image processing apparatus which executes processing by allocating a plurality of weak discriminators to form a tree structure having branches corresponding to types of objects so as to detect objects included in image data, wherein each weak discriminator performs:

• a calculation step of calculating a feature amount to be used in a calculation of an evaluation value of the image data;
• and
• a discrimination step of discriminating whether or not the object is included in the image data based on the evaluation value,
• wherein the weak discriminator allocated to a branch point in the tree structure further performs a selection step of selecting a branch destination based on the accumulated evaluation values calculated by head weak discriminators of the weak discriminators included in the respective branch destinations.

An image processing method in an image processing apparatus which executes processing by allocating a plurality of weak discriminators to form a tree structure having branches corresponding to types of objects so as to detect objects included in image data, wherein each weak discriminator performs:

• a calculation step of calculating a feature amount to be used in a calculation of an evaluation value of the image data;
• and
• a discrimination step of discriminating whether or not the object is included in the image data based on the evaluation value,
• wherein the weak discriminator allocated to a branch point in the tree structure further performs a selection step of selecting a branch destination in which the accumulated evaluation value calculated by executing a predetermined number of weak discriminators of the plurality of weak discriminators included in the respective branch destinations is largest.

An image processing method in an image processing apparatus which executes processing by allocating a plurality of weak discriminators to form a tree structure having branches corresponding to types of objects so as to detect objects included in image data, wherein each weak discriminator performs:

• a calculation step of calculating a feature amount;
• and
• a discrimination step of discriminating whether or not the object is included in the image data based on the feature amount,
• wherein the weak discriminator allocated to a branch point in the tree structure further performs a selection step of selecting a branch destination based on the feature amount for predetermined number of weak discriminators included in respective branch destinations.

A non-transitory computer readable medium containing computer-executable instructions to be utilized in an image processing apparatus for executing processing by allocating a plurality of weak discriminators to form a tree structure having branches corresponding to types of objects so as to detect objects included in image data, wherein computer-executable instructions performed by each weak discriminator includes:

• computer-executable instructions for calculating a feature amount to be used in a calculation of an evaluation value of the image data;
• and
• computer-executable instructions for discriminating whether or not the object is included in the image data based on the evaluation value,
• wherein computer-executable instructions performed by the weak discriminator allocated to a branch point in the tree structure further includes computer-executable instructions for selecting a branch destination based on the accumulated evaluation values calculated by head weak discriminators of the weak discriminators included in the respective branch destinations.

A non-transitory computer readable medium containing computer-executable instructions to be utilized in an image processing apparatus for executing processing by allocating a plurality of weak discriminators to form a tree structure having branches corresponding to types of objects so as to detect objects included in image data, wherein computer-executable instructions performed by each weak discriminator includes:

• computer-executable instructions for calculating a feature amount to be used in a calculation of an evaluation value of the image data;
• and
• computer-executable instructions for discriminating whether or not the object is included in the image data based on the evaluation value,
• wherein computer-executable instructions performed by the weak discriminator allocated to a branch point in the tree structure further includes computer-executable instructions for selecting a branch destination in which the accumulated evaluation value calculated by executing a predetermined number of weak discriminators of weak discriminators included in the respective branch destinations is largest.

A non-transitory computer readable medium containing computer-executable instructions to be utilized in an image processing apparatus for executing processing by allocating a plurality of weak discriminators to form a tree structure having branches corresponding to types of objects so as to detect objects included in image data, wherein computer-executable instructions performed by each weak discriminator includes:

• computer-executable instructions for calculating a feature amount;
• and
• computer-executable instructions for discriminating whether or not the object is included in the image data based on the feature amount,
• wherein computer-executable instructions performed by the weak discriminator allocated to a branch point in the tree structure further includes computer-executable instructions for selecting a branch destination based on the feature amount for predetermined number of weak discriminators included in respective branch destinations.