Abstract: A method for information processing includes a learning process to generate a tree structured dictionary based on a plurality of patterns including a target object to be recognized. The method includes selecting a plurality of points from an input pattern based on a distribution of a probability that the target object to be recognized is present in the input pattern at each node of a tree structure generated in the learning process, and classifying the input pattern into a branch based on a value of a predetermined function that corresponds to values of the input pattern at selected plurality of points.

Abstract: An image recognition apparatus is provided which comprises a first extracting means for extracting, from every registration image previously registered, a set of registration partial images of a predetermined size, and a second extracting means for extracting, from an input new image, a set of new partial images of a predetermined size. The apparatus further comprises a discriminating means for discriminating an attribute of the new partial image based on a rule formed by dividing the set of the registration partial images extracted by the first extracting means, and a collecting means for deriving a final recognition result of the new image by collecting discrimination results by the discriminating means at the time when the new partial images as elements of the set of the new partial images are input.

Abstract: A galvano device that rotates a mirror provided at a motor shaft by rotating a motor and changes a direction of light by allowing the mirror to reflect the light includes a sensor configured to detect a rotation angle of a motor rotating shaft and a filter configured to estimate a rotation angle of the mirror from a value output from the sensor. The rotation angle of the mirror is output from the filter.

Abstract: An information processing apparatus having a changed region detection unit performs a process that includes repeating a cycle. The cycle includes causing a projection unit to project a pattern, that includes light and dark portions, onto target objects, causing an image capturing unit to capture an image of the target objects while the pattern is being projected by the projection unit, and causing a holding unit to hold one of the target objects based on a captured image obtained by the image capturing processing. Based on a reference boundary position corresponding to a boundary between the light and dark portions in the pattern in the captured image obtained in a previous cycle and a target boundary position in the captured image obtained in a current cycle, the changed region detection unit detects a changed region with a change between the previous cycle and the current cycle.

Abstract: An information processing apparatus acquires an image of multiple objects, acquires positions and orientations of the objects based on the image, and decides the holding order of the objects based on the positions and orientations and a direction that is set.

Abstract: An information processing device performs a contour extraction of an object based on an image information which is obtained by imaging the object and in which each pixel has information regarding a distance from a reference position and includes a processor configured to perform a contour extraction process on the image information. The processor performs the contour extraction process on one pixel of the image information based on a difference equal to or greater than a threshold among differences between the distance corresponding to the one pixel and the distances corresponding to a plurality of peripheral pixels in periphery of the one pixel.

Abstract: An image recognition apparatus is provided which comprises a first extracting means for extracting, from every registration image previously registered, a set of registration partial images of a predetermined size, and a second extracting means for extracting, from an input new image, a set of new partial images of a predetermined size. The apparatus further comprises a discriminating means for discriminating an attribute of the new partial image based on a rule formed by dividing the set of the registration partial images extracted by the first extracting means, and a collecting means for deriving a final recognition result of the new image by collecting discrimination results by the discriminating means at the time when the new partial images as elements of the set of the new partial images are input.

Abstract: An image recognition apparatus is provided which comprises a first extracting means for extracting, from every registration image previously registered, a set of registration partial images of a predetermined size, and a second extracting means for extracting, from an input new image, a set of new partial images of a predetermined size. The apparatus further comprises a discriminating means for discriminating an attribute of the new partial image based on a rule formed by dividing the set of the registration partial images extracted by the first extracting means, and a collecting means for deriving a final recognition result of the new image by collecting discrimination results by the discriminating means at the time when the new partial images as elements of the set of the new partial images are input.

Abstract: An information processing apparatus comprises: a registration unit adapted to register information required to determine at least one specific pattern in an image; an input unit adapted to input image data; a first generation unit adapted to extract a predetermined feature distribution from the input image data, and to generate a first feature distribution map indicating the feature distribution; a second generation unit adapted to generate a second feature distribution map by applying a conversion required to relax localities of the first feature distribution map to the first feature distribution map; and a determination unit adapted to determine, using sampling data on the second feature distribution map and the registered information, which of the specific patterns the image data matches.

Abstract: An information processing apparatus acquires an image of multiple objects, acquires positions and orientations of the objects based on the image, and decides the holding order of the objects based on the positions and orientations and a direction that is set.

Abstract: An information processing apparatus, for training a classifier that classifies local regions of an object, includes a feature amount setting unit, a selection unit, and a training unit. The feature amount setting unit sets a feature amount to be used by the classifier. The selection unit selects a local region of the object based on a predetermined selection condition based on positions for obtaining the feature amount set by the feature amount setting unit. The training unit trains the classifier using the feature amount set by the feature amount setting unit and the local region selected by the selection unit.

Abstract: An information processing apparatus having a changed region detection unit performs a process that includes repeating a cycle. The cycle includes causing a projection unit to project a pattern, that includes light and dark portions, onto target objects, causing an image capturing unit to capture an image of the target objects while the pattern is being projected by the projection unit, and causing a holding unit to hold one of the target objects based on a captured image obtained by the image capturing processing. Based on a reference boundary position corresponding to a boundary between the light and dark portions in the pattern in the captured image obtained in a previous cycle and a target boundary position in the captured image obtained in a current cycle, the changed region detection unit detects a changed region with a change between the previous cycle and the current cycle.

Abstract: A multi view-point image composed of a great number of images according to a shape of an object is generated or an information processing method used for generating a three-dimensional model or performing image processing of arbitrary view-point object recognition is provided, and based on a plurality of captured images obtained by imaging of the object from a plurality of view points by an imaging means, a relative position and orientation with respect to the object relative to the imaging means for each of the plurality of view points is calculated, and based on the calculated plurality of relative positions and orientations, a missing position and orientation of the imaging means in a direction in which imaging by the imaging means is missing is calculated, and an image used for displaying the calculated missing position and orientation on a display means is generated.

Abstract: An information processing apparatus comprises: a registration unit adapted to register information required to determine at least one specific pattern in an image; an input unit adapted to input image data; a first generation unit adapted to extract a predetermined feature distribution from the input image data, and to generate a first feature distribution map indicating the feature distribution; a second generation unit adapted to generate a second feature distribution map by applying a conversion required to relax localities of the first feature distribution map to the first feature distribution map; and a determination unit adapted to determine, using sampling data on the second feature distribution map and the registered information, which of the specific patterns the image data matches.

Abstract: An information processing apparatus comprises: a registration unit adapted to register information required to determine at least one specific pattern in an image; an input unit adapted to input image data; a first generation unit adapted to extract a predetermined feature distribution from the input image data, and to generate a first feature distribution map indicating the feature distribution; a second generation unit adapted to generate a second feature distribution map by applying a conversion required to relax localities of the first feature distribution map to the first feature distribution map; and a determination unit adapted to determine, using sampling data on the second feature distribution map and the registered information, which of the specific patterns the image data matches.

Abstract: A method for information processing includes a learning process to generate a tree structured dictionary based on a plurality of patterns including a target object to be recognized. The method includes selecting a plurality of points from an input pattern based on a distribution of a probability that the target object to be recognized is present in the input pattern at each node of a tree structure generated in the learning process, and classifying the input pattern into a branch based on a value of a predetermined function that corresponds to values of the input pattern at selected plurality of points.

Abstract: Luminance information of an object and information representing a three-dimensional shape of the object are acquired from an image of the object. Normal line information on a surface of the object is estimated from the information representing the three-dimensional shape, and the normal line information represents a normal direction of the surface of the object. A reflection characteristic of the object is estimated based on a correspondence between the luminance information and normal directions represented by the normal line information. It is evaluated whether a distribution of the normal directions represented by the normal line information is sufficient for estimation of the reflection characteristic.

Abstract: An information processing method includes detecting a partial area configuring a target object from an input image, evaluating appropriateness of the detection result, voting with respect to the target object based on the detection result and the evaluation result, and identifying an attribute of the target object based on the voting result.

Abstract: A method for information processing includes a learning process to generate a tree structured dictionary based on a plurality of patterns including a target object to be recognized. The method includes selecting a plurality of points from an input pattern based on a distribution of a probability that the target object to be recognized is present in the input pattern at each node of a tree structure generated in the learning process, and classifying the input pattern into a branch based on a value of a predetermined function that corresponds to values of the input pattern at selected plurality of points.

Abstract: An information processing apparatus for estimating a position and orientation of a target object in a three-dimensional space, inputs a plurality of captured images obtained by imaging the target object from a plurality of viewpoints, clips, for each of the input captured images, a partial image corresponding to a region occupied by a predetermined partial space in the three-dimensional space, from the captured image, extracts, from a plurality of partial images clipped from the plurality of captured images, feature information indicating a feature of the plurality of partial images, stores dictionary information indicating a position and orientation of an object in association with feature information of the object corresponding to the position and orientation, and estimates the position and orientation of the target object by comparing the feature information of the extracted target object and the feature information indicated in the dictionary information.