摘要:
According to an embodiment, a command issuing apparatus includes an acquiring unit configured to acquire an image obtained by capturing a subject; a detector configured to detect a specific region of the subject from the image; a first setting unit configured to set a specific position indicating a position of the specific region; a second setting unit configured to set a reference position indicating a position that is to be a reference in the image; a first calculator configured to calculate a position vector directing toward the specific position from the reference position; a second calculator configured to calculate, for each of a plurality of command vectors respectively corresponding to predetermined commands, a first parameter indicating a degree of coincidence between the command vector and the position vector; and an issuing unit configured to issue the command based on the first parameter.
摘要:
According to one embodiment, an image processing apparatus includes an image-capturing module configured to captures an image, a module configured to detect a first object region from the image, a module configured to extract color information of an image of the first object region, a module configured to detect candidates of a second object region, which is an object of recognition, from the image, a module configured to extract color information of an image of the second object region, and sets reference color data, a module configured to select the candidates of the second object region on the basis of the reference color data and the color information of the image of the first object region with respect to each of the candidates of the second object region, and a module configured to output, as an object of recognition, any one of the candidates of the second object region.
摘要:
According to one embodiment, a time series information acquisition unit acquires time series information of a position or a size of a specific part of a user's body. An operation segment detection unit detects a movement direction of the specific part from the time series information, and detects a plurality of operation segments each segmented by two of a start point, a turning point and an end point of the movement direction. A recognition unit specifies a first operation segment to be recognized and a second operation segment following the first operation segment among the plurality of operation segments, and recognizes a motion of the specific part in the first operation segment by using a first feature extracted from the time series information of the first operation segment and a second feature extracted from the time series information of the second operation segment.
摘要:
According to one embodiment, an information search apparatus includes a generation unit, a selection unit, a search unit and a display unit. The generation unit generates recognition candidate character strings based on shapes of strokes and combinations of the shapes. The selection unit calculates reliability values for the recognition candidate character strings and selects search keys from the recognition candidate character strings. The search unit searches a database for second character strings including the search keys, and obtains one or more result character strings indicating search results of each of the search keys. The display displays the one or more result character strings corresponding to each of the search keys distinctively.
摘要:
An apparatus for a user to interface with a control object apparatus by a posture or a motion of the user's physical part. An image input unit inputs an image including the user's physical part. A gesture recognition unit recognizes the posture or the motion of the user's physical part from the image. A control unit controls the control object apparatus based on an indication corresponding to the posture or the motion. A gesture information display unit displays an exemplary image of the posture or the motion recognized for the user's reference to indicate the control object apparatus.
摘要:
An image processing apparatus includes a classification unit configured to extract N features from an input image using pre-generated N feature extraction units and calculate confidence value which represents object-likelihood based on the extracted N features, an object detection unit configured to detect an object included in the input image based on the confidence value, a feature selection unit configured to select M feature extraction units from the N feature extraction units such that separability between the confidence value of the object and that of background thereof becomes greater than a case where the N feature extraction units are used, the M being a positive integer smaller than N, and an object tracking unit configured to extract M features from the input image and tracks the object using the M features selected by the feature selection unit.
摘要:
According to one embodiment, an information search apparatus includes a generation unit, a selection unit, a search unit and a display unit. The generation unit generates recognition candidate character strings based on shapes of strokes and combinations of the shapes. The selection unit calculates reliability values for the recognition candidate character strings and selects search keys from the recognition candidate character strings. The search unit searches a database for second character strings including the search keys, and obtains one or more result character strings indicating search results of each of the search keys. The display displays the one or more result character strings corresponding to each of the search keys distinctively.
摘要:
In order to detect a specific detection object from an input image, a color serving as a reference is calculated in a reference image region. The difference for each color component between each pixel in the detection window and the reference color is calculated. Whether or not the detection object is included in the detection window is discriminated by a feature vector indicating how the difference is distributed in the detection window.
摘要:
A gesture recognition apparatus including a detector, a controller and a gesture recognizer, and is able to detect a portion to be detected using an image captured at a first resolution without reducing the number of images to be entered per unit of time to an object detector by detecting an auxiliary portion instead when the portion to be detected is not detected at a second resolution, estimating the position of the auxiliary portion based on the position of the auxiliary portion, and extracting the periphery thereof from the image captured at the first resolution.
摘要:
An apparatus for a user to interface with a control object apparatus by a posture or a motion of the user's physical part. An image input unit inputs an image including the user's physical part. A gesture recognition unit recognizes the posture or the motion of the user's physical part from the image. A control unit controls the control object apparatus based on an indication corresponding to the posture or the motion. A gesture information display unit displays an exemplary image of the posture or the motion recognized for the user's reference to indicate the control object apparatus.