摘要:
An information processing device includes a learning image input unit configured to input a learning image, in which a tracked object is captured on different shooting conditions, together with the shooting conditions, a feature response calculation unit configured to calculate a response of one or more integrated features, with respect to the learning image while changing a parameter in accordance with the shooting conditions, a feature learning unit configured to recognize spatial distribution of the one or more integrated features in the learning image based on a calculation result of the response and evaluate a relationship between the shooting conditions and the parameter and a spatial relationship among the integrated features so as to learn a feature of the tracked object, and a feature storage unit configured to store a learning result of the feature.
摘要:
There is provided a gesture input device including an input unit to which at least one of image information and voice information representing a user's action is input, a detection unit that detects the user's action based on the input at least one of the image information and the voice information, a prediction unit that predicts one or more gestures that the user desires to input based on a detection result of the action, and a notification unit that notifies the user of an action to be performed next by the user in order to input the predicted one or more gestures.
摘要:
An information processing device includes a learning image input unit configured to input a learning image, in which a tracked object is captured on different shooting conditions, together with the shooting conditions, a feature response calculation unit configured to calculate a response of one or more integrated features, with respect to the learning image while changing a parameter in accordance with the shooting conditions, a feature learning unit configured to recognize spatial distribution of the one or more integrated features in the learning image based on a calculation result of the response and evaluate a relationship between the shooting conditions and the parameter and a spatial relationship among the integrated features so as to learn a feature of the tracked object, and a feature storage unit configured to store a learning result of the feature.
摘要:
A gesture input device includes an input unit to which image information representing an action is input. The gesture input device also includes a detection unit that detects the action based on a shape of the input image information. The gesture input device further includes a prediction unit that predicts one or more gestures based on a detection result of the action. In addition, the gesture input device includes a notification unit that notifies an action to be performed next to input the predicted one or more gestures.
摘要:
An image processing device includes a clothing extractor extracting a face or head portion from an input image, the face or head portion being a region estimated to be a face or head image, and extracting a clothing region from a region immediately below the face or head portion, the clothing region being a region estimated to be a clothing image, and a clothing converter changing clothing in the input image by performing predetermined image processing on an image in the clothing region in the input image.
摘要:
An image processing system includes a storing section that stores a database in which specific pose data representing each of specific poses of a human, and effect manipulation data specifying each of manipulations applied to an image are registered in association with each other, a human region detecting section that detects a human region that is a region where a human appears in an image on which to perform image processing, a human pose recognizing section that recognizes a pose of the human in the human region detected by the human region detecting section, a matching section that finds the specific pose data matching the pose recognized by the human pose recognizing section, by referencing the database, and a manipulating section that applies a manipulation to the image on the basis of the effect manipulation data associated with the specific pose data found by the matching section.
摘要:
An image processing device includes a clothing extractor extracting a face or head portion from an input image, the face or head portion being a region estimated to be a face or head image, and extracting a clothing region from a region immediately below the face or head portion, the clothing region being a region estimated to be a clothing image, and a clothing converter changing clothing in the input image by performing predetermined image processing on an image in the clothing region in the input image.
摘要:
A learning apparatus includes a feature extractor for extracting a feature at a feature point in a plurality of training images including training images that contains a target object to be recognized and that does not contain the target object, a tentative learner generator for generating a tentative learner for detecting the target object in an image, where the tentative learner is formed from a plurality of weak learners through statistical learning using the training images and the feature obtained from the training images, and a learner generator for generating a final learner that is formed from at least one of the weak learners and that detects the target object in an image by substituting the feature into a feature function formed from some of the weak learners of the tentative learner so as to obtain a new feature and performing statistical learning using the new feature and training images.
摘要:
An image processing apparatus includes a detector, a setting unit, and an image generator. The detector detects a target object image region from a first image. When one or more predetermined parameters are applicable to a target object within the region detected by the detector, the setting unit sets the relevant target object image region as a first region. The image generator then generates a second image by applying predetermined processing to either the image portion within the first region, or to the image portions in a second region containing image portions within the first image that are not contained in the first region.
摘要:
A learning apparatus includes a feature extractor for extracting a feature at a feature point in a plurality of training images including training images that contains a target object to be recognized and that does not contain the target object, a tentative learner generator for generating a tentative learner for detecting the target object in an image, where the tentative learner is formed from a plurality of weak learners through statistical learning using the training images and the feature obtained from the training images, and a learner generator for generating a final learner that is formed from at least one of the weak learners and that detects the target object in an image by substituting the feature into a feature function formed from some of the weak learners of the tentative learner so as to obtain a new feature and performing statistical learning using the new feature and training images.