Abstract: 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.

Abstract: Provided is a learning device including: an acquisition section that acquires a plurality of image pairs in which the same subjects appear and a plurality of image pairs in which different subjects appear; a setting section that sets feature points on one image and the other image of each image pair; a selection section that selects a plurality of prescribed feature points, which are set at the same positions of the one image and the other image, so as to thereby select a feature extraction filter for each prescribed feature point; an extraction section that extracts the features of the prescribed feature points of each of the one image and the other image by using the plurality of feature extraction filters; a calculation section that calculates a correlation between the features; and a learning section that learns a same-subject classifier on the basis of the correlation and label information.

Abstract: An information processing device includes a first calculation unit which calculates a score of each sample image including a positive image in which an object as an identification object is present and a negative image in which the object as the identification object is not present, for each weak identifier of an identifier including a plurality of weak identifiers, a second calculation unit which calculates the number of scores when the negative image is processed, which are scores less than a minimum score among scores when the positive image is processed; and an realignment unit which realigns the weak identifiers in order from a weak identifier in which the number calculated by the second calculation unit is a maximum.

Abstract: 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.

Abstract: An image processing apparatus identifies tissues in respective parts of a tissue image. A tissue image subdivider subdivides a tissue image for identification into local regions. A detector detects texture feature values of the local regions. A determining unit compares the detected texture feature value of a local region to a learned feature value for identification associated with a predetermined tissue, and on the basis of the comparison result, determines whether or not the local region belongs to the predetermined tissue.

Abstract: An information processing apparatus, which creates a tree structure used by a recognition apparatus which recognizes specific information using the tree structure, including a memory unit which stores data including the information to be recognized and data not including the information so as to correspond to a label showing whether or not the data includes the information, a recognition device which recognizes the information and outputs a high score value when the data including the information is input, and a grouping unit which performs grouping of the recognition devices using a score distribution obtained when the data is input into the recognition devices.

Abstract: Systems and methods for implementing a superpixel boosted top-down image recognition framework are provided. The framework utilizes superpixels comprising contiguous pixel regions sharing similar characteristics. Feature extraction methods described herein provide non-redundant image feature vectors for classification model building. The provided framework differentiates a digitized image into a plurality of superpixels. The digitized image is characterized through image feature extraction methods based on the plurality of superpixels. Image classification models are generated from the extracted image features and ground truth labels and may then be used to classify other digitized images.

Abstract: 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.

Abstract: A data processing apparatus includes an obtaining unit for obtaining time-series data, an activity model learning unit for learning an activity model representing a user activity state as a stochastic state transition model from the obtained time-series data, a recognition unit for recognizing a current user activity state by using the learned activity model, and a prediction unit for predicting a user activity state after a predetermined time elapses from a current time from the recognized current user activity state, wherein the prediction unit predicts the user activity state as an occurrence probability, and calculates the occurrence probabilities of the respective states on the basis of the state transition probability of the stochastic state transition model to predict the user activity state, while it is presumed that observation probabilities of the respective states at the respective times of the stochastic state transition model are an equal probability.

Abstract: An integrated interactive segmentation with spatial constraint method utilizes a combination of several of the most popular online learning algorithms into one and implements a spatial constraint which defines a valid mask local to the user's given marks. Additionally, both supervised learning and statistical analysis are integrated, which are able to compensate each other. Once prediction and activation are obtained, pixel-wised multiplication is conducted to fully indicate how likely each pixel belongs to the foreground or background.

Abstract: A learning apparatus includes an image generator, a feature point extractor, a feature value calculator, and a classifier generator. The image generator generates, from an input image, images having differing scale coefficients. The feature point extractor extracts feature points from each image generated by the image generator. The feature value calculator calculates feature values for the feature points by filtering the feature points using a predetermined filter. The classifier generator generates one or more classifiers for detecting a predetermined target object from an image by means of statistical learning using the feature values.

Abstract: An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points; an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation.

Abstract: 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.

Abstract: An information processing apparatus includes a characteristic amount calculating unit calculating a characteristic amount for each of a plurality of n different image patterns, a specifying unit specifying a best-matching image pattern among the plurality of n image patterns for each of frames forming a learning moving picture and having temporal continuity, a computing unit computing a collocation probability Pij indicating a probability that, for a frame located at a position where a temporal distance to a frame for which a first image pattern Xi is specified among the plurality of n image patterns is within a predetermined threshold ?, a second image pattern Xj is specified among the plurality of n image patterns, and a grouping unit grouping the plurality of n image patterns by using the computed collocation probability Pij.

Abstract: The present invention provides an information processing apparatus including combination generating means for getting a first feature quantity of N dimensions, N being an integer of at least two, from first information prepared for execution of learning and use the first feature quantity of N dimensions to generate at least two of a first feature quantity combination that are not greater than N dimensions of the first feature quantity; and learning processing executing means for computing a correlation coefficient between the plurality of first feature quantity combinations generated by the combination generating means and a learning model feature quantity matching each dimension of the plurality of first feature quantity combinations and, by use of the first correlation coefficient, classify the first information, thereby executing learning processing for classifying predetermined second information.

Abstract: An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points; an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation.

Abstract: 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.

Abstract: Systems and methods for implementing a multi-label image recognition framework for classifying digital images are provided. The provided multi-label image recognition framework utilizes an iterative, multiple analysis path approach to model training and image classification tasks. A first iteration of the multi-label image recognition framework generates confidence maps for each label, which are shared by the multiple analysis paths to update the confidence maps in subsequent iterations. The provided multi-label image recognition framework permits model training and image classification tasks to be performed more accurately than conventional single-label image recognition frameworks.

Abstract: Systems and methods for implementing a multi-step image recognition framework for classifying digital images are provided. The provided multi-step image recognition framework utilizes a gradual approach to model training and image classification tasks requiring multi-dimensional ground truths. A first step of the multi-step image recognition framework differentiates a first image region from a remainder image region. Each subsequent step operates on a remainder image region from the previous step. The provided multi-step image recognition framework permits model training and image classification tasks to be performed more accurately and in a less resource intensive fashion than conventional single-step image recognition frameworks.

Abstract: Methods and systems disclosed herein provide the capability to automatically process digital pathology images quickly and accurately. According to one embodiment, an digital pathology image segmentation task may be divided into at least two parts. An image segmentation task may be carried out utilizing both bottom-up analysis to capture local definition of features and top-down analysis to use global information to eliminate false positives. In some embodiments, an image segmentation task is carried out using a “pseudo-bootstrapping” iterative technique to produce superior segmentation results. In some embodiments, the superior segmentation results produced by the pseudo-bootstrapping method are used as input in a second segmentation task that uses a combination of bottom-up and top-down analysis.