Abstract: According to one embodiment, a three-dimensional object determining apparatus includes: a detecting unit configured to detect a plurality of feature points of an object included in an image data that is acquired; a pattern normalizing unit configured to generate a normalized pattern that is normalized by a three-dimensional model from the image data using the plurality of feature points; an estimating unit configured to estimate an illumination direction in which light is emitted to the object in the image data from the three-dimensional model and the normalized pattern; and a determining unit configured to determine whether or not the object in the image data is a three-dimensional object on the basis of the illumination direction.

Abstract: According to an embodiment, a collation apparatus includes a receiving unit, a detecting unit, a setting unit, a face collation unit, an object collation unit, and a calculating unit. The receiving unit is configured to receive a captured image including a user's face and an object positioned with respect to the face. The detecting unit is configured to detect a face region from the image. The setting unit is configured to set an object region in the image. The face collation unit is configured to collate a face feature vector extracted from the face region with a stored face feature vector. The object collation unit is configured to collate an object feature vector extracted from the object region with a stored object feature vector. The calculating unit is configured to calculate a user collation using at least one of the collation results for the face and object feature vectors.

Abstract: According to an embodiment, a learning device includes a selecting unit, a learning unit, and an evaluating unit. The selecting unit performs a plurality of selection processes of selecting a plurality of groups including one or more learning samples from a learning sample storage unit, where respective learning samples are classified into any one of a plurality of categories. The learning unit learns a classification metric and obtains a set of a classification metric.

Abstract: According to an embodiment, a recognition device includes a generation unit to select, plural times, groups each including learning samples from a storage unit, learn a classification metric for classifying the groups selected in each selection, and generate an evaluation metric including the classification metrics; a transformation unit to transform a first feature value of an image including an object into a second feature value using the evaluation metric; a calculation unit to calculate similarities of the object to categories in a table using the second feature value and reference feature values; and a registration unit to register the second feature value as the reference feature value in the table associated with the category of the object and register the first feature value as the learning sample belonging to the category of the object in the storage unit. The generation unit performs the generation again.

Abstract: According to an embodiment, a learning apparatus includes a learning sample storage unit configured to store therein a plurality of learning samples that are classified into a plurality of categories; a selecting unit configured to perform, plural times, a selection process of selecting a plurality of groups each including one or more learning samples from the learning sample storage unit; and a learning unit configured to learn a classification metric for classifying the plurality of groups selected in each selection process and generate an evaluation metric including the learned classification metrics.

Abstract: According to one embodiment, a three-dimensional object determining apparatus includes: a detecting unit configured to detect a plurality of feature points of an object included in an image data that is acquired; a pattern normalizing unit configured to generate a normalized pattern that is normalized by a three-dimensional model from the image data using the plurality of feature points; an estimating unit configured to estimate an illumination direction in which light is emitted to the object in the image data from the three-dimensional model and the normalized pattern; and a determining unit configured to determine whether or not the object in the image data is a three-dimensional object on the basis of the illumination direction.

Abstract: An image input unit, a feature point detection unit configured to extract at least four image feature points including a feature point of a pupil and which do not exist on an identical plane from an input image, a three-dimensional face model storage unit configured to store shape information of a three-dimensional face model and at least coordinates of reference feature points on the three-dimensional face model corresponding to the feature points extracted by the feature point detection unit, a converting unit configured to convert a coordinate of the feature point of the pupil onto surface of the three-dimensional face model on the basis of the correspondence between the extracted feature points and the reference feature points, and a gaze estimating unit configured to estimate the gaze direction from the converted coordinate of the pupil are provided.

Abstract: An image processing apparatus includes an image input unit, a feature point extraction unit which extracts a plurality of feature points from an input image, a three-dimensional model storage unit which stores a three-dimensional model and reference feature point coordinates on the three-dimensional model, a target area setting unit which sets target areas from the three-dimensional model, a correspondence relationship calculation unit which, using the extracted feature points and reference feature points belonging to the target areas, estimates a correspondence relationship between the input image and the target areas, and a three-dimensional model integration unit which integrates target areas related to the image.

Abstract: An object is identified by detecting an object area image of an object to be recognized from a degraded image, converting the object area image to a frequency area, extracting a feature vector which indicates the amount of blur, comparing the feature vector and a classified plurality of blurred images, obtaining a cluster which is the most similar to the feature vector, selecting one point spread function corresponding to the similar cluster, restoring the object area image to the image before being blurred using the point spread function, and comparing the restored image and a target image.

Abstract: In an embodiment, a method for image recognition of an object having a three-dimensional shape, from a photographed image of the object, comprising: inputting the image; storing three-dimensional shape information as an origin of a three-dimensional model of the object; creating the three-dimensional model by using the input image and the three-dimensional shape information; creating plural pattern images in which the three-dimensional model is projected on a plane in different directions; extracting a feature quantity from the plural pattern images; holding a dictionary feature quantity of the object; and calculating a similarity degree between the extracted feature quantity and the dictionary feature quantity of the object to recognize the object based on the calculated similarity degree.

Abstract: A face feature point detecting device according to embodiments includes a unit inputting an image containing a face of a person, a unit detecting a feature point set candidate comprising plural kinds of feature points, and a unit calculating an error between each feature point of the projected feature point set candidate and each feature point of the feature point set including plural kinds of feature points of the three-dimensional model information; and a unit selecting a feature point set having consistency from the feature point set candidates on basis of the errors of the feature points or an integral value of the errors.

Abstract: An apparatus for detecting a feature point includes an image input unit that inputs an image of the target object; a three-dimensional shape information holding unit that stores three-dimensional shape information including reference feature points of a model relating to the target object; a correspondence relation acquiring unit that acquires a correspondence relation between the input image and the three-dimensional shape; a seek area acquiring unit that acquires image information of a seek area on the input image corresponding to an area including a point corresponding to the specific feature point in the model on the basis of the correspondence relation; and a feature point detecting unit that detects the position of the specific feature point in the input image from the image information.

Abstract: 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.

Abstract: An image processing apparatus includes an image input unit, a feature point extraction unit which extracts a plurality of feature points from an input image, a three-dimensional model storage unit which stores a three-dimensional model and reference feature point coordinates on the three-dimensional model, a target area setting unit which sets target areas from the three-dimensional model, a correspondence relationship calculation unit which, using the extracted feature points and reference feature points belonging to the target areas, estimates a correspondence relationship between the input image and the target areas, and a three-dimensional model integration unit which integrates target areas related to the image.

Abstract: The invention includes a reference oint setting unit configured to extract a plurality of reference points from an input image; a pattern extractor configured to extract a local pattern of the reference points; a characteristic set holder configured to hold a group of characteristic sets having both local patterns of the reference points extracted from a learned image and vectors from the reference points to characteristic points to be detected; a matching unit configured to compare the local patterns extracted from the reference points and the group of characteristic sets and select the nearest characteristic set as a characteristic set having the most similar pattern; and a characteristic point detector configured to detect a final position of the characteristic point based on a vector from the reference point to the characteristic point included in the selected nearest characteristic set.

Abstract: An object is identified by detecting an object area image of an object to be recognized from a degraded image, converting the object area image to a frequency area, extracting a feature vector which indicates the amount of blur, comparing the feature vector and a classified plurality of blurred images, obtaining a cluster which is the most similar to the feature vector, selecting one point spread function corresponding to the similar cluster, restoring the object area image to the image before being blurred using the point spread function, and comparing the restored image and a target image.

Abstract: A face image processing apparatus, includes: a face region detecting unit configured to detect a face feature point of a person from a plurality of images picked up by a plurality of imaging units respectively, to detect a face region; a face feature extracting unit configured to extract a face feature from an image of the face region detected by the face region detecting unit; a person recognizing unit configured to calculate a similarity measure based on a face feature of a specific person being previously registered and the face feature extracted by the face feature extracting unit to recognize the person; and an output apparatus which outputs a recognition result in the person recognizing unit.

Abstract: An image input unit, a feature point detection unit configured to extract at least four image feature points including a feature point of a pupil and which do not exist on an identical plane from an input image, a three-dimensional face model storage unit configured to store shape information of a three-dimensional face model and at least coordinates of reference feature points on the three-dimensional face model corresponding to the feature points extracted by the feature point detection unit, a converting unit configured to convert a coordinate of the feature point of the pupil onto surface of the three-dimensional face model on the basis of the correspondence between the extracted feature points and the reference feature points, and a gaze estimating unit configured to estimate the gaze direction from the converted coordinate of the pupil are provided.

Abstract: A face image processing apparatus, includes: a face region detecting unit configured to detect a face feature point of a person from a plurality of images picked up by a plurality of imaging units respectively, to detect a face region; a face feature extracting unit configured to extract a face feature from an image of the face region detected by the face region detecting unit; a person recognizing unit configured to calculate a similarity measure based on a face feature of a specific person being previously registered and the face feature extracted by the face feature extracting unit to recognize the person; and an output apparatus which outputs a recognition result in the person recognizing unit.

Abstract: A face image processing apparatus, includes: a face region detecting unit configured to detect a face feature point of a person from a plurality of images picked up by a plurality of imaging units respectively, to detect a face region; a face feature extracting unit configured to extract a face feature from an image of the face region detected by the face region detecting unit; a person recognizing unit configured to calculate a similarity measure based on a face feature of a specific person being previously registered and the face feature extracted by the face feature extracting unit to recognize the person; and an output apparatus which outputs a recognition result in the person recognizing unit.