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: 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: A face feature point detecting device includes a unit for inputting an image containing a face of a person, a unit for detecting a feature point set candidate comprising plural kinds of feature points, a unit for calculating the corresponding error between the detected feature point set and the corresponding feature point set on the three-dimensional model of the face, and a unit for judging the consistency of the arrangement of the detected feature point set candidate.

Abstract: An image recognition method or apparatus, the method comprising: inputting an image containing an object to be recognized; creating an input subspace from the inputted image; storing a model subspace to represent three-dimensional object models respectively for different environments; projectively transforming the input subspace in a manner to suppress an element common between the input subspace and the model subspace and thereby suppress influence due to environmental variation, into an environment-suppressing subspace; storing dictionary subspaces relating to registered objects; calculating a similarity between the environment-suppressing subspace and the dictionary subspace; and identifying the object to be recognized as one of the registered objects corresponding to the dictionary subspace having similarity exceeding a threshold.

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 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.