Abstract: According to one embodiment, a method includes acquiring ID information read from a medium at a passage zone, identifying a passerby facial image and an accompanier facial image from a captured image of the passage zone, wherein a facial image area of a first user carrying the medium is identified as one of the passerby facial image and the accompanier facial image, and a facial image area of a second user accompanying the first user is identified as the other one of the passerby facial image and the accompanier facial image, and authenticating the first and second users as passage permitted persons if at least one of the passerby facial image and the accompanier facial image matches a correct facial image corresponding to the ID information.

Abstract: According to an embodiment, a display control apparatus includes a clustering unit, a sub-clustering unit, and a display control unit. The clustering unit is configured to classify images into a plurality of clusters based on similarity degrees of the images and a first threshold. The sub-clustering unit is configured to further classify images within each of the plurality of clusters into a plurality of sub-clusters based on the similarity degrees and a second threshold that is higher than the first threshold. The display control unit is configured to display, on a display unit, display information including a cluster representative indicative of a representative of images included in a cluster and a sub-cluster representative indicative of a representative of an image included in a sub-cluster.

Abstract: In a passage management computer program product, acquiring processing of identification information acquires identification information of a user read by a reading unit that is installed in a passage area and that reads the identification information from an authentication medium. Acquiring processing of photographed image acquires a photographed image of the passage area. Among one or more face image regions in the photographed image, specifying processing specifies a face image region of a user who is carrying the authentication medium as a passerby face image. When the passerby face image matches with a pre-stored face image corresponding to the identification information, authenticating processing authenticates the user who is carrying the authentication medium as an authorized person, and when the passerby face image does not match with the pre-stored face image, authenticates the user who is carrying the authentication medium as an unauthorized person.

Abstract: According to one embodiment, an image processing apparatus 1 includes one or more hardware processors configured to function as an acquisition unit 20A, a pseudo label estimation unit 20B, and a learning unit 20C. The acquisition unit 20A acquires unlabeled training data including an image to which a correct label of an attribute is unassigned. The pseudo-label estimation unit 20B estimates a pseudo-label, which is an estimation result of the attribute of the image of the unlabeled training data, based on an identification target region according to a type of the attribute to be identified by a first learning model 30 to be learned in the image of the unlabeled training data. The learning unit 20C learns the first learning model 30 identifying the attribute of the image by using first labeled training data with the pseudo-label being assigned to the image of the unlabeled training data.

Abstract: According to one embodiment, an apparatus includes a first acquisition unit, a second acquisition unit, an identification unit, and an output unit. The first acquisition unit acquires a query image and a query text relating to a target object. The second acquisition unit acquires candidate images of the target object. The identification unit identifies from the candidate images a positive image containing a region demonstrating a similarity to the query image higher than or equal to a first threshold value, and identifies a position of the region in the positive image. The output unit outputs training data including the positive image, information representing the position of the region, and a correct label.

Abstract: According to one embodiment, an apparatus includes a first acquisition unit, a second acquisition unit, an identification unit, and an output unit. The first acquisition unit acquires a query image and a query text relating to a target object. The second acquisition unit acquires candidate images of the target object. The identification unit identifies from the candidate images a positive image containing a region demonstrating a similarity to the query image higher than or equal to a first threshold value, and identifies a position of the region in the positive image. The output unit outputs training data including the positive image, information representing the position of the region, and a correct label.

Abstract: According to an embodiment, a display control apparatus includes a clustering unit, a sub-clustering unit, and a display control unit. The clustering unit is configured to classify images into a plurality of clusters based on similarity degrees of the images and a first threshold. The sub-clustering unit is configured to further classify images within each of the plurality of clusters into a plurality of sub-clusters based on the similarity degrees and a second threshold that is higher than the first threshold. The display control unit is configured to display, on a display unit, display information including a cluster representative indicative of a representative of images included in a cluster and a sub-cluster representative indicative of a representative of an image included in a sub-cluster.

Abstract: According to one embodiment, a monitoring system includes a monitoring terminal and a server. The monitoring terminal includes a detector, a tracking unit, a first selector, and a transmitter. The server includes a receiver, a second selector, a collation unit, and an output unit. The receiver receives a first best shot images from the monitoring terminal. The second selector performs second selection processing, as part of a predetermined selection processing other than a first selection processing, of selecting a second best shot image suitable for collation with a predetermined image from among the first best shot images. The collation unit performs collation processing of collating the second best shot image with the predetermined image. The output unit outputs a result of the collation processing.

Abstract: An image collation system comprising: a detection unit that detects an object from an image acquired by imaging a predetermined position using an imaging unit; a tracking unit that tracks an object image of the same object; a selection unit that calculates an evaluated value for each of the object images of the same object and selects the object image of which the evaluated value is equal to or greater than a predetermined value as a best shot image; a collation unit that performs a collation process of collating the best shot image with a registered image and determining whether the object present at the predetermined position is a previously registered object; and a display that displays a performance result of the collation process, the image collation system including a storage unit that stores the best shot image; and a preparation unit that updates or re-prepares an evaluation expression that calculates the evaluated value.

Abstract: According to an embodiment, a people search system includes a receiver, a detector, a search unit, and a display. The search unit obtains features of a first face image and a second face image of a predetermined person and searches for the predetermined person based on a similarity between the features of the first and the second face images when an inhibiting factor is not detected, and generates a third face image that is a composite image of the second face image and the inhibiting factor, obtains features of the first and the third face images, and searches for the predetermined person based on a similarity between the features of the first and the third face images when the inhibiting factor is detected. The display displays the search result of the predetermined person obtained by the search unit.

Abstract: According to one embodiment, a monitoring system includes a monitoring terminal and a server. The monitoring terminal includes a detector, a tracking unit, a first selector, and a transmitter. The server includes a receiver, a second selector, a collation unit, and an output unit. The receiver receives a first best shot images from the monitoring terminal. The second selector performs second selection processing, as part of a predetermined selection processing other than a first selection processing, of selecting a second best shot image suitable for collation with a predetermined image from among the first best shot images. The collation unit performs collation processing of collating the second best shot image with the predetermined image. The output unit outputs a result of the collation processing.

Abstract: A moving object tracking system includes an input unit, a detection unit, a creating unit, a weight calculating unit, a calculating unit, and an output unit. The detection unit detects all tracking target moving objects from each of input images input. The creating unit creates a combination of a path that links each moving object detected in a first image to each moving object detected in a second image, a path that links each moving object detected in the first image to an unsuccessful detection in the second image, and a path that links an unsuccessful detection in the first image to each moving object detected in the second image. The calculating unit calculates a value for the combination of the paths to which weights are allocated. The output unit outputs a tracking result.

Abstract: An image collation system comprising: a detection unit that detects an object from an image acquired by imaging a predetermined position using an imaging unit; a tracking unit that tracks an object image of the same object; a selection unit that calculates an evaluated value for each of the object images of the same object and selects the object image of which the evaluated value is equal to or greater than a predetermined value as a best shot image; a collation unit that performs a collation process of collating the best shot image with a registered image and determining whether the object present at the predetermined position is a previously registered object; and a display that displays a performance result of the collation process, the image collation system including a storage unit that stores the best shot image; and a preparation unit that updates or re-prepares an evaluation expression that calculates the evaluated value.

Abstract: According to one embodiment, an identity authentication system includes a detecting unit that detects an identity theft by determining whether a photographing target is a living body or a non-living body, a collating unit that performs identity collation based on a photographed image, and a control unit that controls execution timing of a detection process performed by the detecting unit and an identity collating processing performed by the collating unit and, in a case where the detection performed by the detecting unit is performed for a first number of times, performs the collation process performed by the collating unit, wherein the first number of times is set in consideration of a tradeoff between a required intensity of security and convenience of a user using the identity authentication system.

Abstract: According to one embodiment, a person authentication method includes obtaining, from a medium carried by a person who passes through a first position, first information indicating the gender and the age of the person; performing a first authentication operation with respect to a person whose face image is included in a first image obtained by capturing a person passing through the first position; and setting, as the first authentication operation, an authentication operation to be performed using the face image of a person having the gender and the age specified in the first information.

Abstract: A person verification system includes an imager, a reader, storage, a selector, and a determiner. The imager images a target person trying to pass through a first gate. The reader reads personal information including an image of a person indicated by identification and attributes of the person, from the identification held by the target person. The storage stores plural algorithms, each algorithm is provided for each of the attributes of the person. The selector selects the algorithm for each of the attributes that are included in the personal information, from the storage unit. The determiner calculates the degree of similarity between the captured image and the image included in the personal information, in accordance with the algorithm selected, and determines whether or not the target person is the person indicated by the identification using the degree of similarity calculated.

Abstract: According to one embodiment, a biological information processor includes: an area detection unit configured to detect an area in which a person is displayed from image information; a feature extraction unit configured to extract feature information based on a characteristic portion of a person from the area detected by the area detection unit from the image information; and a determination unit configured to determine an extraction precision indicating whether or not the characteristic portion of the person can be extracted, with respect to the feature information extracted by the feature extraction unit based on a position of the characteristic portion.

Abstract: According to an embodiment, a people search system includes a receiver, a detector, a search unit, and a display. The search unit obtains features of a first face image and a second face image of a predetermined person and searches for the predetermined person based on a similarity between the features of the first and the second face images when an inhibiting factor is not detected, and generates a third face image that is a composite image of the second face image and the inhibiting factor, obtains features of the first and the third face images, and searches for the predetermined person based on a similarity between the features of the first and the third face images when the inhibiting factor is detected The display displays the search result of the predetermined person obtained by the search unit.

Abstract: According to one embodiment, an information processing method includes a process to execute, using first biological data read from a medium held by a passer passing through a first position, and second biological data acquired from an image obtained by imaging the passer passing through the first position, a first authentication processing to authenticate the passer; a process to store third biological data, based on at least one of the first biological data and the second biological data used in the first authentication processing, in a memory, when the authentication of the passer by the first authentication processing has succeeded; a process to execute, using fourth biological data acquired from an image obtained by imaging a passer passing through a second position at a more downstream side than the first position in a proceeding direction of the passer, and the third biological data stored in the memory, a second authentication processing to authenticate the passer; and a process to permit passing throu

Abstract: A person recognition apparatus is disclosed that includes an image input unit, a face detection unit in which a face is expressed from the inputted image data, as a score which takes a value in accordance with facial likeness, a facial feature point detection unit, a feature extraction unit, a feature data administrative unit, a person identification unit to calculate similarity between the amount calculated by the feature extraction unit and the amount stored in the feature data administrative unit, a number of candidates calculation unit which displays the images stored in descending order of the similarity, and calculates a score from the face detection unit and the facial feature point detection unit, a candidate confirmation unit in which images displayed in descending order of the similarity are subjected to visual inspection.