Abstract: According to one or more embodiments, an image processing device includes a storage device and a processor. The storage device stores a plurality of time-series images. The processor extracts one or more feature points of a first image of the time-series images, sets a search range for one or more corresponding points of the feature points in a second image of the time-series images, searches for the one or more corresponding points in the search range of the second image, if there are a plurality of corresponding points searched, associates the searched corresponding points with the feature points based on a positional relationship between the corresponding points.

Abstract: According to one or more embodiments, an image processing device includes a storage device and a processor. The storage device stores a plurality of time-series images. The processor extracts one or more feature points of a first image of the time-series images, sets a search range for one or more corresponding points of the feature points in a second image of the time-series images, searches for the one or more corresponding points in the search range of the second image, if there are a plurality of corresponding points searched, associates the searched corresponding points with the feature points based on a positional relationship between the corresponding points.

Abstract: A moving body control apparatus of an embodiment is a moving body control apparatus including an image processing device configured to estimate a camera attitude on the basis of a photographed image obtained by a camera provided on a moving body and to output the camera attitude as an estimation result and a power control portion configured to control a power portion provided on the moving body on the basis of the estimation result, in which the image processing device includes a reliability feature amount calculating portion configured to calculate a reliability feature amount of the estimation result and a reliability determining portion configured to determine reliability of the estimation result on the basis of the reliability feature amount, and the power control portion determines whether automatic control of the power portion is executed or not on the basis of a determination result of the reliability.

Abstract: In a person retrieval apparatus, a plurality of extraction processing sections each extract personal biometric information from images taken by a plurality of cameras. A quality determination section determines a quality of each piece of biometric information extracted by the extraction processing sections. A reliability level setting section sets a reliability level to each piece of biometric information on the basis of the quality determined by the quality determination section. The biometric information extracted by the extraction processing sections and the reliability level set by the reliability level setting section are stored in a memory. In this state, in the person retrieval apparatus, the face retrieval section performs person retrieval processing on each piece of biometric information stored in the memory in descending order of the reliability level corresponding to each piece of biometric information.

Abstract: According to embodiments, an image display apparatus includes: a face detection processing section configured to detect face areas included in video content to generate face cut-out images including the face areas; a face clustering processing section configured to group a plurality of face cut-out images included in the video content by respective characters of the video content to classify clusters corresponding to the characters; an evaluation section configured to obtain evaluation values by evaluating the plurality of face cut-out images in relation to one or more evaluation items among a plurality of evaluation items corresponding to a plurality of features included in the face cut-out images; and a selection section configured to select face cut-out images in which evaluation values are within a predetermined range from among the plurality of face cut-out images in the clusters as representative face icon images used for display.

Abstract: In a person retrieval apparatus, a plurality of extraction processing sections each extract personal biometric information from images taken by a plurality of cameras. A quality determination section determines a quality of each piece of biometric information extracted by the extraction processing sections. A reliability level setting section sets a reliability level to each piece of biometric information on the basis of the quality determined by the quality determination section. The biometric information extracted by the extraction processing sections and the reliability level set by the reliability level setting section are stored in a memory. In this state, in the person retrieval apparatus, the face retrieval section performs person retrieval processing on each piece of biometric information stored in the memory in descending order of the reliability level corresponding to each piece of biometric information.

Abstract: A face authentication unit includes an acquisition unit configured to acquire an image including at least the face of a moving person, a face detection unit configured to detect a face region candidate of the person from the image acquired by the acquisition unit, and to detect a face region from the detected face region candidate, a face recognition unit configured to recognize an image of the face region detected by the face detection unit and registered face information which is stored in advance, and an authentication unit configured to authenticate the person based on the recognition result of the face recognition unit.

Abstract: A face image read apparatus which reads the face image of a moving person by the time he or she arrives at a particular position, comprises first and second image capture units configured to capture an area where the moving person enters from first and second directions, respectively, a first detector unit configured to detect the face region of the moving person from an image captured by the first image capture unit, a second detector unit configured to detect whether the number of face regions detected by the first detector unit is one or more, and a switching control unit configured to, according to the result of detection by the second detector unit, switch between a first process based on an image captured by the first image capture unit and a second process based on images captured by the first and second image capture units.

Abstract: A face authentication system which authenticates the faces of persons passing through at least two parallel passages before the persons reach predetermined positions includes a plurality of image sensing units arranged in the predetermined positions of the plurality of passages to record images of persons passing through the passages, a plurality of face authenticating units for checking whether the persons are preregistered persons, on the basis of the images obtained from the plurality of image sensing units, and a blind plate installed between every two adjacent passages making a pair among the plurality of passages to prevent the image sensing unit installed in one passage to record a person passing through the passage from recording a person passing through the other passage. The recording direction of the image sensing unit installed in one passage points to the other passage.

Abstract: A pedestrian moves in a direction indicated by the arrow “a”, and the face of the pedestrian M facing a door provided in an entrance and exit target area is captured by cameras. Specifically, while the pedestrian M exists between a position C and a position A in the walking area, an image including at least a face of the pedestrian M is captured as an image by the cameras. While the pedestrian M reaches the door from the position A, it is determined whether or not the pedestrian M is a person who has been registered in advance, based on the captured image. In the case where the determination result is affirmative, the door is opened.

Abstract: A pedestrian moves in a direction indicated by the arrow “a”, and the face of the pedestrian M facing a door provided in an entrance and exit target area is captured by cameras. Specifically, while the pedestrian M exists between a position C and a position A in the walking area, an image including at least a face of the pedestrian M is captured as an image by the cameras. While the pedestrian M reaches the door from the position A, it is determined whether or not the pedestrian M is a person who has been registered in advance, based on the captured image. In the case where the determination result is affirmative, the door is opened.

Abstract: In this invention, the detection result indicating physical characteristics obtained from sensor sections and associated with a to-be-detected object for which it is determined that determination of detection thereof by a high-speed detecting process is difficult to make is stored in a data storage unit. Then, in a precise examination processing section, the detecting process is effected on the non-real time basis for a to-be-detected object for which it is determined that the precise examination is necessary by the high-speed detecting process by use of data stored in the data storage unit and the to-be-detected object is distributed into a storage box corresponding to a category of the to-be-detected object as the detection result from the precise examination processing section.

Abstract: In this invention, the detection result indicating physical characteristics obtained from sensor sections and associated with a to-be-detected object for which it is determined that determination of detection thereof by a high-speed detecting process is difficult to make is stored in a data storage unit. Then, in a precise examination processing section, the detecting process is effected on the non-real time basis for a to-be-detected object for which it is determined that the precise examination is necessary by the high-speed detecting process by use of data stored in the data storage unit and the to-be-detected object is distributed into a storage box corresponding to a category of the to-be-detected object as the detection result from the precise examination processing section.