A videoconferencing system includes a camera acquiring image data and a microphone array acquiring audio data. Image data is used in conjunction with sound source localization (SSL) data to locate a talker depicted in the image data. SSL processes the audio data and determines SSL pan angle values indicative of an estimated direction of a sound. Columns of pixels in an image are associated with bins. A bin count is incremented for each SSL pan angle value of the audio data that falls within a given bin. A bounding box in the image data is determined that encompasses a face depicted in the image data. A range of pixels is determined for the bounding box, such as extending from a leftmost column to a rightmost column. The bin with the highest bin count that also overlaps a range of pixels for a bounding box is deemed to contain the talker.

The image processing unit selects multiple subject areas from strobe-ON image data to be corrected, and, from the selected multiple subject areas, the image processing unit acquires a feature amount such as gloss information corresponding to each subject. Subsequently, from each subject area, the image processing unit selects a part of the subject area, based on the acquired feature amount. Then, regarding the partial area of each subject area, which is selected based on the feature amount, the image processing unit estimates the auxiliary light arrival rate corresponding to each subject, based on a pixel value of the strobe-ON image data and a pixel value of strobe-OFF image data. Thereafter, based on the estimated auxiliary light arrival rate, the image processing unit corrects the brightness of each subject area of the strobe-ON image data, in order to generate corrected image data.

A backlight face recognition method, a terminal device using the same, and a computer readable storage medium are provided. The method includes: performing a face detection on each original face image in an original face image sample set to obtain a face frame corresponding to the original face image; capturing the corresponding original face images from the original face image sample set, and obtaining a new face image containing background pixels corresponding to the captured original face images from the original face image sample set; preprocessing all the obtained new face images to obtain a backlight sample set and a normal lighting sample set; and training a convolutional neural network using the backlight sample set and the normal lighting sample set until the convolutional neural network reaches a preset stopping condition. The trained convolutional neural network will improve the accuracy of face recognition in complex background and strong light.

Arrangement for acquiring images for producing a head related transfer function filter is disclosed. In the arrangement the camera of a mobile phone or similar portable device is adjusted for the imaging. All acquired images are analyzed and only suitable images are sent further for producing the head related transfer filter. The arrangement is further configured to provide instructions to the user so that the whole head and other relevant body parts are sufficiently covered.

A system for remote identity verification including a computing device configured to capture a first image of the user a first distance and capture a second image at a second distance and then processing the images to create one or more facemaps. The facemaps are processed to verify that the images were captured from a live person. If the facemaps represents a live person, the facemaps and a user identifying code are sent to a trusted image server. The rusted image server configured to, using the user ID code, retrieve a trusted image from a database and generate a trusted image facemaps. Then, compare captured image facemaps to the trusted image facemaps. Responsive to a match between the captured image facemaps and the trusted image facemaps, send a message to the computing device, a third-party server, or both providing notice of the match.

A collation system of the present invention includes an imaging means for acquiring a captured image of a pre-passage side area with respect to a gate, a collation means for performing a collation process between a previously registered target and a target in the captured image, and a determination means for determining propriety of passage of the target with respect to the gate, on the basis of a result of the collation process. The collation means initiates the collation process on the basis of a condition, set to each area of the captured image, for the target located in the area.

A light emitting device includes a wiring substrate, a light emitting element array that includes a first side surface and a second side surface facing each other, and a third side surface and a fourth side surface connecting the first side surface and the second side surface to each other and facing each other, the light emitting element array being provided on the wiring substrate, a driving element that is provided on the wiring substrate on the first side surface side and drives the light emitting element array, a first circuit element and a second circuit element that are provided on the wiring substrate on the second side surface side to be arranged in a direction along the second side surface, and a wiring member that is provided on the third side surface side and the fourth side surface side and extends from a top electrode of the light emitting element array toward an outside of the light emitting element array.

A self-service terminal (100) and a method (300, 600) for operating a self-service terminal are disclosed, wherein the self-service terminal (100) comprises: an imaging device (102), configured for providing at least one digital image (104); at least one processor (110), configured for: determining whether the at least one digital image (104) comprises a face of a person; if the at least one digital image (104) comprises the face of the person, cutting out from the at least one digital image (104) an image region which comprises the face of the person; and a storage device (108), configured for storing the image region.

A vehicle monitoring system includes at least one camera, and a server that is communicably connected to the camera and a client terminal. The camera captures an occupant's face of a vehicle entering an angle of view of the camera, and transmits a captured video to the server. The server acquires an analysis results of an attribute of the vehicle, an analysis result of the occupant's face, and an analysis result of the number of occupants based on the captured video, and accumulates the acquired analysis results as analysis results of the captured video, and sends the analysis result to the client terminal in correlation with a snapshot of the captured video.

A method is provided that includes displaying, by a computing device, representations of a plurality of stock videos to a user. The representations are at a still image, a partial clip, and/or a full play of the stock video. Each of the representations include a face outline for insertion of a facial image of a user. When the user has provided a self-image to the computing device, the facial image of the user is inserted in the face outline of the representations. The facial image is extracted from the self-image. The method may include receiving a selection of one of the representations of the plurality of stock videos, and displaying a personalized video including a selected stock video with the facial image positioned within a further face outline corresponding to the face outline of the selected representation.