Abstract: A method and an apparatus for updating fingerprint templates, and a mobile terminal are provided. The method includes acquiring a fingerprint image input by a user. The fingerprint image is compared with fingerprint templates pre-stored in a fingerprint template set, where the fingerprint template set comprises N fingerprint templates and N is a positive integer. A mobile terminal performs a target operation when a match value between the fingerprint image and an ith fingerprint template of the fingerprint template set is greater than a first preset threshold. The method determines whether the match value set is greater than a second preset threshold. The method generates a new fingerprint template based on the fingerprint image and adds the new fingerprint template to the fingerprint template set when the match value between the fingerprint image and the ith fingerprint template is greater than the second preset threshold.

Abstract: Exemplary embodiments are directed to biometric analysis systems generally including one or more illumination sources, a camera, and an analysis module. The illumination sources are configured to illuminate at least a portion of a face of a subject. The camera is configured to capture one or more images of the subject during illumination of the face of the subject. The analysis module is configured to analyze the one or more images captured by the camera to determine an indication of liveliness of the subject and prevent spoofing.

Abstract: The method of determination of a depth map of a scene comprises generation of a distance map of the scene obtained by time of flight measurements, acquisition of two images of the scene from two different viewpoints, and stereoscopic processing of the two images taking into account the distance map. The generation of the distance map includes generation of distance histograms acquisition zone by acquisition zone of the scene, and the stereoscopic processing includes, for each region of the depth map corresponding to an acquisition zone, elementary processing taking into account the corresponding histogram.

Abstract: A device and method for compensating dead pixels of an image includes estimating brightness changing trends at two sides of a dead pixel in image data and determining dead pixel brightness compensation values corresponding to the two sides of the dead pixel. Difference values between the brightness changing trends and between the dead pixel brightness compensation values at the two sides of the dead pixel along each predetermined direction is determined and a weighting factor corresponding to the difference values is determined. The dead pixel brightness compensation values corresponding to the two sides of the dead pixel along each predetermined direction are subjected to a weighting calculation based on the weighting factor to obtain a compensation result for the dead pixel.

Abstract: The invention relates to an eye tracking device (10a; 10b; 10c) comprising a processing unit (18) and an optical system (14), which comprises a capturing unit. The optical system (14) provides a first optical path (P; P1) with a first imaging property and a second optical path (P; P2) with a second imaging property and the capturing unit (C; C1, C2) captures a first image (24a) by capturing light that has passed along the first optical path (P; P1) and a second image (24b) by capturing light that has passed along the second optical path (P; P2), so that due to the difference of the first and second imaging property the first (24a) and the second image (24b) comprise a difference related to a characteristic of at least part of the first and the second image (24b), wherein the eye tracking device (10a; 10b; 10c) is configured to determine a property of the eye (12) on the basis of at least one of the first image (24a) and the second image (24b).

Abstract: In a watermark embedding method and apparatus, a layered three-dimensional model is aligned in a printing direction based on a layering direction of the layered three-dimensional model. Then, a watermark having a predetermined pattern is embedded into the aligned three-dimensional model in a direction orthogonal to the printing direction so that the embedded watermark is not associated with the printing direction.

Abstract: Models are generated from objects identified in video. Each model is evaluated based on knowledge of the objects determined from video analysis, and preferred models are identified based on the evaluations. In some examples, each model could be evaluated by tracking a movement of each object in the video by using each model to track the object from which it was generated, evaluating an ability of each model to identify the objects in the video that are similar to the object from which it was generated, and determining an amount of false identifications made by each model of different objects in different video that does not include the object from which it was generated.

Abstract: Described herein are systems and methods for capturing images of a field and performing agricultural data analysis of the images. In one embodiment, a computer system for monitoring field operations includes a database for storing agricultural image data including images of at least one stage of crop development that are captured with at least one of an apparatus and a remote sensor moving through a field. The computer includes at least one processing unit that is coupled to the database. The at least one processing unit is configured to execute instructions to analyze the captured images, to determine relevant images that indicate a change in at least one condition of the crop development, and to generate a localized view map layer for viewing the field at the at least one stage of crop development based on at least the relevant captured images.

Abstract: A method, server and system for operating on security inspection data is disclosed. In one aspect, an example method performed by a server for operating on security inspection data includes receiving an operation request for target security inspection data from a client through a network. The target security inspection data is loaded from a storage server based on the operation request. Image processing on the loaded target security inspection data is performed. The processed target security inspection data or a graphic interface including the processed target security inspection data is encoded. The encoded target security inspection data or graphic interface is transmitted to the client through the network in a video stream.

Abstract: A method for determining a spatial distribution of a material property value in an examination region of an examination object is described. With an embodiment of the method, projection scan data is acquired which has been produced with the aid of a single-energy CT scan with a defined X-ray energy spectrum from the examination region of the examination object using a defined scan projection geometry. Furthermore, a target function is established which includes a spectral forward projection of the sought spatial distribution and the acquired projection data. Finally, a spatial distribution of a material property value is determined for which the target function assumes an extremal value. A material property distribution-determining device is also described. A computer tomography system is described, moreover.

Abstract: Examples disclosed herein relate to selecting an image based on text topic and image explanatory value. In one implementation, a processor selects an image to associate with a text based on a criteria indicating the explanatory value of a context information related to the image in relation to the topic of the text. The processor may output the selected image.

Abstract: Various embodiments provide systems, methods, devices, and instructions for performing simultaneous localization and mapping (SLAM) that involve initializing a SLAM process using images from as few as two different poses of a camera within a physical environment. Some embodiments may achieve this by disregarding errors in matching corresponding features depicted in image frames captured by an image sensor of a mobile computing device, and by updating the SLAM process in a way that causes the minimization process to converge to global minima rather than fall into a local minimum.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying people depicted in images. In one aspect, a process includes receiving an image from a camera. A face of a person is detected in the image. The image is compared to a set of images stored in a local cache. A determination is made whether the face of the person matches a face of a person depicted by at least one image of the set of images. In response to determining that the face of the person does not match a face of a person depicted by at least one image of the set of images, a selection is made of a highest quality image of the face of the person. A server system compares the highest quality image to images from data for the multiple people to identify the person.

Abstract: Disclosed are various embodiments for computer-aided tracking and motion analysis with ultrasound. A computing device is employed to access an ultrasound video generated by at least one ultrasonic imaging device and/or at least one motion sensing camera. A target patch embodied is tracked throughout frames of the ultrasound video by compressing target patches of individual ones of the frames of the ultrasound video into vectors; generating a space partitioning data structure for each of the frames of the ultrasound video; and identifying an image intensity feature for each frame utilizing a corresponding one of the space partitioning data structures generated for each frame of the ultrasound video. Optimized tracking locations may be determined for a sequence of the ultrasound video using the image intensity feature identified for each frame.

Abstract: A method for detecting contaminations on a lens of a vehicle camera. Transition values are assigned to pixels of image frames. Three-dimensional coordinates are assigned to the pixels by using a simplified model of the scene. Using the assigned coordinates and movement data, trajectories are assigned to the pixels. An expectation value is derived from a transition value of a starting pixel of a trajectory and a satisfied transition value is derived from transition values along the trajectory. The expectation value and the satisfied transition value are accumulated over time, and a cleanliness value is derived from a ratio of the accumulated satisfied transition value to the accumulated expectation value.

Abstract: The present disclosure describes methods, apparatuses, and non-transitory computer-readable mediums for estimating a three-dimensional (“3D”) pose of an object from a two-dimensional (“2D”) input image which contains the object. Particularly, certain aspects of the disclosure are concerned with 3D pose estimation of a symmetric or nearly-symmetric object. An image or a patch of an image includes the object. A classifier is used to determine whether a rotation angle of the object in the image or the patch of the image is within a first predetermined range. In response to a determination that the rotation angle is within the first predetermined range, a mirror image of the object is determined. Two-dimensional (2D) projections of a three-dimensional (3D) bounding box of the object are determined by applying a trained regressor to the mirror image of the object in the image or the patch of the image. The 3D pose of the object is estimated based on the 2D projections.

Abstract: Assisted manual mail sorting system for assisting an operator in manual sortation of mailpieces in a sorting station including a plurality of destination bins, the system comprising a headset wearable by the operator and connected to a computer comprising an image analysis software for extracting from an image of one of the mailpieces, a name, an address or other relevant information and a sorting application for determining a corresponding relevant destination bin, the headset comprising: a high resolution camera for capturing the image of the mailpiece, a transparent display for signalling to the operator the relevant destination bin where the article is to be placed by highlighting or overlaying a visual artifact on a view of the sorting station while the operator is looking at the sorting station.

Abstract: An image processing device divides a recognition purpose image into a plurality of areas, selects feature points in the recognition purpose image such that a bias of the number of the feature points included in each of the areas is small registers information on the selected feature points in the recognition purpose image in a memory and estimates a position and an orientation of the camera based on the recognition purpose image registered in the memory and based on a captured image captured by a camera.

Abstract: The disclosure provides a digital video content security authentication method, wherein the method comprises: a secret information embedding step of selectively modifying a pixel grayscale value for each frame image in a digital video so as to complete the embedding of 1-bit secret information; and a secret information extraction and video authentication step of carrying out secret information extraction from the digital video in which the secret information is embedded according to a key so as to realize the security authentication of the digital video content. The disclosure also provides a digital video content security authentication system. According to the technical scheme provided by the disclosure, the authentication security is improved on the basis of not influencing user experience.

Abstract: Embodiments of the present invention provide a system for image capture and conversion. The system receives or captures an image of a resource document comprising image coordinates. The system can then cause a user interface of a computing device to display the image of the resource document and request that a specialist provide an input of an image coordinate area associated with a data field of the resource document. The specialist then provides a selection of boundaries for the coordinate area that encloses a value of the data field within the image of the resource document. The system then applies a data field-specific OCR process to the provided image coordinate area to extract a value of the data field. The extracted value can be presented on the display along with an enlarged view of the image coordinate area to allow the specialist to verify the accuracy of the extracted value.