Abstract: Methods and systems for license plate recognition utilizing a trained neural network. In an example embodiment, a neural network can be subject to operations involving iteratively training and adapting the neural network for a particular task such as, for example, text recognition in the context of a license plate recognition application. The neural network can be trained to perform generic text recognition utilizing a plurality of training samples. The neural network can be applied to a cropped image of a license plate in order to recognize text and produce a license plate transcription with respect to the license plate. An example of such a neural network is a CNN (Convolutional Neural. Network).

Abstract: Embodiments that relate to determining an estimated pupil region of an eye are disclosed. In one embodiment a method includes receiving an image of an eye, with the image comprising a plurality of pixels. A rough pupil region is generated using at least a subset of the plurality of pixels. A plurality of pupil boundary point candidates are extracted from the rough pupil region, with each of the candidates weighted based on color values of at least two neighbor pixels. A parametric curve may be fitted to the weighted pupil boundary point candidates to determine the estimated pupil region of the eye of the user.

Abstract: An unpacking method, an unpacking device and an unpacking system of a packed frame are disclosed. The packed frame is to be displayed on a screen and includes a color frame and a resized depth frame, and the color frame is corresponding to the resized depth frame. The center of the color frame is displayed in the central area of the screen. The unpacking method includes the steps of: extracting the color frame and the resized depth frame from the packed frame; and restoring the resized depth frame to obtain an original depth frame.

Abstract: Systems, methods, and non-transitory computer-readable media can calculate raw scores for a plurality of media items based on a classifier model and a target concept. The plurality of media items are ranked based on the raw scores. A review set of the plurality of media items is determined, the review set comprising a subset of the plurality of media items. Each of the media items of the review set is associated with a content depiction determination. A normalized score formula is calculated based on the raw scores and the content depiction determinations for the media items of the review set.

Abstract: A touch screen, now incorporated in most smart phones, presents an effective and transparent method to incorporate continuous active user verification schemes. The projected capacitive grid structure can be used to capture information, such as from the user's fingerprint. This information may be used to verify the user, or that a valid user currently has possession of the mobile device, even while the user is not consciously engaged in an active verification interface. Further processing, such as habitual gesture recognition, can augment the process.

Abstract: A method of a measuring kinematic parameter in a subject is provided. The method includes obtaining a first magnetic resonance (MR) image set of a bone marrow segment of the subject in a first position and obtaining a second MR image set of the bone marrow segment of the subject in a second position where the second position different from the first position. The method further includes registering the first image set with the second image set and measuring a kinematic parameter.

Abstract: A fire detection method and apparatus accurately detects a fire. The fire detection method includes obtaining RGB data from an image; calculating at least one index related to the attributes of fire using the obtained RGB data; and determining the occurrence of a fire using the index.

Abstract: An image generating apparatus for image generation is provided. The image generating apparatus includes a movable detector for detecting nuclear radiation during a detection period and an evaluation system. The evaluation system includes an interface system for transmitting detector data to the evaluation system. The detector data include information about the detected radiation for image generation. The evaluation system further includes a data memory portion for storing the detector data. The evaluation system further includes a program memory portion with a program for repeatedly determining at least one quality value with respect to image generation during the detection period.

Abstract: Provided is an image processing device including a selection section configured to select, from a plurality of transform units with different sizes, a transform unit used for inverse orthogonal transformation of image data to be decoded, a generation section configured to generate, from a first quantization matrix corresponding to a transform unit for a first size, a second quantization matrix corresponding to a transform unit for a second size from a first quantization matrix corresponding to a transform unit for a first size, and an inverse quantization section configured to inversely quantize transform coefficient data for the image data using the second quantization matrix generated by the generation section when the selection section selects the transform unit for the second size.

Abstract: Systems, methods, and non-transitory computer-readable media can receive a selection of an image. An object included in the image can be detected. An image portion that includes the object can be extracted from the image. The image portion can be provided for image analysis based on one or more object recognition processes. An identifier for the object can be received. The identifier can be determined based on the one or more object recognition processes being applied to the image portion.

Abstract: A radiation detection system includes a detector unit and at least one processor. The detector unit is configured to generate signals responsive to radiation. The at least one processor is operably coupled to the detector unit and configured to receive the signals from the detector unit. The at least one processor is configured to obtain, during an imaging process, a first count for at least one of the signals corresponding to a first intrinsic energy window, the first energy window corresponding to values higher than an intrinsic peak value; obtain a second count for the at least one of the signals corresponding to a second intrinsic energy window, the second energy window corresponding to values lower than the intrinsic peak value; and adjust a gain applied to the signals based on at least the first count and the second count.

Abstract: A machine vision system for automatically identifying and inspecting objects is disclosed, including composable vision-based recognition modules and a decision algorithm to perform the final determination on object type and quality. This vision system has been used to develop a Projectile Identification System and an Automated Tactical Ammunition Classification System. The technology can be used to create numerous other inspection and automated identification systems.

Abstract: A method and apparatus for processing images. A set of candidate targets is identified in a first image and in a second image that corresponds with the first image. A set of first scores is generated for the set of candidate targets using the first image. A set of second scores is generated for the set of candidate targets using the second image. A set of final scores is computed for the set of candidate targets using the set of first scores and the set of second scores. A determination is made as to which of the set of candidate targets is a target of interest based on the set of final scores.

Abstract: An apparatus and method for performing automatic 3D image segmentation and reconstruction of organ structures, which is particularly well-suited for use on cortical surfaces is presented. A brain extraction process removes non-brain image elements, then classifies brain tissue as to type in preparation for a cerebrum segmentation process that determines which portions of the image information belong to specific physiological structures. Ventricle filling is performed on the image data based on information from a ventricle extraction process. A reconstruction process follows in which specific surfaces, such as white matter (WM) and grey matter (GM), are reconstructed.

Abstract: A user is authenticated based on user features that can be captured by a camera, such as facial features or eye features. In order for the user to be authenticated, an image is captured of the user while the user is within an interaction zone, which is an area that is within both a field of view of the camera and a suitable distance range from the camera. If the user is not within the suitable distance range from the camera, then feedback is provided indicating that the user is not within the suitable distance range from the camera. Various feedback can be provided, such as one or a combination of audio, visual, and haptic feedback. The feedback notifies the user that an adjustment is to be made to the location of the user and/or the camera in order for the user to be within the interaction zone.

Abstract: Techniques related to image refocusing for camera arrays using a space variant filter based on a pixel by pixel blur level associated with a difference between a reference image and a basic refocused image are discussed. Such techniques may include taking the difference between the reference image and the basic refocused image and applying a space variant filter to the basic refocused image to generate a final refocused image having a region of increased blur with respect to the all in focus reference image. The blur level implemented by the space variant filter may be based on the difference and, optionally, the reference image noise level and the reference image gradient.

Abstract: The present application concerns the visual identification of materials or documents for tracking or authentication purposes. It describes methods to automatically authenticate an object by comparing some object images with reference images, the object images being characterized by the fact that visual elements used for comparison are non-disturbing for the naked eye. In some described approaches it provides the operator with visible features to locate the area to be imaged. It also proposes ways for real-time implementation enabling user friendly detection using mobile devices like smart phones.

Abstract: A medical imaging device and a method for providing an image representation supporting positioning of an intervention device such as a wire tip (4) in a region of interest during an intervention is proposed. Therein, the following process steps are to be performed: (S1) acquiring a pre-live anatomy image (1) including a region of interest; (S2) acquiring a live anatomy image using a live image acquisition device comprising an adjustable collimator device; (S3) identifying a location (5) of the intervention device (4) within the live anatomy image; (S4) adjusting settings of the collimator device based on the identified location of the intervention device for subsequently acquiring a further live anatomy image representing the region of interest using the live image acquisition device with the collimator device being in the adjusted settings; and providing (S5) the image representation by merging information from the live anatomy image into the pre-live anatomy image.

Abstract: The present invention relates to a system and method for efficiently generating images and videos as an array of objects of interest (e.g., faces and hands, plates, etc.) in a desired resolution to perform vision tasks, such as face recognition, facial expression analysis, detection of hand gestures, among others. The composition of such images and videos takes into account the similarity of objects in the same category to encode them more effectively, providing savings in terms of time transmission and storage. Transmission time is less advantage to such a system in terms of efficiency, while less low cost storage means for storing data.

Abstract: A system and a method for determining an orthodontic diagnostic analysis of a patient at various dental maturity stages predicts future conditions and/or treatment recommendations. The system and the method locate points in a mouth of a patient using an imaging device wherein the imaging device generates imaging data. The imaging data is transferred to a central processing unit wherein the central processing unit has access to a database having information associated with orthodontic conditions stored therein. The central processing unit obtains measurements associated with selected points and dentition in the mouth of the patient and predicts orthodontic conditions of the patient based upon the measurements and the information in the database. The central processing unit recommends treatments to the patient based upon the predicted orthodontic conditions.