Abstract: Described is a multiple-camera system and process for re-identifying a user located in a materials handling facility based on user patterns and/or descriptors representative of the user. In one implementation, a user pattern and/or a plurality of descriptors representative of a user are maintained as a position of a user is tracked through a materials handling facility. If the tracking of the user is lost, the last known position is stored with the user pattern and/or descriptors. If a new object is detected and confirmed to be a user, a user pattern and/or descriptors of the new object are compared with the stored user pattern and/or descriptors to determine if the new object is the user.

Abstract: Embodiments relate to bioimpedence-based spoof detection in an optical biometric reader. For example, embodiments operate in context of a biometric reader having a platen integrated with substantially transparent bioimpedance source and receiver electrodes covered by a substantially transparent protective layer. A multi-frequency input signal can be injected from the source electrode into a purported skin site (through the protective layer), so that a response signal is received by the receiver electrode. The response signal is interrogated to formulate a dispersive bioimpedance response of the purported skin site to the input signal over multiple frequencies. A biometric spoof determination can then be made according to the dispersive bioimpedance response. The spoof determination can be used for spoof detection, presence detection, and/or other functions.

Abstract: This disclosure provides an image processing method and processing system. The method includes obtaining an image and selecting a calibration area of the image. The method also includes reading a feature parameter corresponding to the calibration area from a preset segmentation model. The method further includes segmenting the image by using the feature parameter, to generate a segmentation result corresponding to the calibration area. This image segmentation by using the feature parameter obtained from the segmentation model provides a high accuracy segmentation rate and can be applied in wide scenarios.

Abstract: Various techniques are disclosed for systems and methods to provide image resolution enhancement. For example, a method includes: receiving a reference image (e.g., a visible light image) of a scene comprising image pixels identified by pixel coordinates; receiving a lower-resolution target image (e.g., an infrared image) of the scene; resizing the target image to a larger size; determining an adaptive-shape neighborhood for each pixel coordinate, wherein the adaptive-shape neighborhood extends from the each pixel coordinate such that those reference image pixels that are within the shape-adaptive neighborhood meet a regularity condition; determining, for each adaptive-shape neighborhood, a local estimate based on those target image pixels that are within the adaptive-shape neighborhood; and aggregating the local estimates associated with the adaptive-shape neighborhoods to provide a global estimate that corresponds to the target image with an improved resolution.

Abstract: An example apparatus for imaging in low-light environments includes a raw sensor data receiver to receive raw sensor data from an imaging sensor. The apparatus also includes a convolutional neural network trained to generate an illuminated image based on the received raw sensor data. The convolutional neural network is trained based on images captured by a sensor similar to the imaging sensor.

Abstract: Aspects of the present disclosure provide a method for compressing a point cloud. The method includes determining a sub-division technique for the volume based on one or more numbers derived from a distribution of points in the volume, dividing the volume into a number of sub-volumes according to the sub-division technique, and determining whether each sub-volume of the sub-volumes is occupied by at least one point. The method includes generating a bit sequence for the volume comprising a control code that is based on the sub-division technique and an occupancy indicator that indicates whether or not each sub-volume is occupied by at least one point.

Abstract: Embodiments of the present invention provide a method for sharing and downloading a light field image. The method includes: receiving a request for sharing a light field image with a first object; analyzing the light field image to obtain a refocusing focal point of the light field image; generating an ordinary image by using the light field image and by using the refocusing focal point as a focal point; and sharing the ordinary image with the first object. According to the method provided in the embodiments of the present invention, a refocusing focal point is automatically selected, so that a problem of selecting a refocusing focal point when a light field image is converted into an ordinary image is resolved, and the light field image is converted by using the refocusing focal point and shared with the first object.

Abstract: A medical information processing apparatus according to an embodiment includes processing circuitry. The processing circuitry obtains image data rendering a blood vessel of patient. The processing circuitry performs a fluid analysis on the obtained image data and calculates an index value related to a blood flow in the blood vessel with respect to each of a plurality of positions in the blood vessel. With respect to the index values to be calculated, the processing circuitry selects a position in which a first value is to be obtained from among the plurality of positions or selects a value serving as the first value from among the index values exhibited in positions. The processing circuitry causes a display to display the first value in a predetermined display region thereof used for displaying the first value.

Abstract: An image identification system may identify key points on a known image and an unidentified image. One or more geometric shapes may be formed from the key points. A match between the unidentified image and the know image nay be determined by comparison of the respective geometric shapes.

Abstract: A two-step approach for image segmentation during the treatment planning process is disclosed. In a first step, an automatic segmentation method can be used to generate a first, provisional segmentation. The first, provisional segmentation may be generated using fast, but less accurate segmentation methods. The first provisional segmentation may be used to generate a default treatment plan for approval. Once the default treatment plan is approved, a more robust, second image segmentation may be performed. The second segmentation may be used to design patient-specific devices that can be used to deliver the patient-specific medical treatment.

Abstract: Provided are an image processing device, an imaging device, and an image processing method which are capable of obtaining a captured image with desired image quality. An image processing unit functioning as an image processing device includes a point image restoration processing unit that performs point image restoration processing using a restoration filter based on a point spread function of a lens unit on image data obtained from an imaging element through imaging of a subject using an imaging unit having a lens unit including a lens and the imaging element, and a determination unit that determines whether or not to perform the point image restoration processing using the point image restoration processing unit based on spherical aberration of the lens changed by an imaging condition. The point image restoration processing unit performs the point image restoration processing only in a case where the determination unit determines to perform the point image restoration processing.

Abstract: Systems and methods provide adapted content to a visitor to a physical environment. An example method receives an image of a visitor to an environment. A visitor portion of the image is distinct from an environment portion of the image. The method detects one or more shapes in the visitor portion of the image using an automatic shape detection technique and defines an approximate boundary of the one or more shapes using a mask. The one or more shapes can be shapes of the visitor's clothing items. The method then calculates an attribute for an area of the image within the mask and identifies electronic content based on the attribute for the area of the image within the mask. The attribute can be a color attribute for the area such as a median color or a dominant color. The method provides the identified electronic content for display in the environment.

Abstract: A coding efficiency improvement is achieved by performing bit-plane coding in a manner so that coefficient groups for which the set of coded bit-planes is predictively signaled in the datastream, are grouped in two group sets and if a signal is spent in the datastream which signals, for a group set, whether the set of coded bit-planes of all coefficient groups of the respective group set are empty, i.e. all coefficients within the respective group sets are insignificant. In accordance with another aspect, a coding efficiency improvement is achieved by providing bit-plane coding with group-set-wise insignificant signalization according to the first aspect as a coding option alternative relative to the signalization for group sets for which it is signaled that there is no coded prediction residual for the coded bit-planes for the claim groups within the respective group set.

Abstract: Returning a location for a device is accomplished by receiving a first image, captured by a device, and a first orientation of the device from the device over one or more networks. A second image, captured by the device, and a second orientation of the device is received from the device over one or more networks. A first location of a first object included in the first image and a second location of a second object included in the second image can be determined respectively from a database of object locations. A location of the device is determined according to the first orientation, the second orientation, the first location of the first object and the second location of the second object. The device location is transmitted to the device.

Abstract: Face recognition of a face, to determine whether the face correlates with an enrolled face, may include generating a personalized three-dimensional (3D) face model based on a two-dimensional (2D) input image of the face, acquiring 3D shape information and a normalized 2D input image of the face based on the personalized 3D face model, generating feature information based on the 3D shape information and pixel color values of the normalized 2D input image, and comparing the feature information with feature information associated with the enrolled face. The feature information may include first and second feature information generated based on applying first and second deep neural network models to the pixel color values of the normalized 2D input image and the 3D shape information, respectively. The personalized 3D face model may be generated based on transforming a generic 3D face model based on landmarks detected in the 2D input image.

Abstract: A method for transforming an image descriptor, based on a gradient histogram (h) having a plurality of histogram bins (hi), into a transformed gradient histogram descriptor (v) including a set of values (vj), wherein it is provided the step of applying at least one criterium for calculating the set of values (vj), at least one criterium having a location criterium of the histogram bins (hi). The invention also relates to an image processing device suitable for carrying out the method.

Abstract: A video analysis system includes: a video data acquiring means that acquires video data; a moving object detecting means that detects a moving object from video data acquired by the video data acquiring means, by using a moving object detection parameter, which is a parameter for detecting a moving object; an environment information collecting means that collects environment information representing an external environment of a place where the video data acquiring means is installed; and a parameter changing means that changes the moving object detection parameter used when the moving object detecting means detects a moving object, on the basis of the environment information collected by the environment information collecting means.

Abstract: The inventive concept relate to an empty house utilization evaluation method comprising receiving, by an empty house utilization evaluation server, satellite image data for an empty house to be evaluated, extracting, by the empty house utilization evaluation server, images of a population element, a traffic element, a natural element, and a social element of the empty house to be evaluated from the received satellite image data, analyzing, by the empty house utilization evaluation server, utilization of the empty house to be evaluated based on the extracted images of the population element, the traffic element, a natural element, and the social element of the empty house to be evaluated and suggesting, by the empty house utilization evaluation server, a use of the empty house to be evaluated according to a result of the analyzing utilization of the empty house to be evaluated.

Abstract: Provided are an image processing device, an imaging device, and an image processing method which are capable of obtaining a captured image with desired image quality. An image processing unit functioning as an image processing device includes a point image restoration processing unit that performs point image restoration processing using a restoration filter based on a point spread function of a lens unit on image data obtained from an imaging element through imaging of a subject using an imaging unit having the lens unit including a lens and the imaging element, and a determination unit that determines to perform the point image restoration processing using the point image restoration processing unit in a case where a modulation transfer function in a predetermined spatial frequency in which the point image restoration processing contributes is smaller than a threshold value. Here, the modulation transfer function is changed by an imaging condition.

Abstract: Fill techniques as implemented by a computing device are described to perform hole filling of a digital image. In one example, deeply learned features of a digital image using machine learning are used by a computing device as a basis to search a digital image repository to locate the guidance digital image. Once located, machine learning techniques are then used to align the guidance digital image with the hole to be filled in the digital image. Once aligned, the guidance digital image is then used to guide generation of fill for the hole in the digital image. Machine learning techniques are used to determine which parts of the guidance digital image are to be blended to fill the hole in the digital image and which parts of the hole are to receive new content that is synthesized by the computing device.