Abstract: Disclosed is an electronic device. The electronic device includes a display; a camera; a sensor; a storage configured to store position information and work information of a smart machine; and a processor configured to identify a smart machine which is located within a peripheral area of the electronic device based on position information of the electronic device sensed through the sensor and position information of the smart machine stored in the storage, to obtain work information of the identified smart machine from the storage, and to indicate a work area of the smart machine on an image photographed through the camera based on the obtained work information of the smart machine and provide the image including the work area on the display.

Abstract: Methods and apparatus to determine the dimensions of a region of interest of a target object and a class of the target object from an image using target object landmarks are disclosed herein. An example method includes identifying a landmark of a target object in an image based on a match between the landmark and a template landmark; classifying a target object based on the identified landmark; projecting dimensions of the template landmark based on a location of the landmark in the image; and determining a region of interest based on the projected dimensions, the region of interest corresponding to text printed on the target object.

Abstract: Described is a novel method for feature extraction for automatic gait recognition. This method uses Multi-kernel Fuzzy-based Local Gabor Binary Pattern. From a captured gait video sequence, the gait period is determined then a gait energy image is constructed to represent the spatial-temporal variations during one motion cycle of the gait sequence. Then, each gait sequence is represented with a feature vector. The computation of this vector is conducted by first applying the 2D Gabor filter bank then encoding the variations in the Gabor magnitude using a multi-kernel fuzzy local binary pattern operator. Finally, gait classification is performed using a support vector machine.

Abstract: The present disclosure includes methods and systems to generate compression garment fit information from 3D images taken of one or more body parts of a patient indicated for application of compression therapy. The body parts can include legs or arms or other areas. Three-dimensional (“3D”) imaging information can be used to derive compression garment fit information, where the shape description information includes for each body part: tissue compressibility information, outer circumference information, and length information. Comparisons between corresponding body parts on a person can also be conducted.

Abstract: A method for facial analytics includes capturing a series of images of individuals from a camera into a circular buffer and selecting a plurality of images from the buffer for analysis in response to a trigger event, wherein the plurality of images are chronologically proximate before and/or after the trigger event in time. The method includes analyzing the plurality of images to determine image quality and selecting one of the plurality of images based on image quality to form a cropped facial image most likely to result in positive facial recognition matching. Methods of signaling to control the pedestrian traffic flow can maximize the individuals' facial alignment to the capturing camera's field of view. Non-relevant facial images associated with individuals outside a given region of interest can be discarded. Facial recognition is run on the resultant cropped facial image. Output can be displayed with information from the facial recognition.

Abstract: A system and method for generating high resolution images using a plenoptic camera having a main lens in front of an array of microlenses and an image sensor, characterized in that it comprises: capturing a first set of images in a first unexcited state of operation by using a birefringent medium disposed between a said main lens and an said array of microlenses, said unexcited state of said birefringent medium providing an ordinary ray to each pixel; causing said first unexcited state to become a second excited state by applying a voltage across said birefringent medium; capturing a second set of images in said second excited state, said excited state of said birefringent medium splitting the light from said main lens into an ordinary ray and an extraordinary ray, said extraordinary ray being shifted by a distance of one half-pixel from the ordinary ray on said image sensor; subtracting pixel value associated with said first set of images from at least two times the pixel value associated with said second se

Abstract: An algorithm for performing an image or video processing task is generated that may be used to combine a plurality of different independent solutions to the image or video processing task in an optimized manner. A plurality of base algorithms may be applied to a training set of images or video and a first generation of different combining algorithms may be applied to combine the respective solutions from each of the respective base algorithms into respective combined solutions. The respective combined solutions may be evaluated to generate respective fitness scores representing measures of how well the plurality of different combining algorithms each perform the image or video processing task. The algorithms may be iteratively updated to generate an optimized combining algorithm that may be applied to an input image or video.

Abstract: There is provided an encoding and decoding method and an information recognition device using the same. A code block includes a center coding region and a peripheral coding region arranged around the center coding region. The encoding and decoding method uses the feature of at least one microdot included in the center coding region as codes. The encoding and decoding method uses the feature of at least one microdot included in the peripheral coding region as codes. The encoding and decoding method uses the relative feature between the center coding region and the peripheral coding region as codes. The information recognition device compares the read feature with pre-stored features to decode information such as position codes, object codes, parameter codes and control codes.

Abstract: A system includes a processor and a memory storing instructions executable by the processor to predict a path of a liquid droplet on a surface, and then, actuate one or more vehicle components based on the path.

Abstract: The present disclosure relates to generating computer searchable text from digital images that depict documents utilizing an orientation neural network and/or text prediction neural network. For example, one or more embodiments detect digital images that depict documents, identify the orientation of the depicted documents, and generate computer searchable text from the depicted documents in the detected digital images. In particular, one or more embodiments train an orientation neural network to identify the orientation of a depicted document in a digital image. Additionally, one or more embodiments train a text prediction neural network to analyze a depicted document in a digital image to generate computer searchable text from the depicted document.

Abstract: An identification method includes: controlling at least one camera to acquire a face image and an eye image of a target object, wherein the eye image includes at least one of an iris feature or an eye-print feature; and identifying the target object based on the face image and the eye image.

Abstract: A method of color mapping a video signal represented in a first color volume from color mapping data to be applied on a video signal represented in a second color volume is disclosed. The method comprises: color mapping (14) said video signal represented in a first color volume from said first color volume into said second color volume in the case where said first and second color volumes are different; and color mapping (16) said color mapped video signal based on said color mapping data.

Abstract: A method for a verification process that performs neighbor discovery for one or more feature points projected to an m-dimensional space (m is a natural number equal to or greater than 2), includes: acquiring a feature point group including one or more feature points projected to coordinate values of the m-dimensional space ordered in a coordinate value order on each of two or more coordinate axes that define the m-dimensional spacer (m is a natural number equal to or greater than 2); selecting a datum axis on which a comparison time number in neighbor discovery is small, the comparison time number being obtained by performing simulation of neighbor discovery.

Abstract: At least one apparatus recognizes a first object and a second object associated with the first object in a plurality of images, calculates a score for each of the plurality of images based on a result of the recognition of the first object and the second object, and selects an image concerning the first object from the plurality of images based on the score for each of the plurality of images.

Abstract: An embodiment of a semiconductor package apparatus may include technology to store a block of self-contained data including one or more time sequential frames of image data from two or more camera positions, and access a portion of the image data based on a start location and offset information from a header of the block. Other embodiments are disclosed and claimed.

Abstract: An image processing apparatus having a generation unit configured to generate an aligned image by arranging a plurality of candidate images extracted from a reference image around a work inspection image extracted from an inspection target image; a unit configured to subject the aligned image to similar region extraction processing to represent a similarity between regions in the aligned image; a determination unit configured to select a candidate image and determine it as a work reference image based on the aligned image after being subjected to the similar region extraction processing; and a comparison unit to compare the work inspection image with the work reference image. The similar region extraction processing subjects each of a plurality of division regions obtained by dividing the aligned image based on predetermined division size and phase, to averaging processing, and then adds the results of the averaging processing that are obtained by varying at least one of the division size and phase.

Abstract: One aspect of the current disclosure provides a method of upscaling an image. The method includes: rendering an image, wherein the rendering includes generating color samples of the image at a first resolution and depth samples of the image at a second resolution, which is higher than the first resolution; and upscaling the image to an upscaled image at a third resolution, which is higher than the first resolution, using the color samples and the depth samples.

Abstract: Virtual boundary processing in adaptive loop filtering (ALF) requires that padded values be substituted for unavailable pixel rows outside the virtual boundaries. Methods and apparatus are provided for virtual boundary processing in ALF that allow the use of more actual pixel values for padding than in the prior art.

Abstract: Methods, systems, and devices for object recognition are described. Generally, the described techniques provide for a compact and efficient convolutional neural network (CNN) model for facial recognition. The proposed techniques relate to a light model with a set of layers of convolution and one fully connected layer for feature representation. A new building block of for each convolution layer is proposed. A maximum feature map (MFM) operation may be employed to reduce channels (e.g., by combining two or more channels via maximum feature selection within the channels). Depth-wise separable convolution may be employed for computation reduction (e.g., reduction of convolution computation). Batch normalization may be applied to normalize the output of the convolution layers and the fully connected layer (e.g., to prevent overfitting). The described techniques provide a compact and efficient CNN model which can be used for efficient and effective face recognition.

Abstract: A head-mounted display, a display control method, and a program that facilitate a user to understand proximity between the user and an object around the user are provided. A display block (36) is arranged in front of the eyes of the user wearing a HMD (12). In accordance with proximity between the user and an object around the user, the HMD (12) controls the display block (36) so as to have the user visually recognize a forward direction of the display block (36).