A method for detecting an object in a first distorted image using a sliding window algorithm, comprising: receiving an inverse of a mathematical representation of a distortion of the first distorted image; wherein the detection of an object comprises sliding a sliding window over the first distorted image, the sliding window comprising a feature detection pattern, and for each position of a plurality of positions in the first distorted image: transforming the sliding window based on the inverse of the mathematical representation of the distortion at the position, wherein the step of transforming the sliding window comprises transforming the feature detection pattern of the sliding window such that a resulting distortion of the feature detection pattern of the transformed sliding window corresponds to the distortion of the first distorted image at the position; and using the transformed sliding window comprising the transformed feature detection pattern in the sliding window algorithm.

A face authentication apparatus includes a face image acquisition unit that acquires a face image of a user who passes through a first gate provided at a first boundary between zones, a collation unit that performs face authentication on the face image on the basis of a threshold, an operating state acquisition unit that acquires an operating state of a second gate provided at a second boundary that is different from the first boundary, and a threshold change unit that changes the threshold on the basis of the operating state of the second gate.

Techniques for generating magnetic resonance (MR) images of a subject from MR data obtained by a magnetic resonance imaging (MRI) system, the techniques including: obtaining input MR data obtained by imaging the subject using the MRI system; generating a plurality of transformed input MR data instances by applying a respective first plurality of transformations to the input MR data; generating a plurality of MR images from the plurality of transformed input MR data instances and the input MR data using a non-linear MR image reconstruction technique; generating an ensembled MR image from the plurality of MR images at least in part by: applying a second plurality of transformations to the plurality of MR images to obtain a plurality of transformed MR images; and combining the plurality of transformed MR images to obtain the ensembled MR image; and outputting the ensembled MR image.

An analysis method of lane stripe images, an image analysis device and a non-transitory computer readable medium thereof are provided to perform steps of: setting a reference point as a center to recognize the lane stripe image in a plurality of default directions; defining a plurality of preset sections onto the lane stripe image and determining a characteristic value of the lane stripe image in each of the preset sections whenever the lane stripe image is recognized in one of the default directions; determining a first feature parameter according to the characteristic values of the lane stripe image in the preset sections when the lane stripe image is recognized in at least one of the default directions; and determining an actual lane parameter of the lane stripe image according to at least the first feature parameter.

Provided is an object detection method using template matching. The method includes a step of specifying a template image of an object that is to be detected in an input image and generating a descriptor of the specified template image, an image pyramid generation step of converting a scale of the input image and generating image patches, a step of determining a rotation angle of the input image, a step of generating a descriptor of the generated image patches based on the determined rotation angle, and a step of matching the descriptor of the specified template image and the descriptor of the generated image patches, thus detecting the object that is to be detected. Therefore, it is possible to detect an object in real time without being limited by the size, angle, type, etc. of the object that is to be detected.

A mechanism for radiation detection is disclosed. An integrated circuit usable in detecting radiation includes a plurality of readout circuits is described. A readout circuit of the plurality of readout circuits includes an integration capacitor and an averaging capacitor. The integration capacitor is coupled with a pixel of a photodetector pixel array. The pixel has a pixel area. An available area less than the pixel area is usable for layout of the integration capacitor. The integration capacitor has a capacitor area less than the available area. The averaging capacitor has an averaging capacitance greater than the integration capacitance of the integration capacitor. In some aspects, the integrated circuit further includes at least one cascaded averaging circuit coupled with the averaging capacitor.

The tooth type judgment program includes, extracting point groups indicating a surface of three-dimensional profile data from inputted three-dimensional profile data; moving and/or rotating the three-dimensional profile data of a tooth corresponding to a specific type of tooth; calculating an arrangement relationship in which an error between a point group included in any of a region of the extracted point groups and the three-dimensional profile data of the tooth becomes minimum, and estimating a direction of the tooth included in the region based on the calculated arrangement relationship.

The present invention discloses a depth sensing method, device and system based on symbols array plane structured light. The coded symbols array pattern is projected by the laser pattern projector to the target object or space, and the image sensor collects and obtains the successive sequence of the encoded image of the input symbols. Firstly, the input image encoded with the symbols is decoded. The decoding process includes preprocessing, symbols location, symbols recognition and symbols correction. Secondly, the disparity of the decoded symbols are calculated by the symbols match calculation between the decoded image of the input symbols with completed symbols recognition and the decoded image of the reference symbols with the known distance. Finally the depth calculation formula is combined to generate depth point cloud information of the target object or projection space that is represented in the form of grid. The present invention can quickly obtain high-resolution and high-precision depth information of the target object or projection space in dynamic scenes, which facilitates the porting or insertion as a module into the intelligent device for 3D modeling, 3D mapping, etc.

A digital recording device is configured to automatically capture digital images. In the digital recording device, a camera module operating in a live preview mode generates a video stream comprising digital images. A content analyzer generates a trigger signal based on an initial image-capturing template. The camera module captures and stores digital images responsive to receiving the trigger signal. A user interface component receives from a user one or more selections among the stored digital images, a template adjuster adjusts at least one target pose specified by the image-capturing template based on the one or more user selections, wherein the content analyzer generates the trigger signal based on the adjusted image-capturing template.

A method for generating object and part detectors includes accessing a collection of training images. The collection of training images includes images annotated with an object label and images annotated with a respective part label for each of a plurality of parts of the object. Joint appearance-geometric embeddings for regions of a set of the training images are generated. At least one detector for the object and its parts is learnt using annotations of the training images and respective joint appearance-geometric embeddings, e.g., using multi-instance learning for generating parameters of scoring functions which are used to identify high scoring regions for learning the object and its parts. The detectors may be output or used to label regions of a new image with object and part labels.