Abstract: Apparatuses, systems, and techniques to perform non-maximum suppression (NMS) with a bit-reduced radix sort to remove redundant bounding boxes are described. In at least one embodiment, one or more circuits perform i) a bit-reduced radix sort operation to sort a list of confidence scores associated with a set of bounding boxes corresponding to one or more objects within one or more digital images and ii) a non-maximum suppression (NMS) operation on the sorted list to remove one or more redundant bounding boxes from the set.

Abstract: Disclosed are an information processing method and a terminal device. The method comprises: acquiring first information, wherein the first information is information to be processed by a terminal device; calling an operation instruction in a calculation apparatus to calculate the first information so as to obtain second information; and outputting the second information. By means of the examples in the present disclosure, a calculation apparatus of a terminal device can be used to call an operation instruction to process first information, so as to output second information of a target desired by a user, thereby improving the information processing efficiency. The present technical solution has advantages of a fast computation speed and high efficiency.

Abstract: The invention relates to method and system for automatically generating and labelling reference images. In some embodiments, the method includes tracking a plurality of highlighted objects in a set of input images along with audio data associated with the plurality of highlighted objects. The method further includes cropping each of the plurality of highlighted objects from each of the set of images based on tracking, contemporaneously capturing an audio clip associated with each of the plurality of highlighted objects from the audio data based on tracking, and labelling each of the plurality of highlighted objects based on text data generated from the audio clip associated with each of the plurality of objects to generate a labelled reference image.

Abstract: A human detection device configured to analyze a fisheye image obtained by a fisheye camera installed above a to-be-detected area to detect a person existing in the to-be-detected area includes a head detector configured to detect at least one head candidate from the fisheye image by using an algorithm for detecting a human head, a human body detector configured to detect at least one human body candidate from the fisheye image by using an algorithm for detecting a human body, and a determining unit configured to determine, as a person, a pair satisfying a prescribed condition among pairs of the head candidate and the human body candidate formed of a combination of a detection result from the head detector and a detection result from the human body detector.

Abstract: Embodiments for determining an orientation of a scanned image. In an exemplary embodiment, a method comprises receiving image data of an image of one or more objects. Each object of the one or more objects in the image includes a plurality of points on a surface of the object. The method further comprises generating a plurality of subsets of points of the plurality of points and fitting a parametric model to more than one subset of the plurality of subsets to generate a plurality of parametric models. Further, the method identifies a parametric model of the plurality of parametric models that includes the largest number of points and orients the image based on the parametric model that includes the largest number of points.

Abstract: This application provides a face living body detection method performed by a computing device, the method including: obtaining a first face image of a target detection object in a first illumination condition and a second face image of the target detection object in a second illumination condition, determining a difference image according to the two images, decoupling an object reflectivity and an object normal vector corresponding to the target detection object from a feature map extracted from the difference image, and determining whether the target detection object is a living body according to the object reflectivity and the object normal vector. This method decouples texture information and depth information of a face, and performs living body detection by using decoupled information, which increases the defense capability against 3D attacks, thereby effectively defending against planar attacks and 3D attacks.

Abstract: A foreign matter inspection system that is less likely to misidentify a crack as a foreign matter during an image inspection in which a vibration is applied to a powder contained in a bag-like container. The foreign matter inspection system includes a vibration device configured to apply a vibration to a container, a photography device configured to optically photograph the inside of the container through a transparent area, and a determination device configured to determine whether a foreign matter is present inside the container based on an image of the container photographed by the photography device. The vibration device alternately applies weak vibrations W and strong vibrations S to the container. The determination device determines whether the foreign matter is present inside the container based on the image of the container photographed by the photography device when the vibration device applies the weak vibrations W.

Abstract: A difference detection device includes a difference detection unit configured to, based on association among a first image and a second image captured at different times and illustrating a substantially identical space and encoding information of each of the first image and the second image, detect difference between a third image and a fourth image captured at different times and illustrating a substantially identical space, and the encoding information is information acquired from data including the first image encoded and data including the second image encoded, before inverse transform processing is executed in decoding processing executed on each of the first image and the second image.

Abstract: An image acquisition unit acquires a plurality of projection images corresponding to a plurality of radiation source positions in a case of tomosynthesis imaging. A reconstruction unit reconstructs all or a part of the plurality of projection images to generate a tomographic image on each of a plurality of tomographic planes of a subject. A feature point detecting unit detects at least one feature point from a plurality of the tomographic images. A positional shift amount derivation unit derives a positional shift amount between the plurality of projection images with the feature point as a reference on a corresponding tomographic plane corresponding to the tomographic image in which the feature point is detected. The reconstruction unit reconstructs the plurality of projection images by correcting the positional shift amount to generate a corrected tomographic image.

Abstract: The system for the qualitative evaluation of human organs includes: a camera (101) for capturing an image of the organ, the organ being in the donor's body or already collected or placed in a hypothermic, normothermic and/or subnormothermic graft infusion machine at the time of image capture; an image processor (103, 104) configured to extract at least a portion of the organ image from the captured image and an estimator (103, 104) for estimating, from the extracted image, the health of the organ. In some embodiments, the device also includes a means of introducing into the donor's body at least one optical window of the image capture means as well as a light source to illuminate the donor's organ, while maintaining the sterility of the surgical field. In some embodiments, the image processor involves applying a clipping mask to the captured image.

Abstract: A method includes receiving patient health data; determining a score using a trained machine learning model; determining a threshold value using an adaptive threshold tuning learning model; comparing the score to the threshold value; and generating an alarm. A computing system includes a processor; and a memory having stored thereon instructions that, when executed by the processor, cause the computing system to: receive patient health data; determine a score using a trained machine learning model; determine a threshold value using an adaptive threshold tuning learning model; compare the score to the threshold value; and generate an alarm. A non-transitory computer readable medium includes program instructions that when executed, cause a computer to: receive patient health data; determine a score using a trained machine learning model; determine a threshold value using an adaptive threshold tuning learning model; compare the score to the threshold value; and generate an alarm.

Abstract: An eye detecting device is configured to: acquire a color image including a face of a person taken by an image taking device; generate a grayscale image by multiplying each of a red component value, a green component value, and a blue component value of each pixel of the color image by a predetermined ratio according to characteristics of a lens of glasses that the person wears; detect an eye of the person from the grayscale image; and output eye information on the eye of the person.

Abstract: A vehicle and control method of the vehicle are provided. The vehicle includes a camera provided on the vehicle and configured to capture an image of an object outside the vehicle, a controller configured to determine a photographing position required for facial recognition from the captured image, a guide configured to guide the photographing position, and a display configured to display a result of the facial recognition.

Abstract: An image pre-processing method and an image processing apparatus for a fundoscopic image are provided. A region of interest (ROI) is obtained from a fundoscopic image to generate a first image. The ROI is focused on an eyeball in the fundoscopic image. A smoothing process is performed on the first image to generate a second image. A value difference between neighboring pixels in the second image is increased to generate a third image.

Abstract: In some embodiments, an apparatus includes a memory and a processor. The processor is configured to extract a set of features from a potentially malicious file and provide the set of features as an input to a normalization layer of a neural network. The processor is configured to implement the normalization layer by calculating a set of parameters associated with the set of features and normalizing the set of features based on the set of parameters to define a set of normalized features. The processor is further configured to provide the set of normalized features and the set of parameters as inputs to an activation layer of the neural network such that the activation layer produces an output based on the set of normalized features and the set of parameters. The output can be used to produce a maliciousness classification of the potentially malicious file.

Abstract: A context-based object classifying model is applied to a set of object location representations (12, 14), derived from an object detection applied to a frame (10) of a video stream, to obtain a context-adapted classification probability for each object location representation (12, 14). Each object location representation (12, 14) defines a region of the frame (10) and each context-adapted classification probability represents a likelihood that the region comprises an object (11, 13). The model is generated based on object location representations from previous frames of the video stream. It is determined whether the region defined by the object location representation (12, 14) comprises an object (11, 13) based on the context-adapted classification probability and a detection probability. The detection probability is derived from the object detection and represents a likelihood that the region defined by the object location representation (12, 14) comprises an object (11, 13).

Abstract: The present disclosure relates to systems and methods for image processing. The methods may include obtaining imaging data of a subject, generating a first image based on the imaging data, and generating at least two intermediate images based on the first image. At least one of the at least two intermediate images may be generated based on a machine learning model. And the at least two intermediate images may include a first intermediate image and a second intermediate image. The first intermediate image may include feature information of the first image, and the second intermediate image may have lower noise than the first image. The methods may further include generating, based on the first intermediate image and at least one of the first image or the second intermediate image, a target image of the subject.

Abstract: A system and method for learning human activities from video demonstrations using video augmentation is disclosed. The method includes receiving original videos from one or more data sources. The method includes processing the received original videos using one or more video augmentation techniques to generate a set of augmented videos. Further, the method includes generating a set of training videos by combining the received original videos with the generated set of augmented videos. Also, the method includes generating a deep learning model for the received original videos based on the generated set of training videos. Further, the method includes learning the one or more human activities performed in the received original videos by deploying the generated deep learning model. The method includes outputting the learnt one or more human activities performed in the original videos.

Abstract: Methods and systems include receiving, at de-ringing circuitry of a display pipeline of an electronic device, scaled image content based on image data. The de-ringing circuitry also receives a fallback scaler output. The de-ringing circuitry determines whether the image data has a change frequency greater than a threshold. In response to the change frequency being above the threshold, the de-ringing circuitry determines a weight. Based at least in part on the weight, the de-ringing circuitry blends the scaled image content and the fallback scaler output based at least in part on the weight.

Abstract: The present teaching relates to method, system, medium, and implementations for detecting liveness. When an image is received with visual information claimed to represent a palm of a person, a region of interests (ROI) in the image that corresponds to the palm is identified. Each of a plurality of fake palm detectors individually generates an individual decision on whether the ROI corresponds to a specific type of fake palm that the fake palm detector is to detect. Such individual decisions from the plurality of fake palm detectors are combined to derive a liveness detection decision with respect to the ROI.