摘要:
Various technologies described herein pertain to performing video analytics. The approaches set forth herein support live video analytics at scale with approximate and delay-tolerant processing. Video streams can be captured by multiple cameras and continuously streamed to a video analytics computing system; the video streams can be received at the video analytics computing system. Multiple video analytics queries can be executed on the video streams. The multiple video analytics queries can be concurrently executed by the video analytics computing system on the video streams as the video streams are continuously streamed to the video analytics computing system. The multiple video analytics queries can be executed utilizing resources of the video analytics computing system allocated between the multiple video analytics queries. Execution of the multiple video analytics queries can return respective results for the multiple video analytics queries. The results for the multiple video analytics queries can be outputted.
摘要:
A method to determine whether a user is experiencing difficulty visually resolving content is disclosed. The method includes capturing one or more images of the user while the user is viewing the content. The method also includes obtaining facial parameters related to a visual acuity of the user from the captured one or more images. The method further includes determining whether the user is experiencing difficulty visually resolving the content based on the obtained one or more facial parameters. The method is implemented in a device such as a smartphone, tablet computer, or television. The facial parameters include information about the extent to which the user has their eyes open or closed, whether the user is wearing glasses, and the distance at which the user is viewing the content.
摘要:
Techniques for increasing robustness of a convolutional neural network based on training that uses multiple datasets and multiple tasks are described. For example, a computer system trains the convolutional neural network across multiple datasets and multiple tasks. The convolutional neural network is configured for learning features from images and accordingly generating feature vectors. By using multiple datasets and multiple tasks, the robustness of the convolutional neural network is increased. A feature vector of an image is used to apply an image-related operation to the image. For example, the image is classified, indexed, or objects in the image are tagged based on the feature vector. Because the robustness is increased, the accuracy of the generating feature vectors is also increased. Hence, the overall quality of an image service is enhanced, where the image service relies on the image-related operation.
摘要:
The present disclosure discloses a method and a terminal device for processing an image. The method includes: acquiring an image; recognizing a face contained in the image; acquiring information of character features according to the face in the image; processing the image according to the information of character features; and obtaining the processed image. In the embodiments of the present disclosure, by automatically recognizing the face in the image, and acquiring the information of character features thereby acquiring a cosmetic process mode corresponding to the information of character features, and then processing the image according to the selected cosmetic process mode, manual setting of cosmetic process parameters can be avoided and the efficiency of image processing can be improved.
摘要:
A facial recognition system determines an estimated biological age of a subject in a current image. A facial recognition controller identifies the subject in the current image using a number of historical images, at least one of which includes the subject and a logically associated identifier. The system compares the estimated biological age of the subject to a defined threshold value. The system determines a temporal difference between a time/date logically associated with the current image and a time/date logically associated with the historical image. If the estimated biological age of the subject in the current image is less than a defined age threshold and the temporal difference between the time/date logically associated with the current image and a time/date logically associated with the historical image is less than a temporal threshold, the identifier logically associated with the historical image is logically associated with the current image.
摘要:
A content output apparatus includes: a detector for detecting a user; an extractor for extracting a feature of the user detected by the detector; and a controller for controlling a reproduction speed of content to be output to a display, based on the feature extracted by the extractor.
摘要:
An image processing apparatus including an acquisition unit configured to acquire results of analysis processing for a plurality of images; a designation unit configured to designate a type of a target to be detected from an image; and a determination unit configured to determine, among the plurality of images, an image used for detection processing of the detection target designated by the designation unit based on the type of the detection target designated by the designation unit and the result of the analysis processing.
摘要:
An electronic apparatus is provided. The electronic apparatus includes an input comprising input circuitry configured to receive an image and a processor configured to detect a skin area from the image to acquire information on a pixel value of a pixel included in the skin area, to acquire information on characteristics of the skin area based on a face area in the skin area, and to process image quality of the skin area based on the information on the pixel value and the information on the characteristics of the skin area. As a result, it is possible to reduce the image distortion of the skin area occurring when only the analysis of the quantitative elements is performed and to improve the image quality preference of the skin area based on the analysis of the qualitative elements in addition to the quantitative elements.
摘要:
Disclosed are a grading-based program playing method based on face recognition and an electronic device. The method includes: detecting a program on-demand instruction input by a user, enabling a face recognition function to collect a face image of the current user, and generating age data according to the face image of the current user; determining a program corresponding to the program on-demand instruction, calling predetermined grading-based playing settings, and acquiring an age data interval corresponding to the program; and judging whether the age data falls within the age data interval, if the age data falls within the age data interval, normally playing the program, and otherwise, not playing the program and sending a prompt to the user. According to the embodiments of the present disclosure, a simple and highly-efficient grading control-based program playing effect is achieved.
摘要:
According to an embodiment, a display control device includes hardware processing circuitry. The hardware processing circuitry programmed to acquire event information indicating an event and event position information indicating a location of the event, the event detected from an image captured by an imager; calculate a priority for displaying the event information based on at least one of the event position information or the event information; determine a display format of the event information based at least in part on the priority; and cause a display to display the event information in accordance with the display format determined.