Image aesthetic processing method and electronic device

    公开(公告)号:US11314988B2

    公开(公告)日:2022-04-26

    申请号:US16771063

    申请日:2018-03-26

    Abstract: This application provides an image aesthetic processing method and an electronic device. A method for generating an image aesthetic scoring model includes: constructing a first neural network based on a preset convolutional structure set; obtaining an image classification neural network, where the image classification neural network is used to classify image scenarios; obtaining a second neural network based on the first neural network and the image classification neural network, where the second neural network is a neural network containing scenario information; and determining an image aesthetic scoring model based on the second neural network, where output information of the image aesthetic scoring model includes image scenario classification information. In this method, scenario information is integrated into a backbone neural network, so that a resulting image aesthetic scoring model is interpretable. In addition, scoring accuracy of the image aesthetic scoring model can be improved by using the preset convolutional structure set.

    SECURITY CONTROL METHOD AND COMPUTER SYSTEM
    3.
    发明申请

    公开(公告)号:US20200250302A1

    公开(公告)日:2020-08-06

    申请号:US16838935

    申请日:2020-04-02

    Abstract: This application provides a security control method and a computer system. A first domain and a second domain are deployed in the computer system, the second domain is more secure than the first domain, a program is deployed in the first domain, and a control flow management module and an audit module are deployed in the second domain. The second domain is more secure than the first domain. When the program in the first domain is executed, the control flow management module obtains control flow information by using a tracer. The audit module audits the to-be-audited information according to an audit rule, and when the to-be-audited information matches the audit rule, determines that the audit succeeds and then allows the first domain to perform a subsequent operation, for example, to access a secure program in the second domain.

    IMAGE AESTHETIC PROCESSING METHOD AND ELECTRONIC DEVICE

    公开(公告)号:US20210182613A1

    公开(公告)日:2021-06-17

    申请号:US16771063

    申请日:2018-03-26

    Abstract: This application provides an image aesthetic processing method and an electronic device. A method for generating an image aesthetic scoring model includes: constructing a first neural network based on a preset convolutional structure set; obtaining an image classification neural network, where the image classification neural network is used to classify image scenarios; obtaining a second neural network based on the first neural network and the image classification neural network, where the second neural network is a neural network containing scenario information; and determining an image aesthetic scoring model based on the second neural network, where output information of the image aesthetic scoring model includes image scenario classification information. In this method, scenario information is integrated into a backbone neural network, so that a resulting image aesthetic scoring model is interpretable. In addition, scoring accuracy of the image aesthetic scoring model can be improved by using the preset convolutional structure set.

    Text Recognition Method and Terminal Device

    公开(公告)号:US20210326655A1

    公开(公告)日:2021-10-21

    申请号:US17361746

    申请日:2021-06-29

    Abstract: A text recognition method includes scaling a to-be-recognized image based on a first scale ratio, determining first coordinate information corresponding to a text line area in the scaled to-be-recognized image, determining, based on the first scale ratio, second coordinate information corresponding to the first coordinate information, where the second coordinate information is coordinate information of the text line area in the to-be-recognized image, performing character recognition on text line images corresponding to the second coordinate information by using a recognition model, and determining text line content corresponding to the text line images, where the to-be-recognized image includes the text line images.

Patent Agency Ranking