Generating more realistic synthetic data with adversarial nets

    公开(公告)号:US11475276B1

    公开(公告)日:2022-10-18

    申请号:US15804900

    申请日:2017-11-06

    申请人: Apple Inc.

    IPC分类号: G06N3/04 G06N3/08 G06K9/62

    摘要: A generative network may be learned in an adversarial setting with a goal of modifying synthetic data such that a discriminative network may not be able to reliably tell the difference between refined synthetic data and real data. The generative network and discriminative network may work together to learn how to produce more realistic synthetic data with reduced computational cost. The generative network may iteratively learn a function that synthetic data with a goal of generating refined synthetic data that is more difficult for the discriminative network to differentiate from real data, while the discriminative network may be configured to iteratively learn a function that classifies data as either synthetic or real. Over multiple iterations, the generative network may learn to refine the synthetic data to produce refined synthetic data on which other machine learning models may be trained.

    Interactive Reading Assistant
    3.
    发明申请

    公开(公告)号:US20200312183A1

    公开(公告)日:2020-10-01

    申请号:US16798820

    申请日:2020-02-24

    申请人: Apple Inc.

    摘要: A method includes displaying a first set of text content characterized by a first difficulty level. The method includes obtaining speech data associated with the first set of text content. The method includes determining linguistic feature(s) within the speech data. The method includes in response to completion of the speech data, determining a reading proficiency value associated with the first set of text content and based on the linguistic feature(s). The method includes in accordance with determining the reading proficiency value satisfies change criteria, changing a difficulty level for a second set of text content. After changing the difficulty level, the second set of text content corresponds to a second difficulty level different from the first difficulty level. The method includes in accordance with determining the reading proficiency value does not satisfy the change criteria, maintaining the second set of text content at the first difficulty level.

    Grain generation and blending
    4.
    发明授权

    公开(公告)号:US09652867B2

    公开(公告)日:2017-05-16

    申请号:US14058097

    申请日:2013-10-18

    申请人: Apple Inc.

    IPC分类号: G06T11/00 G06F3/0484 G06T5/00

    摘要: A method and system for providing a dynamic grain effect tool for a media-editing application that generates a grain effect and applies the grain effect to a digital image. The application first generates a random pixel field for the image based on a seed value. The application then generates a film grain pattern for the image by consecutively applying a blurring function and an unsharp masking function, based on an ISO value, to the randomly generated pixel field. The application then blends the grain field with the original image by adjusting each pixel based on the value of the corresponding pixel location in the grain field. The application then adjusts the grain amount in the previously generated full-grain image by receiving a grain amount value from a user and applying this value to the full-grain image.

    CONTROLLING MULTIPLE PHOTOGRAPHIC ADJUSTMENTS WITH A SINGLE CONTROL
    5.
    发明申请
    CONTROLLING MULTIPLE PHOTOGRAPHIC ADJUSTMENTS WITH A SINGLE CONTROL 有权
    控制多个摄影调整与一个单一的控制

    公开(公告)号:US20150347858A1

    公开(公告)日:2015-12-03

    申请号:US14292921

    申请日:2014-06-01

    申请人: Apple Inc.

    IPC分类号: G06K9/03 G06T11/60 G06T5/00

    摘要: A method and system for controlling multiple image editing controls using one master control. The system identifies various characteristics of an image being edited. The system generates, for each of multiple image editing controls, a relationship between the master control and the image editing control. The relationship is based on at least one of the identified characteristics of the image being edited. The relationship is different for different images when the different images have different characteristics, such as different average color component values at a particular percentile of pixels in the images.

    摘要翻译: 一种用于使用一个主控制来控制多个图像编辑控制的方法和系统。 系统识别正在编辑的图像的各种特征。 对于多个图像编辑控件中的每一个,系统产生主控制和图像编辑控制之间的关系。 该关系基于所编辑的图像的识别特征中的至少一个。 当不同的图像具有不同的特征,例如图像中特定百分位数的不同平均颜色分量值时,不同图像的关系是不同的。

    UNIFIED SLIDER CONTROL FOR MODIFYING MULTIPLE IMAGE PROPERTIES
    6.
    发明申请
    UNIFIED SLIDER CONTROL FOR MODIFYING MULTIPLE IMAGE PROPERTIES 审中-公开
    用于修改多个图像特性的统一滑块控制

    公开(公告)号:US20150331595A1

    公开(公告)日:2015-11-19

    申请号:US14809126

    申请日:2015-07-24

    申请人: Apple Inc.

    摘要: Some embodiments provide a novel user interface (UI) tool that is a unified slider control, which includes multiple sliders that slide along a region. The region is a straight line in some embodiments, while it is an angular arc in other embodiments. In some embodiments, the unified slider control is used in a media editing application to allow a user to modify several different properties of the image by moving several different sliders along the region. Each slider is associated with a property of the image. A position of the slider in the region corresponds to a value of the property associated with the slider.

    摘要翻译: 一些实施例提供了一种新颖的用户界面(UI)工具,其是统一的滑块控件,其包括沿着区域滑动的多个滑块。 在一些实施例中,该区域是直线,而在其他实施例中该区域是一个角弧。 在一些实施例中,在媒体编辑应用中使用统一滑块控件,以允许用户通过沿着该区域移动若干不同的滑块来修改图像的若干不同属性。 每个滑块与图像的属性相关联。 滑块在该区域中的位置对应于与滑块相关联的属性的值。

    Gray color balance tools for editing images
    7.
    发明授权
    Gray color balance tools for editing images 有权
    用于编辑图像的灰色平衡工具

    公开(公告)号:US09099024B2

    公开(公告)日:2015-08-04

    申请号:US13629496

    申请日:2012-09-27

    申请人: Apple Inc.

    IPC分类号: G09G5/02

    摘要: Some embodiments provide a method that provides a graphical user interface (GUI) for color balancing an image. The method provides a display area for displaying the image. The method provides several color balance modes. The method provides a user interface (UI) control associated with a color balance mode in the several color balance modes. The UI control performs a color balance operation on the image by (1) identifying a color cast in the image and (2) modifying pixels in the image based on the pixels' luminance values in order to reduce the color cast in the image.

    摘要翻译: 一些实施例提供了一种提供用于颜色平衡图像的图形用户界面(GUI)的方法。 该方法提供用于显示图像的显示区域。 该方法提供多种色彩平衡模式。 该方法提供与几种颜色平衡模式中的颜色平衡模式相关联的用户界面(UI)控制。 UI控件通过(1)识别图像中的颜色投影和(2)基于像素的亮度值来修改图像中的像素来对图像执行颜色平衡操作,以减少图像中的投影。

    TEMPERED AUTO-ADJUSTING, IMAGE-EDITING OPERATION
    8.
    发明申请
    TEMPERED AUTO-ADJUSTING, IMAGE-EDITING OPERATION 有权
    温度自动调节,图像编辑操作

    公开(公告)号:US20130332866A1

    公开(公告)日:2013-12-12

    申请号:US13629504

    申请日:2012-09-27

    申请人: APPLE INC.

    IPC分类号: G06K9/40 G06F3/048

    摘要: Some embodiments provide a novel method for tempering an adjustment of an image to account for prior adjustments to the image. The adjustment in some embodiments is an automatic exposure adjustment. The method performs an operation for a first adjustment on a first set of parameters (e.g., saturation, sharpness, luminance). The method compares the first set of parameters to a second set of parameters to produce a third set of parameters that expresses the difference between the first adjustment and a second adjustment. The method performs a third operation to produce an adjusted image. The first set of parameters quantify a set of prior adjustments to the image by an image capturing device when the image was captured in some embodiments. The second set of parameters is a set of target parameters. The third set of parameters specify the tempered adjustment of the image.

    摘要翻译: 一些实施例提供了一种用于回火图像调整以考虑对图像的先前调整的新颖方法。 一些实施例中的调整是自动曝光调整。 该方法执行用于对第一组参数(例如,饱和度,锐度,亮度)的第一调整的操作。 该方法将第一组参数与第二组参数进行比较,以产生表示第一调整和第二调整之间的差的第三组参数。 该方法执行第三操作以产生调整图像。 当在一些实施例中拍摄图像时,第一组参数量化由图像捕获装置对图像进行的一组先前的调整。 第二组参数是一组目标参数。 第三组参数指定图像的温和调整。