利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

11 条记录 (耗时 0.02 秒)

    Image Cropping Suggestion Using Multiple Saliency Maps
    1.
    发明申请
    Image Cropping Suggestion Using Multiple Saliency Maps 审中-公开

    公开(公告)号：US20170178291A1

    公开(公告)日：2017-06-22

    申请号：US15448138

    申请日：2017-03-02

    申请人： Adobe Systems Incorporated

    发明人： Zhe Lin ,  Radomir Mech ,  Xiaohui Shen ,  Brian L. Price ,  Jianming Zhang ,  Anant Gilra ,  Jen-Chan Jeff Chien

    IPC分类号： G06T3/40 ,  G06K9/46 ,  G06T11/60 ,  G06T3/00

    CPC分类号： G06T3/40 ,  G06K9/4671 ,  G06T3/0012 ,  G06T11/60 ,  G06T2210/22

    摘要： Image cropping suggestion using multiple saliency maps is described. In one or more implementations, component scores, indicative of visual characteristics established for visually-pleasing croppings, are computed for candidate image croppings using multiple different saliency maps. The visual characteristics on which a candidate image cropping is scored may be indicative of its composition quality, an extent to which it preserves content appearing in the scene, and a simplicity of its boundary. Based on the component scores, the croppings may be ranked with regard to each of the visual characteristics. The rankings may be used to cluster the candidate croppings into groups of similar croppings, such that croppings in a group are different by less than a threshold amount and croppings in different groups are different by at least the threshold amount. Based on the clustering, croppings may then be chosen, e.g., to present them to a user for selection.

    DIGITAL IMAGE BLEMISH REMOVAL
    2.
    发明申请
    DIGITAL IMAGE BLEMISH REMOVAL 有权

    公开(公告)号：US20170103502A1

    公开(公告)日：2017-04-13

    申请号：US15375525

    申请日：2016-12-12

    申请人： Adobe Systems Incorporated

    发明人： Anant Gilra

    IPC分类号： G06T5/00

    CPC分类号： G06T5/005 ,  G06F3/04842 ,  G06F3/04845 ,  G06T5/001 ,  G06T2207/10004 ,  G06T2207/20104

    摘要： Techniques are disclosed for removing blemishes from a digital image by detecting pixels containing the blemishes and replacing or blending those pixels with other pixels in the image that have a relatively low probability of containing a blemish. A standard pixel mask includes a user-selected region of the image; an extended mask extends beyond the user-selected region; and a minimal output pixel mask corresponds to the user-selected region. The minimal mask increases the transparency of some regions in the standard mask while maintaining the opacity of the standard mask in the blemish areas. Colors in the extended mask are weighted and clustered, and pixels in the minimal mask are assigned varying shades of transparency as a function of the color frequency. A blemish removal algorithm is applied using the minimal mask, with semi-transparent regions receiving a blend of source and patch pixel colors according to the level of transparency.

    Implementing out of order access to reversal operations in images
    5.
    发明授权
    Implementing out of order access to reversal operations in images 有权

    公开(公告)号：US09972109B2

    公开(公告)日：2018-05-15

    申请号：US14814273

    申请日：2015-07-30

    申请人： Adobe Systems Incorporated

    发明人： Anant Gilra

    IPC分类号： G06F3/0484 ,  G06T11/60

    CPC分类号： G06T11/60 ,  G06F3/04845 ,  G06F3/04847 ,  G06T2200/24

    摘要： A computing device is provided. The computing device includes a memory, at least one processor coupled to the memory and an action undo module executable by the processor. The action undo module is configured to receive user input requesting a target session of one or more sessions be undone. Each session of the one or more sessions includes at least one identifier of at least one tile that is affected by a respective action. The target session includes an identifier of a target action having affected one or more tiles identified in a collateral session of the one or more sessions. The collateral session includes an identifier of a collateral action. In one embodiment, the target session is lower in the first stack than the collateral session and the action undo module is configured to undo the collateral action and undo the target action.

    Digital image blemish removal
    6.
    发明授权
    Digital image blemish removal 有权

    公开(公告)号：US09886747B2

    公开(公告)日：2018-02-06

    申请号：US15375525

    申请日：2016-12-12

    申请人： Adobe Systems Incorporated

    发明人： Anant Gilra

    IPC分类号： G06K9/40 ,  G06T5/00

    CPC分类号： G06T5/005 ,  G06F3/04842 ,  G06F3/04845 ,  G06T5/001 ,  G06T2207/10004 ,  G06T2207/20104

    摘要： Techniques are disclosed for removing blemishes from a digital image by detecting pixels containing the blemishes and replacing or blending those pixels with other pixels in the image that have a relatively low probability of containing a blemish. A standard pixel mask includes a user-selected region of the image; an extended mask extends beyond the user-selected region; and a minimal output pixel mask corresponds to the user-selected region. The minimal mask increases the transparency of some regions in the standard mask while maintaining the opacity of the standard mask in the blemish areas. Colors in the extended mask are weighted and clustered, and pixels in the minimal mask are assigned varying shades of transparency as a function of the color frequency. A blemish removal algorithm is applied using the minimal mask, with semi-transparent regions receiving a blend of source and patch pixel colors according to the level of transparency.

    Concurrently Supporting Both Document-Based and Object-Based Undo Operations
    7.
    发明申请
    Concurrently Supporting Both Document-Based and Object-Based Undo Operations 审中-公开
    同时支持基于文档和基于对象的撤消操作

    公开(公告)号：US20160147721A1

    公开(公告)日：2016-05-26

    申请号：US14549952

    申请日：2014-11-21

    申请人： Adobe Systems Incorporated

    发明人： Anant Gilra

    IPC分类号： G06F17/24 ,  G06F17/21

    CPC分类号： G06F17/24

    摘要： During operation of a program, various different editing actions can be performed on data (e.g., image or video data) in a document. The data includes multiple objects, each of which is a user-selectable element of the data, such as a line, a shape, or a filter applied to the data. A record of actions taken on objects in the data is maintained, and the actions can be undone. A document-based undo operation can be performed, which undoes the last action performed in the document. An object-based undo can also be performed, which undoes the last action performed on a selected one or more objects in the document. A document-based redo operation can be performed, which redoes the last action undone in the document. An object-based redo can also be performed, which redoes the last action undone on a selected one or more objects in the document.

    摘要翻译： 在程序操作期间，可以对文档中的数据（例如，图像或视频数据）执行各种不同的编辑动作。 数据包括多个对象，每个对象是用户可选择的数据元素，例如应用于数据的行，形状或过滤器。 保留对数据中对象执行的操作的记录，并且可以撤消操作。 可以执行基于文档的撤消操作，撤销文档中执行的最后一个操作。 还可以执行基于对象的撤销，这将撤消对文档中所选一个或多个对象执行的最后一个操作。 可以执行基于文档的重做操作，该操作会重新取消文档中撤消的最后一个操作。 也可以执行基于对象的重做，该操作会重新取消文档中所选一个或多个对象上的最后一个操作。

    Image Cropping Suggestion Using Multiple Saliency Maps
    8.
    发明申请
    Image Cropping Suggestion Using Multiple Saliency Maps 有权
    使用多重显着图的图像裁剪建议

    公开(公告)号：US20160104055A1

    公开(公告)日：2016-04-14

    申请号：US14511001

    申请日：2014-10-09

    申请人： Adobe Systems Incorporated

    发明人： Zhe Lin ,  Radomir Mech ,  Xiaohui Shen ,  Brian L. Price ,  Jianming Zhang ,  Anant Gilra ,  Jen-Chan Jeff Chien

    IPC分类号： G06K9/46 ,  G06T3/40

    CPC分类号： G06T3/40 ,  G06K9/4671 ,  G06T3/0012 ,  G06T11/60 ,  G06T2210/22

    摘要： Image cropping suggestion using multiple saliency maps is described. In one or more implementations, component scores, indicative of visual characteristics established for visually-pleasing croppings, are computed for candidate image croppings using multiple different saliency maps. The visual characteristics on which a candidate image cropping is scored may be indicative of its composition quality, an extent to which it preserves content appearing in the scene, and a simplicity of its boundary. Based on the component scores, the croppings may be ranked with regard to each of the visual characteristics. The rankings may be used to cluster the candidate croppings into groups of similar croppings, such that croppings in a group are different by less than a threshold amount and croppings in different groups are different by at least the threshold amount. Based on the clustering, croppings may then be chosen, e.g., to present them to a user for selection.

    摘要翻译： 描述了使用多个显着图的图像裁剪建议。 在一个或多个实现中，针对使用多个不同显着图的候选图像裁剪计算指示为视觉上令人满意的裁剪而建立的视觉特征的分数分数。 评估候选图像裁剪的视觉特征可以指示其组成质量，其保存出现在场景中的内容的程度以及其边界的简单性。 基于分量分数，可以根据每个视觉特征来排列裁剪。 排名可以用于将候选作物聚类成类似的作物的组，使得组中的作物差异小于阈值量，并且不同组中的剪切至少达到阈值量。 基于聚类，可以选择裁剪，例如将其呈现给用户进行选择。

    Image cropping suggestion using multiple saliency maps
    9.
    发明授权
    Image cropping suggestion using multiple saliency maps 有权

    公开(公告)号：US09626584B2

    公开(公告)日：2017-04-18

    申请号：US14511001

    申请日：2014-10-09

    申请人： Adobe Systems Incorporated

    发明人： Zhe Lin ,  Radomir Mech ,  Xiaohui Shen ,  Brian L. Price ,  Jianming Zhang ,  Anant Gilra ,  Jen-Chan Jeff Chien

    IPC分类号： G06K9/34 ,  G06K9/46 ,  G06T3/00

    CPC分类号： G06T3/40 ,  G06K9/4671 ,  G06T3/0012 ,  G06T11/60 ,  G06T2210/22

    摘要： Image cropping suggestion using multiple saliency maps is described. In one or more implementations, component scores, indicative of visual characteristics established for visually-pleasing croppings, are computed for candidate image croppings using multiple different saliency maps. The visual characteristics on which a candidate image cropping is scored may be indicative of its composition quality, an extent to which it preserves content appearing in the scene, and a simplicity of its boundary. Based on the component scores, the croppings may be ranked with regard to each of the visual characteristics. The rankings may be used to cluster the candidate croppings into groups of similar croppings, such that croppings in a group are different by less than a threshold amount and croppings in different groups are different by at least the threshold amount. Based on the clustering, croppings may then be chosen, e.g., to present them to a user for selection.

    Digital image blemish removal
    10.
    发明授权
    Digital image blemish removal 有权
    数字图像瑕疵去除

    公开(公告)号：US09552626B1

    公开(公告)日：2017-01-24

    申请号：US14877238

    申请日：2015-10-07

    申请人： Adobe Systems Incorporated

    发明人： Anant Gilra

    IPC分类号： G06K9/40 ,  G06T5/00 ,  G06F3/0484

    CPC分类号： G06T5/005 ,  G06F3/04842 ,  G06F3/04845 ,  G06T5/001 ,  G06T2207/10004 ,  G06T2207/20104

    摘要： Techniques are disclosed for removing blemishes from a digital image by detecting pixels containing the blemishes and replacing or blending those pixels with other pixels in the image that have a relatively low probability of containing a blemish. A standard pixel mask includes a user-selected region of the image; an extended mask extends beyond the user-selected region; and a minimal output pixel mask corresponds to the user-selected region. The minimal mask increases the transparency of some regions in the standard mask while maintaining the opacity of the standard mask in the blemish areas. Colors in the extended mask are weighted and clustered, and pixels in the minimal mask are assigned varying shades of transparency as a function of the color frequency. A blemish removal algorithm is applied using the minimal mask, with semi-transparent regions receiving a blend of source and patch pixel colors according to the level of transparency.

    摘要翻译： 公开了用于通过检测包含瑕疵的像素并且将这些像素与图像中具有相对较低的含有瑕疵概率的其他像素进行替换或混合来从数字图像中去除瑕疵的技术。 标准像素掩模包括图像的用户选择区域; 扩展掩模延伸超出用户选择的区域; 并且最小输出像素掩码对应于用户选择的区域。 最小面罩增加了标准面罩中某些区域的透明度，同时保持了瑕疵区域中标准面罩的不透明度。 扩展掩模中的颜色被加权和聚类，并且最小掩模中的像素被赋予作为颜色频率的函数的透明度的变化阴影。 使用最小掩模应用瑕疵删除算法，半透明区域根据透明度水平接收源和补丁像素颜色的混合。