公开(公告)号：US20160148352A1

公开(公告)日：2016-05-26

申请号：US14550808

申请日：2014-11-21

Applicant: Adobe Systems Incorporated

Inventor： Zhe Lin ,  Byungmoon Kim ,  Yuan Gao

IPC: G06T5/00 ,  G06F3/041

CPC classification number: G06F3/04845 ,  G06F3/041 ,  G06F3/04817 ,  G06F3/04847 ,  G06F3/0488 ,  G06F3/04883 ,  G06T5/001 ,  G06T5/002 ,  G06T5/003 ,  G06T2200/24

Abstract: This document describes techniques and apparatuses for area-dependent image enhancement. These techniques are capable of enabling selection, through a touch-enabled mobile-device display, of an area of a photographic image through movement of a spatially-variable implement, such as brush icon moved over the image. Selected areas can be enhanced differently than other areas, such as to apply sharpening to the selected area and blurring to a non-selected area.

Abstract translation: 本文档描述了区域依赖图像增强的技术和装置。 这些技术能够通过诸如移动在图像上的画笔图标的空间可变的工具的移动，使得能够通过启用触摸的移动设备显示来选择摄影图像的区域。 所选区域可以与其他区域不同地增强，例如对所选择的区域应用锐化和模糊到未选择的区域。

公开(公告)号：US20160140408A1

公开(公告)日：2016-05-19

申请号：US14548170

申请日：2014-11-19

Applicant: Adobe Systems Incorporated

Inventor： Xiaohui Shen ,  Xin Lu ,  Zhe Lin ,  Radomir Mech

IPC: G06K9/00 ,  G06K9/62

CPC classification number: G06K9/4676 ,  G06K9/4628

Abstract: Neural network patch aggregation and statistical techniques are described. In one or more implementations, patches are generated from an image, e.g., randomly, and used to train a neural network. An aggregation of outputs of patches processed by the neural network may be used to label an image using an image descriptor, such as to label aesthetics of the image, classify the image, and so on. In another example, the patches may be used by the neural network to calculate statistics describing the patches, such as to describe statistics such as minimum, maximum, median, and average of activations of image characteristics of the individual patches. These statistics may also be used to support a variety of functionality, such as to label the image as described above.

Abstract translation: 描述神经网络补丁聚合和统计技术。 在一个或多个实现中，从图像生成补片，例如随机地，并用于训练神经网络。 由神经网络处理的补丁的输出的聚合可以用于使用图像描述符来标记图像，例如标记图像的美学，对图像进行分类等等。 在另一示例中，神经网络可以使用补丁来计算描述补丁的统计量，例如描述诸如单个补丁的图像特征的激活的最小值，最大值，中值和平均值的统计信息。 这些统计信息也可以用于支持各种功能，例如如上所述标记图像。

公开(公告)号：US20160117798A1

公开(公告)日：2016-04-28

申请号：US14524489

申请日：2014-10-27

Applicant: Adobe Systems Incorporated

Inventor： Zhe Lin ,  Radomir Mech ,  Xiaohui Shen ,  Brian L. Price ,  Jianming Zhang

IPC: G06T3/40

CPC classification number: G06T3/40

Abstract: Image zooming is described. In one or more implementations, zoomed croppings of an image are scored. The scores calculated for the zoomed croppings are indicative of a zoomed cropping's inclusion of content that is captured in the image. For example, the scores are indicative of a degree to which a zoomed cropping includes salient content of the image, a degree to which the salient content included in the zoomed cropping is centered in the image, and a degree to which the zoomed cropping preserves specified regions-to-keep and excludes specified regions-to-remove. Based on the scores, at least one zoomed cropping may be chosen to effectuate a zooming of the image. Accordingly, the image may be zoomed according to the zoomed cropping such that an amount the image is zoomed corresponds to a scale of the zoomed cropping.

Abstract translation: 描述图像缩放。 在一个或多个实现中，对图像进行缩放裁剪​​。 针对放大的裁剪计算的分数表示缩放的裁剪包含在图像中捕获的内容。 例如，分数表示缩放裁剪包括图像的显着内容的程度，包括在缩放裁剪中的显着内容在图像中的程度以及缩放裁剪保留指定的程度 区域 - 要保留并排除指定的要移除的区域。 基于分数，可以选择至少一个缩放的裁剪来实现图像的缩放。 因此，可以根据缩放的裁剪来缩放图像，使得图像被缩放的量对应于缩放裁剪的比例。

公开(公告)号：US09299004B2

公开(公告)日：2016-03-29

申请号：US14062680

申请日：2013-10-24

Applicant: Adobe Systems Incorporated

Inventor： Zhe Lin ,  Radomir Mech ,  Peng Wang

IPC: G06K9/46 ,  G06K9/66 ,  G06T7/00

CPC classification number: G06K9/4671 ,  G06T7/11 ,  G06T7/136 ,  G06T7/162 ,  G06T7/194 ,  G06T2207/20004 ,  G06T2207/20016 ,  G06T2207/20076 ,  G06T2207/20081

Abstract: In techniques for image foreground detection, a foreground detection module is implemented to generate varying levels of saliency thresholds from a saliency map of an image that includes foreground regions. The saliency thresholds can be generated based on an adaptive thresholding technique applied to the saliency map of the image and/or based on multi-level segmentation of the saliency map. The foreground detection module applies one or more constraints that distinguish the foreground regions in the image, and detects the foreground regions of the image based on the saliency thresholds and the constraints. Additionally, different ones of the constraints can be applied to detect different ones of the foreground regions, as well as to detect multi-level foreground regions based on the saliency thresholds and the constraints.

Abstract translation: 在用于图像前景检测的技术中，实施前景检测模块以从包括前景区域的图像的显着图生成不同级别的显着阈值。 可以基于应用于图像的显着图的自适应阈值技术和/或基于显着图的多级分割来生成显着阈值。 前景检测模块应用区分图像中的前景区域的一个或多个约束，并且基于显着性阈值和约束来检测图像的前景区域。 此外，可以应用不同的约束来检测不同的前景区域，以及基于显着性阈值和约束来检测多级前景区域。

公开(公告)号：US20160026899A1

公开(公告)日：2016-01-28

申请号：US14338216

申请日：2014-07-22

Applicant: Adobe Systems Incorporated

Inventor： Jue Wang ,  Jianchao Yang ,  Zhe Lin ,  Ke Ma

IPC: G06K9/62 ,  G06T7/00 ,  G06K9/72

CPC classification number: G06K9/6261 ,  G06K9/00442 ,  G06K9/00449 ,  G06K9/00463 ,  G06K9/00818 ,  G06K9/3258 ,  G06K9/72 ,  G06T7/11 ,  H04N1/00331

Abstract: Techniques for detecting and recognizing text may be provided. For example, an image may be analyzed to detect and recognize text therein. The analysis may involve detecting text components in the image. For example, multiple color spaces and multiple-stage filtering may be applied to detect the text components. Further, the analysis may involve extracting text lines based on the text components. For example, global information about the text components can be analyzed to generate best-fitting text lines. The analysis may also involve pruning and splitting the text lines to generate bounding boxes around groups of text components. Text recognition may be applied to the bounding boxes to recognize text therein.

Abstract translation: 可以提供用于检测和识别文本的技术。 例如，可以分析图像以检测和识别其中的文本。 分析可能涉及检测图像中的文本成分。 例如，可以应用多个颜色空间和多级过滤来检测文本分量。 此外，分析可以涉及基于文本成分提取文本行。 例如，可以分析关于文本组件的全局信息，以生成最合适的文本行。 分析还可能涉及修剪和分割文本行以在文本组件组周围生成边界框。 可以将文本识别应用于边界框以识别其中的文本。

公开(公告)号：US09189834B2

公开(公告)日：2015-11-17

申请号：US14080659

申请日：2013-11-14

Applicant: Adobe Systems Incorporated

Inventor： Zhe Lin ,  Jianchao Yang ,  Hailin Jin ,  Xin Lu

IPC: G06K9/56 ,  G06T5/00 ,  G06K9/46

CPC classification number: G06T5/002 ,  G06K9/4609 ,  G06K9/4642 ,  G06K9/56 ,  G06T5/50 ,  G06T2207/20012 ,  G06T2207/20021 ,  G06T2207/20182

Abstract: In techniques for adaptive denoising with internal and external patches, example image patches taken from example images are grouped into partitions of similar patches, and a partition center patch is determined for each of the partitions. An image denoising technique is applied to image patches of a noisy image to generate modified image patches, and a closest partition center patch to each of the modified image patches is determined. The image patches of the noisy image are then classified as either a common patch or a complex patch of the noisy image, where an image patch is classified based on a distance between the corresponding modified image patch and the closest partition center patch. A denoising operator can be applied to an image patch based on the classification, such as applying respective denoising operators to denoise the image patches that are classified as the common patches of the noisy image.

Abstract translation: 在使用内部和外部补丁进行自适应去噪的技术中，从示例图像获取的示例图像修补程序分组到类似修补程序的分区中，并为每个分区确定分区中心修补程序。 将图像去噪技术应用于噪声图像的图像补丁以产生修改后的图像斑块，并确定每个修改后的图像斑块的最接近的分割中心斑块。 然后，噪声图像的图像块被分类为噪声图像的公共补丁或复杂补丁，其中基于相应修改的图像补丁和最接近的分割中心补丁之间的距离对图像补丁进行分类。 可以基于分类将去噪算子应用于图像补片，例如应用相应的去噪算子去除被分类为噪声图像的公共斑块的图像斑块。

公开(公告)号：US09152847B2

公开(公告)日：2015-10-06

申请号：US13686737

申请日：2012-11-27

Applicant: Adobe Systems Incorporated

Inventor： Feng Zhou ,  Jon Brandt ,  Zhe Lin

IPC: G06K9/00

CPC classification number: G06K9/00281

Abstract: Systems and methods are discussed to localize facial landmarks using a test facial image and a set of training images. The landmarks can be localized on a test facial image using training facial images. A plurality of candidate landmark locations on the test facial image can be determined. A subset of the training facial images with facial features similar to the facial features in the test facial image can be identified. A plurality of shape constraints can be determined for each test facial image in the subset of test facial images. These shape constraints graphically relate to one landmark location from a linear combination of the other landmark locations in the test facial image. Shape constraints can be determined for every landmark within each test facial image. A candidate landmark can be chosen from the plurality of candidate landmarks using the shape constraints.

Abstract translation: 讨论系统和方法以使用测试面部图像和一组训练图像来定位面部地标。 可以使用训练面部图像将地标定位在测试面部图像上。 可以确定测试面部图像上的多个候选标记位置。 可以识别训练面部图像的一部分，其面部特征与测试面部图像中的面部特征相似。 可以在测试面部图像的子集中的每个测试面部图像确定多个形状约束。 这些形状约束图形地涉及来自测试面部图像中的其他地标位置的线性组合的一个地标位置。 每个测试面部图像中的每个地标都可以确定形状约束。 可以使用形状约束从多个候选地标中选择候选地标。

公开(公告)号：US09117262B2

公开(公告)日：2015-08-25

申请号：US13691190

申请日：2012-11-30

Applicant: Adobe Systems Incorporated

Inventor： Zhe Lin ,  Xin Lu ,  Jonathan Brandt ,  Hailin Jin

IPC: G06K9/00 ,  G06T5/00

CPC classification number: G06T5/002 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Systems and methods are provided for providing learned, piece-wise patch regression for image enhancement. In one embodiment, an image manipulation application generates training patch pairs that include training input patches and training output patches. Each training patch pair includes a respective training input patch from a training input image and a respective training output patch from a training output image. The training input image and the training output image include at least some of the same image content. The image manipulation application determines patch-pair functions from at least some of the training patch pairs. Each patch-pair function corresponds to a modification to a respective training input patch to generate a respective training output patch. The image manipulation application receives an input image generates an output image from the input image by applying at least some of the patch-pair functions based on at least some input patches of the input image.

Abstract translation: 提供了系统和方法，用于为图像增强提供学习的分段补丁回归。 在一个实施例中，图像处理应用产生训练补丁对，其包括训练输入补丁和训练输出补丁。 每个训练补丁对包括来自训练输入图像的相应训练输入补丁和来自训练输出图像的相应训练输出补丁。 训练输入图像和训练输出图像包括至少一些相同的图像内容。 图像处理应用程序从至少一些训练补丁对确定补丁对功能。 每个补丁对功能对应于对相应的训练输入补丁的修改以生成相应的训练输出补丁。 图像处理应用程序接收输入图像，基于输入图像的至少一些输入图像块，通过应用至少一些补丁对功能，从输入图像生成输出图像。

公开(公告)号：US09081800B2

公开(公告)日：2015-07-14

申请号：US13781988

申请日：2013-03-01

Applicant: Adobe Systems Incorporated

Inventor： Zhe Lin ,  Jonathan Brandt ,  Xiaohui Shen

IPC: G06K9/62 ,  G06F17/30 ,  G06K9/46 ,  G06K9/00

CPC classification number: G06F17/30259 ,  G06K9/00228 ,  G06K9/4676 ,  G06K9/6211 ,  G06K9/6292

Abstract: One exemplary embodiment involves receiving a test image generating, by a plurality of maps for the test image based on a plurality of object images. Each of the object images comprises an object of a same object type, e.g., each comprising a different face. Each of the plurality of maps is generated to provide information about the similarity of at least a portion of a respective object image to each of a plurality of portions of the test image. The exemplary embodiment further comprises detecting a test image object within the test image based at least in part on the plurality of maps.

Abstract translation: 一个示例性实施例涉及通过基于多个对象图像的测试图像的多个映射来接收测试图像。 每个对象图像包括相同对象类型的对象，例如，每个对象包括不同的面。 生成多个地图中的每一个以提供关于相应对象图像的至少一部分与测试图像的多个部分中的每一个相似度的信息。 该示例性实施例还包括至少部分地基于多个地图检测测试图像内的测试图像对象。

公开(公告)号：US20150139536A1

公开(公告)日：2015-05-21

申请号：US14081684

申请日：2013-11-15

Applicant: Adobe Systems Incorporated

Inventor： Hailin Jin ,  Thomas Le Paine ,  Jianchao Yang ,  Zhe Lin ,  Jonathan W. Brandt

IPC: G06K9/62 ,  G06K9/46

CPC classification number: G06K9/6267 ,  G06K9/46 ,  G06K9/4652

Abstract: Image classification techniques using images with separate grayscale and color channels are described. In one or more implementations, an image classification network includes grayscale filters and color filters which are separate from the grayscale filters. The grayscale filters are configured to extract grayscale features from a grayscale channel of an image, and the color filters are configured to extract color features from a color channel of the image. The extracted grayscale features and color features are used to identify an object in the image, and the image is classified based on the identified object.

Abstract translation: 描述使用具有单独灰度和颜色通道的图像的图像分类技术。 在一个或多个实现中，图像分类网络包括与灰阶滤波器分离的灰度滤波器和滤色器。 灰度滤波器被配置为从图像的灰度级通道提取灰度特征，并且滤色器被配置为从图像的颜色通道中提取颜色特征。 提取的灰度特征和颜色特征用于识别图像中的对象，并且基于识别的对象对图像进行分类。