-
公开(公告)号：US20150170000A1
公开(公告)日：2015-06-18
申请号：US14107191
申请日：2013-12-16
Applicant: Adobe Systems Incorporated
Inventor： Jianchao Yang , Guang Chen , Hailin Jin , Jonathan Brandt , Elya Shechtman , Aseem Omprakash Agarwala
IPC: G06K9/62
CPC classification number: G06K9/6267 , G06K9/6219 , G06K9/6282 , G06K9/6807
Abstract: Example systems and methods for classifying visual patterns into a plurality of classes are presented. Using reference visual patterns of known classification, at least one image or visual pattern classifier is generated, which is then employed to classify a plurality of candidate visual patterns of unknown classification. The classification scheme employed may be hierarchical or nonhierarchical. The types of visual patterns may be fonts, human faces, or any other type of visual patterns or images subject to classification.
Abstract translation: 提出了将视觉模式分类为多个类的示例系统和方法。 使用已知分类的参考视觉图案，生成至少一个图像或视觉模式分类器，然后将其用于对未知分类的多个候选视觉图案进行分类。 所使用的分类方案可以是分层的或非分层的。 视觉图案的类型可以是字体，人脸或任何其他类型的可分类的视觉图案或图像。
-
公开(公告)号：US20150139557A1
公开(公告)日：2015-05-21
申请号：US14085488
申请日：2013-11-20
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin , Jianchao Yang , Hailin Jin , Xin Lu
IPC: G06K9/62
CPC classification number: G06K9/4642 , G06K9/6273 , G06K9/6276
Abstract: In techniques for fast dense patch search and quantization, partition center patches are determined for partitions of example image patches. Patch groups of an image each include similar image patches and a reference image patch that represents a respective patch group. A partition center patch of the partitions is determined as a nearest neighbor to the reference image patch of a patch group. The partition center patch can be determined based on a single-nearest neighbor (1-NN) distance determination, and the determined partition center patch is allocated as the nearest neighbor to the similar image patches in the patch group. Alternatively, a group of nearby partition center patches are determined as the nearest neighbors to the reference image patch based on a k-nearest neighbor (k-NN) distance determination, and the nearest neighbor to each of the similar image patches in the patch group is determined from the nearby partition center patches.
Abstract translation: 在快速密集补丁搜索和量化的技术中，为示例图像补丁的分区确定分区中心补丁。 图像的补丁组各自包括相似的图像补丁和代表相应补丁组的参考图像补丁。 分区的分区中心补丁被确定为补丁组的参考图像补丁的最近邻。 可以基于单个最近邻居（1-NN）距离确定来确定分区中心补丁，并且将所确定的分区中心补丁分配为补丁组中的相似图像补丁的最近邻。 或者，基于k个最近邻（k-NN）距离确定，将一组附近的分区中心补丁确定为参考图像补丁的最近邻，并且补丁组中每个相似图像补丁的最近邻 是从附近的分区中心补丁确定的。
-
公开(公告)号：US20150063713A1
公开(公告)日：2015-03-05
申请号：US14012770
申请日：2013-08-28
Applicant: Adobe Systems Incorporated
Inventor： Jianchao Yang , Guang Chen , Hailin Jin , Jonathan Brandt , Elya Shechtman
IPC: G06K9/62
CPC classification number: G06K9/6267 , G06K9/00979 , G06K9/4671 , G06K9/6219 , G06K9/6298 , G06K9/6828
Abstract: A hierarchy machine may be configured as a clustering machine that utilizes local feature embedding to organize visual patterns into nodes that each represent one or more visual patterns. These nodes may be arranged as a hierarchy in which a node may have a parent-child relationship with one or more other nodes. The hierarchy machine may implement a node splitting and tree-learning algorithm that includes hard-splitting of nodes and soft-assignment of nodes to perform error-bounded splitting of nodes into clusters. This may enable the hierarchy machine, which may form all or part of a visual pattern recognition system, to perform large-scale visual pattern recognition, such as font recognition or facial recognition, based on a learned error-bounded tree of visual patterns.
Abstract translation: 层次机器可以被配置为利用局部特征嵌入将可视图案组织成每个表示一个或多个视觉图案的节点的聚类机器。 这些节点可以被布置为其中节点可以与一个或多个其他节点具有父子关系的层级。 层次机器可以实现节点分割和树学习算法，其包括节点的硬分割和节点的软分配，以执行节点到分簇的有界限制的分割。 这可以使得可以形成视觉图案识别系统的全部或一部分的层次机器基于学习的有界错误的视觉图案树来执行诸如字体识别或面部识别的大规模视觉模式识别。
-
公开(公告)号：US20140368549A1
公开(公告)日：2014-12-18
申请号：US13920911
申请日：2013-06-18
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin , Jianchao Yang , Scott D. Cohen
IPC: G06T3/40
CPC classification number: G06T3/40 , G06T3/4076
Abstract: Image upscaling techniques are described. These techniques may include use of iterative and adjustment upscaling techniques to upscale an input image. A variety of functionality may be incorporated as part of these techniques, examples of which include content-adaptive patch finding techniques that may be employed to give preference to an in-place patch to minimize structure distortion. In another example, content metric techniques may be employed to assign weights for combining patches. In a further example, algorithm parameters may be adapted with respect to algorithm iterations, which may be performed to increase efficiency of computing device resource utilization and speed of performance. For instance, algorithm parameters may be adapted to enforce a minimum and/or maximum number to iterations, cease iterations for image sizes over a threshold amount, set sampling step sizes for patches, employ techniques based on color channels (which may include independence and joint processing techniques), and so on.
Abstract translation: 描述了图像升高技术。 这些技术可以包括使用迭代和调整放大技术来升高输入图像。 作为这些技术的一部分，可以并入各种功能，其示例包括可用于优先使用就地补丁以最小化结构失真的内容自适应补片发现技术。 在另一示例中，可以采用内容度量技术来分配用于组合补丁的权重。 在另一示例中，算法参数可以针对算法迭代进行调整，这可以被执行以提高计算设备资源利用率和性能的效率。 例如，算法参数可以适于对迭代执行最小和/或最大数量，停止针对阈值量的图像大小的迭代，设置用于补丁的采样步长，采用基于颜色通道的技术（其可以包括独立性和联合 处理技术）等。
-
公开(公告)号：US10043101B2
公开(公告)日：2018-08-07
申请号：US14535963
申请日：2014-11-07
Applicant: Adobe Systems Incorporated
Inventor： Jianchao Yang , Jonathan Brandt
Abstract: Techniques are disclosed for image feature representation. The techniques exhibit discriminative power that can be used in any number of classification tasks, and are particularly effective with respect to fine-grained image classification tasks. In an embodiment, a given image to be classified is divided into image patches. A vector is generated for each image patch. Each image patch vector is compared to the Gaussian mixture components (each mixture component is also a vector) of a Gaussian Mixture Model (GMM). Each such comparison generates a similarity score for each image patch vector. For each Gaussian mixture component, the image patch vectors associated with a similarity score that is too low are eliminated. The selectively pooled vectors from all the Gaussian mixture components are then concatenated to form the final image feature vector, which can be provided to a classifier so the given input image can be properly categorized.
-
Patent Agency Ranking
公开(公告)号：US20170228659A1
公开(公告)日：2017-08-10
申请号：US15082877
申请日：2016-03-28
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin , Jianchao Yang , Hailin Jin , Chen Fang
CPC classification number: G06N20/00 , G06F16/532 , G06F16/58 , G06N3/0454 , G06N3/08 , G06N5/04
Abstract: Certain embodiments involve learning features of content items (e.g., images) based on web data and user behavior data. For example, a system determines latent factors from the content items based on data including a user's text query or keyword query for a content item and the user's interaction with the content items based on the query (e.g., a user's click on a content item resulting from a search using the text query). The system uses the latent factors to learn features of the content items. The system uses a previously learned feature of the content items for iterating the process of learning features of the content items to learn additional features of the content items, which improves the accuracy with which the system is used to learn other features of the content items.
-
公开(公告)号：US09552510B2
公开(公告)日：2017-01-24
申请号：US14661788
申请日：2015-03-18
Applicant: Adobe Systems Incorporated
Inventor： Wilmot Wei-Mau Li , Jianchao Yang , Linjie Luo , Jonathan W. Brandt , Xiang Yu
CPC classification number: G06K9/00288 , G06K9/00228 , G06K9/00281 , G06K9/00302 , G06K9/00315 , G06K9/4604 , G06K9/4628 , G06K9/4642 , G06K9/6269 , G06K9/6272 , G06K9/66 , G06T7/246 , G06T13/40
Abstract: Techniques for facial expression capture for character animation are described. In one or more implementations, facial key points are identified in a series of images. Each image, in the series of images, is normalized from the identified facial key points. Facial features are determined from each of the normalized images. Then a facial expression is classified, based on the determined facial features, for each of the normalized images. In additional implementations, a series of images are captured that include performances of one or more facial expressions. The facial expressions in each image of the series of images are classified by a facial expression classifier. Then the facial expression classifications are used by a character animator system to produce a series of animated images of an animated character that include animated facial expressions that are associated with the facial expression classification of the corresponding image in the series of images.
Abstract translation: 描述了用于人物动画的面部表情捕获的技术。 在一个或多个实现中，在一系列图像中识别面部关键点。 一系列图像中的每个图像都从识别的面部关键点进行归一化。 从每个标准化图像确定面部特征。 然后，基于所确定的面部特征，针对每个标准化图像分类面部表情。 在另外的实现中，捕获包括一个或多个面部表情的表现的一系列图像。 一系列图像的每个图像中的面部表情由面部表情分类器分类。 然后，人物动画师系统使用面部表情分类来产生动画角色的一系列动画图像，其包括与一系列图像中的对应图像的面部表情分类相关联的动画面部表情。
-
38.发明授权公开(公告)号：US09501724B1
公开(公告)日：2016-11-22
申请号：US14734466
申请日：2015-06-09
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： Jianchao Yang , Zhangyang Wang , Jonathan Brandt , Hailin Jin , Elya Shechtman , Aseem Omprakash Agarwala
CPC classification number: G06T3/40 , G06K9/6255 , G06K9/6828
Abstract: A convolutional neural network (CNN) is trained for font recognition and font similarity learning. In a training phase, text images with font labels are synthesized by introducing variances to minimize the gap between the training images and real-world text images. Training images are generated and input into the CNN. The output is fed into an N-way softmax function dependent on the number of fonts the CNN is being trained on, producing a distribution of classified text images over N class labels. In a testing phase, each test image is normalized in height and squeezed in aspect ratio resulting in a plurality of test patches. The CNN averages the probabilities of each test patch belonging to a set of fonts to obtain a classification. Feature representations may be extracted and utilized to define font similarity between fonts, which may be utilized in font suggestion, font browsing, or font recognition applications.
Abstract translation: 对卷积神经网络（CNN）进行字体识别和字体相似学习。 在训练阶段，通过引入差异来合成具有字体标签的文本图像，以最小化训练图像与真实世界文本图像之间的差距。 生成训练图像并将其输入到CNN中。 根据CNN正在训练的字体数量，输出被输入到N-way softmax函数中，产生N类标签上分类文本图像的分布。 在测试阶段，每个测试图像的高度被标准化，并以纵横比挤压，从而产生多个测试贴片。 CNN对属于一组字体的每个测试补丁的概率进行平均，以获得分类。 可以提取和利用特征表示来定义可以在字体建议，字体浏览或字体识别应用中使用的字体之间的字体相似性。
-
公开(公告)号：US09311690B2
公开(公告)日：2016-04-12
申请号：US14205027
申请日：2014-03-11
Applicant: Adobe Systems Incorporated
Inventor： Hailin Jin , Zhuoyuan Chen , Scott D. Cohen , Jianchao Yang , Zhe Lin
CPC classification number: H04N5/21 , G06T3/4053 , G06T3/4076 , G06T5/002 , G06T5/003 , G06T5/20 , G06T5/50 , G06T7/269 , G06T2207/10016 , G06T2207/20021 , G06T2207/20032 , G06T2207/20182 , G06T2207/20201 , H04N5/144 , H04N5/145 , H04N5/147
Abstract: In techniques for video denoising using optical flow, image frames of video content include noise that corrupts the video content. A reference frame is selected, and matching patches to an image patch in the reference frame are determined from within the reference frame. A noise estimate is computed for previous and subsequent image frames relative to the reference frame. The noise estimate for an image frame is computed based on optical flow, and is usable to determine a contribution of similar motion patches to denoise the image patch in the reference frame. The similar motion patches from the previous and subsequent image frames that correspond to the image patch in the reference frame are determined based on the optical flow computations. The image patch is denoised based on an average of the matching patches from reference frame and the similar motion patches determined from the previous and subsequent image frames.
Abstract translation: 在使用光流的视频去噪的技术中，视频内容的图像帧包括破坏视频内容的噪声。 选择参考帧，并且从参考帧内确定参考帧中的图像块的匹配补丁。 针对相对于参考帧的先前和后续图像帧计算噪声估计。 基于光流计算图像帧的噪声估计，并且可用于确定类似运动补丁对参考帧中的图像补丁进行去噪的贡献。 基于光流计算确定与参考帧中的图像块相对应的来自先前和后续图像帧的类似运动补丁。 基于来自参考帧的匹配补丁的平均值和从先前和后续图像帧确定的类似运动补丁，去除图像补丁。
-
公开(公告)号：US09305339B2
公开(公告)日：2016-04-05
申请号：US14320987
申请日：2014-07-01
Applicant: Adobe Systems Incorporated
Inventor： Jianchao Yang , Jue Wang , Ketan Tang
CPC classification number: G06K9/4661 , G06K9/40 , G06T5/003 , G06T2207/10016 , G06T2207/10024 , G06T2207/20024 , H04N5/217 , H04N5/23229
Abstract: Multi-feature image haze removal is described. In one or more implementations, feature maps are extracted from a hazy image of a scene. The feature maps convey information about visual characteristics of the scene captured in the hazy image. Based on the feature maps, portions of light that are not scattered by the atmosphere and are captured to produce the hazy image are computed. Additionally, airlight of the hazy image is ascertained based on at least one of the feature maps. The calculated airlight represents constant light of the scene. Using the computed portions of light and the ascertained airlight, a dehazed image is generated from the hazy image.
Abstract translation: 描述了多特征图像雾度去除。 在一个或多个实现中，从场景的模糊图像中提取特征图。 特征图传达关于在朦胧图像中捕获的场景的视觉特征的信息。 基于特征图，计算不被大气散射并被捕获以产生模糊图像的部分光。 此外，基于特征图中的至少一个来确定模糊图像的飞行器。 计算出的空气动力表示场景的恒定光。 使用所计算的光部分和所确定的空气光，从模糊图像产生脱色图像。
-
-
-
-
-
-
-
-
-
Search Results
57
records
(took 0.023 seconds)
