-
1.发明申请公开(公告)号：US20160364633A1
公开(公告)日：2016-12-15
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：US20170061257A1
公开(公告)日：2017-03-02
申请号：US15349876
申请日：2016-11-11
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： JIANCHAO YANG , GUANG CHEN , HAILIN JIN , JONATHAN BRANDT , ELYA SHECHTMAN , ASEEM OMPRAKASH AGARWALA
CPC classification number: G06K9/6282 , G06K9/6219 , G06K9/6267 , 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。
-
Patent Agency Ranking
公开(公告)号：US20160335747A1
公开(公告)日：2016-11-17
申请号：US15219590
申请日：2016-07-26
Applicant: Adobe Systems Incorporated
Inventor： JIANCHAO YANG
CPC classification number: G06T5/003 , G06T5/10 , G06T2207/20016
Abstract: Techniques are disclosed for removing blur from a single image by accumulating a blur kernel estimation across several scale levels of the image and balancing the contributions of the different scales to the estimation depending on the noise level in each observation. In particular, a set of observations can be obtained by applying a set of variable scale filters to a single blurry image at different scale levels. A single blur kernel can be estimated across all scales from the set of observations and used to obtain a single latent sharp image. The estimation at a large scale level is refined using the observations at successively smaller scale levels. The filtered observations may be weighted during the estimation to balance the contributions of each scale to the estimation of the blur kernel. A deblurred digital image is recovered by deconvolving the blurry digital image using the estimated blur kernel.
Abstract translation: 公开了通过在图像的多个尺度级上累积模糊核估计并根据每个观察中的噪声水平平衡不同尺度的贡献与估计的平均值来从单个图像中去除模糊的技术。 特别地，可以通过将不同尺度级别的单个模糊图像应用一组可变尺度滤波器来获得一组观察值。 可以从观察组中的所有尺度估计单个模糊核，并用于获得单个潜在清晰图像。 使用在连续较小规模水平的观测值来改进大规模级别的估计。 可以在估计期间对经滤波的观测进行加权，以平衡每个比例的贡献与模糊核的估计。 通过使用估计的模糊核对模糊的数字图像进行去卷积来恢复去模糊的数字图像。
-
公开(公告)号：US20160034788A1
公开(公告)日：2016-02-04
申请号：US14447296
申请日：2014-07-30
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： ZHE LIN , HAILIN JIN , JIANCHAO YANG
CPC classification number: G06T7/33 , G06K9/627 , G06N3/0454
Abstract: A first set of attributes (e.g., style) is generated through pre-trained single column neural networks and leveraged to regularize the training process of a regularized double-column convolutional neural network (RDCNN). Parameters of the first column (e.g., style) of the RDCNN are fixed during RDCNN training Parameters of the second column (e.g., aesthetics) are fine-tuned while training the RDCNN and the learning process is supervised by the label identified by the second column (e.g., aesthetics). Thus, features of the images may be leveraged to boost classification accuracy of other features by learning a RDCNN.
Abstract translation: 通过预训练的单列神经网络产生第一组属性（例如，样式），并且利用正则化的双列卷积神经网络（RDCNN）的训练过程。 在RDCNN训练期间RDCNN的第一列（例如，样式）的参数是固定的在第二列的参数（例如，美学）中进行微调，同时训练RDCNN，学习过程由第二列标识的标签 （如美学）。 因此，可以利用图像的特征来通过学习RDCNN来提高其他特征的分类精度。
-
公开(公告)号：US20170011291A1
公开(公告)日：2017-01-12
申请号：US14793157
申请日：2015-07-07
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： HAILIN JIN , JONATHAN KRAUSE , JIANCHAO YANG
CPC classification number: G06N3/088 , G06F17/30247 , G06K9/00362 , G06K9/4628 , G06K9/6218 , G06K9/627 , G06N99/005
Abstract: Embodiments of the present invention relate to finding semantic parts in images. In implementation, a convolutional neural network (CNN) is applied to a set of images to extract features for each image. Each feature is defined by a feature vector that enables a subset of the set of images to be clustered in accordance with a similarity between feature vectors. Normalized cuts may be utilized to help preserve pose within each cluster. The images in the cluster are aligned and part proposals are generated by sampling various regions in various sizes across the aligned images. To determine which part proposal corresponds to a semantic part, a classifier is trained for each part proposal and semantic part to determine which part proposal best fits the correlation pattern given by the true semantic part. In this way, semantic parts in images can be identified without any previous part annotations.
Abstract translation: 本发明的实施例涉及在图像中发现语义部分。 在实现中，将卷积神经网络（CNN）应用于一组图像以提取每个图像的特征。 每个特征由特征向量定义，其使得能够根据特征向量之间的相似性来聚集图像集合的子集。 可以利用归一化切割来帮助保持每个群集内的姿态。 集群中的图像对齐，并通过对齐的图像中的各种尺寸的各种区域进行采样来生成部件提案。 为了确定哪个部分提案与语义部分相对应，针对每个部分提议和语义部分训练分类器，以确定哪个部分提案最符合真实语义部分给出的相关模式。 以这种方式，可以识别图像中的语义部分，而不需要任何先前的部分注释。
-
公开(公告)号：US20170004383A1
公开(公告)日：2017-01-05
申请号：US14788113
申请日：2015-06-30
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： ZHE LIN , JONATHAN BRANDT , XIAOHUI SHEN , JAE-PIL HEO , JIANCHAO YANG
CPC classification number: G06F17/30268 , G06F17/30277 , G06K9/6215 , G06T2207/20084
Abstract: In various implementations, a personal asset management application is configured to perform operations that facilitate the ability to search multiple images, irrespective of the images having characterizing tags associated therewith or without, based on a simple text-based query. A first search is conducted by processing a text-based query to produce a first set of result images used to further generate a visually-based query based on the first set of result images. A second search is conducted employing the visually-based query that was based on the first set of result images received in accordance with the first search conducted and based on the text-based query. The second search can generate a second set of result images, each having visual similarity to at least one of the images generated for the first set of result images.
Abstract translation: 在各种实现中，个人资产管理应用被配置为执行操作，其便于搜索多个图像的能力，而不管基于简单的基于文本的查询，具有与其相关联的或不具有特征标签的图像。 通过处理基于文本的查询以产生用于基于第一组结果图像进一步生成基于视觉的查询的第一组结果图像来进行第一搜索。 使用基于基于根据所进行的第一次搜索接收的第一组结果图像并基于基于文本的查询的基于视觉的查询进行第二搜索。 第二搜索可以产生第二组结果图像，每个结果图像与对于第一组结果图像生成的图像中的至少一个图像具有视觉相似性。
-
公开(公告)号：US20150339273A1
公开(公告)日：2015-11-26
申请号：US14286242
申请日：2014-05-23
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： JIANCHAO YANG , HAILIN JIN , JONATHAN BRANDT
IPC: G06F17/21 , G06F3/0484 , G06F17/30
CPC classification number: G06F17/214 , G06F3/0484 , G06F3/04842 , G06F17/30 , G06F17/30864 , G06F17/30958 , G06T11/206
Abstract: Font graphs are defined having a finite set of nodes representing fonts and a finite set of undirected edges denoting similarities between fonts. The font graphs enable users to browse and identify similar fonts. Indications corresponding to a degree of similarity between connected nodes may be provided. A selection of a desired font or characteristics associated with one or more attributes of the desired font is received from a user interacting with the font graph. The font graph is dynamically redefined based on the selection.
Abstract translation: 字体图被定义为具有表示字体的有限的节点集合和表示字体之间的相似性的无向边的有限集合。 字体图使用户能够浏览和识别类似的字体。 可以提供与连接的节点之间的相似程度相对应的指示。 从与字体图形交互的用户接收与期望字体的一个或多个属性相关联的期望字体或特征的选择。 基于选择动态地重新定义字体图。
-
-
-
-
-
-
Search Results
7
records
(took 0.013 seconds)
