-
公开(公告)号:US20150294476A1
公开(公告)日:2015-10-15
申请号:US14439293
申请日:2012-10-30
Applicant: HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.
Inventor: FENG TANG , QIAN LIN , DANIEL R. TRETTER
IPC: G06T7/00
CPC classification number: G06T7/248 , G06T7/11 , G06T7/187 , G06T7/194 , G06T2207/20076 , G06T2207/20081 , G06T2207/20104 , G06T2207/30196
Abstract: According to an example, a method for object segmentation may include receiving a digital image, performing initial segmentation on the digital image to generate a segmented digital image, and receiving refinement instructions to refine the initial segmentation. The method may further include inferring an intention of a user to correct a foreground area or a background area of the initial segmentation based on the received refinement instructions, learning a behavior of the user to further infer the intention of the user to correct the foreground area or the background area, and refining, by a processor, the initial segmentation based on the inferred intention.
Abstract translation: 根据示例,用于对象分割的方法可以包括接收数字图像,在数字图像上执行初始分割以生成分割的数字图像,以及接收细化指令以优化初始分割。 该方法还可以包括推断用户基于接收到的细化指令来校正初始分段的前景区域或背景区域的意图,学习用户的行为以进一步推断用户的意图来校正前景区域 或背景区域,并且由处理器基于推断的意图来细化初始分割。
-
公开(公告)号:US20230419636A1
公开(公告)日:2023-12-28
申请号:US18253276
申请日:2020-11-25
Applicant: Hewlett-Packard Development Company, L.P.
Inventor: QIAN LIN , DEANGELI GOMES NEVES , THARSIS SALATHIEL de SOUZA VIANA , AUGUSTO VALENTE
CPC classification number: G06V10/25 , G06T7/337 , G06T2207/20132
Abstract: A region of interest is extracted from a captured image of a physical object. An autoencoder model is applied to the extracted region of interest to reconstruct the region of interest. A location of an anomaly of the physical object within the extracted region of interest, if any, is identified based on the extracted and reconstructed regions of interest.
-
公开(公告)号:US20240020952A1
公开(公告)日:2024-01-18
申请号:US18253264
申请日:2020-11-23
Inventor: SHAOYUAN XU , YANG CHENG , JAN ALLEBACH , QIAN LIN
IPC: G06V10/771 , G06V10/77 , G06V10/46 , G06V10/80 , G06V10/82
CPC classification number: G06V10/771 , G06V10/7715 , G06V10/462 , G06V10/80 , G06V10/82
Abstract: A saliency map of an image is generated. Saliency regions of the saliency map are identified. The saliency regions are merged into a combined saliency region. Candidate image crops of the image are generated based on the combined saliency region. An image crop of the image is selected from the candidate image crops using a machine learning model.
-
公开(公告)号:US20150363140A1
公开(公告)日:2015-12-17
申请号:US14761742
申请日:2013-01-24
Applicant: HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.
Inventor: Georgia Koutrika , QIAN LIN , JERRY J. LIU
IPC: G06F3/12
CPC classification number: G06F3/1204 , G06F3/1254 , G06F3/1273 , G06F3/1288 , G06Q30/0255
Abstract: A system can include a print history analyzer to generate history data based on a document history that includes a list of documents selected to be printed. The history data can characterize a content and layout of documents selected for printing. The system can also include a user print profile builder to generate a user print profile based on the history data. The user print profile can characterize printing preferences of a user. The system can further include a recommendation engine to generate a composite to-print product for the user. The composite to-print product can be based on the user print profile.
Abstract translation: 系统可以包括打印历史分析器,以基于包括选择要打印的文档的列表的文档历史来生成历史数据。 历史数据可以表征选择用于打印的文档的内容和布局。 系统还可以包括用户打印配置文件构建器以基于历史数据生成用户打印配置文件。 用户打印配置文件可以表征用户的打印首选项。 该系统还可以包括用于为用户生成复合打印产品的推荐引擎。 复合打印产品可以基于用户打印配置文件。
-
公开(公告)号:US20140204423A1
公开(公告)日:2014-07-24
申请号:US13747827
申请日:2013-01-23
Applicant: HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.
Inventor: GEORGIA KOUTRIKA , QIAN LIN , JERRY J. LIU
IPC: G06F3/12
CPC classification number: G06F3/1203 , G06F3/1242 , G06F3/1244 , G06F3/1285 , G06Q30/0207 , G06Q30/0251 , G06Q30/0282
Abstract: A system can include a print type classifier to receive a print message that indicates that a file has been selected to be printed. The print type classifier can also determine a print type of the file. The system can also include a print content analyzer to assign a category to the file characterizing a topic of the file based on the content of the file. The print type analyzer can also generate a content representation of the file that characterizes a summary of content of the file. The system can further include a recommendation engine to provide supplemental content based on at least one of the print type, the category and the content representation of the file, wherein the supplemental content is in a printable format.
Abstract translation: 系统可以包括打印类型分类器以接收指示已经选择要打印的文件的打印消息。 打印类型分类器也可以确定文件的打印类型。 该系统还可以包括打印内容分析器,用于基于文件的内容将类别分配给表征文件的主题的文件。 打印类型分析器还可以生成描述文件内容摘要的文件的内容表示。 该系统还可以包括推荐引擎,用于基于文件的打印类型,类别和内容表示中的至少一个提供补充内容,其中补充内容是可打印格式。
-
-
-
-