-
公开(公告)号：US20180310011A1
公开(公告)日：2018-10-25
申请号：US15493674
申请日：2017-04-21
Applicant: Xerox Corporation
Inventor： Sainarayanan Gopalakrishnan , Xing Li , Rajasekar Kanagasabai , Clara Cuciurean-Zapan , Vignesh Doss
IPC: H04N19/426 , H04N19/33 , H04N19/187
Abstract: An image compression method includes compressing an input image with first and second compression methods to generate first and second (e.g., lossless and lossy) compressed images. First and second residual layers are generated, based on a difference between the first and second compressed images. Connected components in the residual layers are identified. Each connected component includes a group of one or more pixels that, when mapped to the second compressed image is connected, in first and second directions, to pixels in the second compressed image. A compressed image is generated, which includes, for a connected component identified in the first residual layer, removing corresponding pixels from the second compressed image, and for a connected component identified in the second residual layer, adding corresponding pixels to the second compressed image. The system and method can thus provide file size savings associated with lossy compression while avoiding character replacement.
-
公开(公告)号：US10079960B1
公开(公告)日：2018-09-18
申请号：US15496054
申请日：2017-04-25
Applicant: Xerox Corporation
Inventor： Sudhagar Subbaian , Sainarayanan Gopalakrishnan
CPC classification number: H04N1/405 , G06K15/1881 , H04N1/4053 , H04N1/52 , H04N2201/0094
Abstract: A print system may include a print engine, a processing device and programming instructions to halftone an electronic document to be printed. The system may receive an input image representing the electronic document to be printed, use a first and second threshold array, which are flipped to each other, to halftone the input image to generate a first and second set of data, respectively, then combine the first and second set of data to generate a halftoned image. In combining the first and second set of data, each dot in the halftoned image may represent full saturation if the corresponding dot in at least one of the first and second set of data represents full saturation, or white if the corresponding dots in both the first and second set of data are white. The system may use the same halftoning method for a monochrome or color document.
-
公开(公告)号：US09973654B1
公开(公告)日：2018-05-15
申请号：US15478262
申请日：2017-04-04
Applicant: XEROX CORPORATION
CPC classification number: H04N1/4092 , H04N2201/0094
Abstract: The present disclosure discloses methods and systems (a multi-function device or a digital printer) having capabilities for an object enhancement. In an example, the MFD includes a digital front end module to detect edge of the object and direction of the edge. Following the detection of the edge, the digital front end module classify the pixels of the edge into two categories, for example, which define that whether the edge pixels are created by black-to-white transition or white-to-black transition. Based on the classification of the edge pixels, the digital front end module performs the object enhancement either in black-to-white transition or in white-to-black transition.
-
公开(公告)号：US09736333B1
公开(公告)日：2017-08-15
申请号：US15094681
申请日：2016-04-08
Applicant: Xerox Corporation
Inventor： Xing Li , Dhevendra Alagan Palanivel , Sainarayanan Gopalakrishnan , Vignesh Doss
CPC classification number: H04N1/409 , G06K15/1843 , G06K15/1847 , G06K15/1872 , G06T3/40 , G06T3/403 , G06T5/003 , G06T7/12 , G06T7/136 , G06T7/187 , H04N1/393 , H04N1/40062 , H04N1/40093 , H04N1/4092
Abstract: A method, non-transitory computer readable medium and apparatus for generating an output image are disclosed. For example, the method includes receiving an image, applying a first filter, applying a second filter, calculating a difference between the image with the second filter that was applied and the image with the first filter that was applied and transmitting the difference to a sharpening module and a segmentation module to generate the output image.
-
公开(公告)号：US09607360B2
公开(公告)日：2017-03-28
申请号：US14452576
申请日：2014-08-06
Applicant: Xerox Corporation
Inventor： Sainarayanan Gopalakrishnan , Dhevendra Alagan Palanivel , Rajasekar Kanagasabai , Ramesh Nagarajan
CPC classification number: G06T3/4092 , G06F17/212 , G06F17/214
Abstract: Various embodiments for methods and systems for processing documents are disclosed. A size of at least a part of a content in an electronic document is determined. Size of the part of the content is modified based at least on a pre-determined threshold value for size and the determined size. Further, various embodiments for methods and systems for processing N-Up documents are disclosed. One or more page images from an N-Up document are extracted based on an analysis of a content distribution in the N-Up document. A size of a content in at least a part of extracted one or more page images is determined. The size of the content is modified in accordance to a pre-determined threshold value receive from a user.
-
Patent Agency Ranking
公开(公告)号：US20160098596A1
公开(公告)日：2016-04-07
申请号：US14505517
申请日：2014-10-03
Applicant: Xerox Corporation
Inventor： Sainarayanan Gopalakrishnan , Rajasekar Kanagasabai , Vignesh Doss , Sudhagar Subbaian , Xing Li
CPC classification number: G06K9/00456 , G06F17/212 , G06K9/00422 , G06K9/2063
Abstract: Methods and systems for classifying a region of interest in an electronic document. A first region from the electronic document is extracted. The first region includes at least the region of interest. A first projection profile of pixels is determined in the region of interest. The first projection profile of pixels is indicative of a presence of a content in the region of interest. The region of interest is classified in at least one category based on a comparison of the first projection profile with a predetermined projection profile associated with the region of interest.
Abstract translation: 在电子文件中分类感兴趣区域的方法和系统。 提取电子文档的第一区域。 第一区域至少包括感兴趣的区域。 在感兴趣的区域中确定像素的第一投影轮廓。 像素的第一投影轮廓指示感兴趣区域中的内容的存在。 基于第一投影轮廓与与感兴趣区域相关联的预定投影轮廓的比较，感兴趣区域被分类为至少一个类别。
-
公开(公告)号：US20150356740A1
公开(公告)日：2015-12-10
申请号：US14296553
申请日：2014-06-05
Applicant: Xerox Corporation
Inventor： Sudhagar Subbaian , Sainarayanan Gopalakrishnan , Xing Li , Clara Cuciurean-Zapan
CPC classification number: G06K9/6267 , G06K9/00456 , G06K9/4638
Abstract: A method and system for segmenting text from non-text portions of a digital image using the size, solidity, and run length characteristics of connected components within the image data. For a connected component comprising a rectangular group of pixels enclosing a set of connected pixels having the same binary state, the size characteristic may be based on a ratio of height to width of the connected component and the total number of pixels within the connected component, the solidity characteristic may be based on a ratio of pixels within a convex hull of the set of connected pixel to a total number of pixels within the connected component, and the run length characteristic may be based on a number of transitions within the connected component.
Abstract translation: 一种用于使用图像数据内的连接分量的大小，坚固度和游程长度特征从数字图像的非文本部分分割文本的方法和系统。 对于包括围绕具有相同二进制状态的一组连接像素的矩形像素组的连接分量，尺寸特征可以基于所连接分量的高度与宽度的比率以及连通分量内的总像素数， 固体特性可以基于所连接的像素组中的凸包内的像素与连通分量内的总像素数的比率，并且游程长度特征可以基于所连接的组件内的多个转换。
-
公开(公告)号：US11954931B1
公开(公告)日：2024-04-09
申请号：US17937794
申请日：2022-10-04
Applicant: XEROX CORPORATION
IPC: G06K9/00 , G06V10/28 , G06V20/00 , G06V30/413 , G06V30/414 , G06V30/418
CPC classification number: G06V30/413 , G06V10/28 , G06V20/95 , G06V30/414 , G06V30/418 , G06V2201/13
Abstract: The present disclosure discloses methods and systems for detecting tampering of an infrared (IR) security mark in a document. The method includes receiving the document including the IR security mark, wherein the IR security mark further includes one or more security texts and/or images. The document is scanned to generate scanned data. A portion of the scanned data including the IR security mark is segmented into a plurality of blocks such as blocks of size 32*32. Thereafter, a ratio of white to black pixels is calculated for each block. The calculated ratio is compared with a known threshold for each block. Upon comparison, the IR security mark is detected as a tampered security mark.
-
公开(公告)号：US11941937B2
公开(公告)日：2024-03-26
申请号：US17391253
申请日：2021-08-02
Applicant: XEROX CORPORATION
CPC classification number: G07D7/121 , H04N1/00331 , H04N1/32256 , G06T2207/10024 , G07D7/00 , G07D7/202 , H04N1/00838 , H04N1/00856 , H04N1/0087 , H04N2201/327
Abstract: The present disclosure discloses methods and systems for detecting an IR security mark in a document based on known color information and halftone frequency information. The method includes receiving a document from a user, including an IR security mark. Then, location information, color information and halftone frequency information are received from the user. The document is scanned. Based on the color information and the location information, the IR security mark is extracted from the scanned document. After this, halftone frequency information of the extracted IR security mark is verified. Based on the verification, text in the extracted IR security mark is identified and is then compared with one or more pre-stored IR security marks to ascertain whether the IR security mark in the document is an authentic security mark.
-
30.发明授权公开(公告)号：US11556597B2
公开(公告)日：2023-01-17
申请号：US17235189
申请日：2021-04-20
Applicant: XEROX CORPORATION
Inventor： Shalini Kondore , Srinivasarao Bindana , Sainarayanan Gopalakrishnan , Nithya Theerthagiri , Dara N Lubin
IPC: G06F16/93 , G06V30/148 , H04N1/00 , G06V30/10
Abstract: The disclosure discloses methods and systems for automatically generating multiple scanned files when scanning a document at a multi-function device. The method includes receiving a multi-page document for scanning from a user. A user interface is provided to the user to input one or more keywords and one or more desired resolution values, where the input resolution values are different from a default resolution value set at the multi-function device. A page of the document is scanned to generate a scanned page of a default resolution value. The scanned page is checked if including the one or more input keywords. Accordingly, the default resolution value of the page is converted to the user desired resolution value. The scanning, checking, and converting are repeated till all the pages of the document are scanned. Multiple scanned files of different resolution values are automatically generated from single scan activity.
-
-
-
-
-
-
-
-
-
Search Results
80
records
(took 0.015 seconds)
