-
公开(公告)号：US10602019B2
公开(公告)日：2020-03-24
申请号：US16039405
申请日：2018-07-19
Applicant: XEROX CORPORATION
Inventor： Sainarayanan Gopalakrishnan , Rajasekar Kanagasabai , Vignesh Doss
Abstract: Examples of systems and methods for enhancing image quality for documents with highlighted portions are described. A highlighted portion from a received input is detected. The highlighted portion is automatically segmented as a text layer and the remaining portion is further segmented as a separate text layer and an image layer. A resolution is assigned to the highlighted portion, wherein the resolution assigned to the highlighted portion is greater than the respective resolution for the text layer and the image layer, to improve quality of the highlighted portion. The text layer corresponding to the highlighted portion and the separate text layer and the image layer are integrated together to generate a scanned document in a Mixed Raster Content (MRC) file format.
-
公开(公告)号：US10460192B2
公开(公告)日：2019-10-29
申请号：US15299717
申请日：2016-10-21
Applicant: XEROX CORPORATION
Abstract: A method and system are provided for optical character recognition (OCR) of multi-language content. The method includes extracting a text portion from an image received from a user-computing device. The text portion comprises a plurality of keywords associated with a plurality of languages. The method further includes segmenting the plurality of keywords into a plurality of layers. Each layer of the plurality of layers comprises one or more keywords which are associated with a language. The method further comprise generating an OCR output of each of the plurality of layers based on the language associated with the one or more keywords in each of the plurality of layers. The method further comprises generating an electronic document of the received image based on the generated OCR output of each of the plurality of layers. The method further includes transmitting the generated electronic document to the user-computing device.
-
33.发明授权公开(公告)号：US10049097B1
公开(公告)日：2018-08-14
申请号：US15417272
申请日：2017-01-27
Applicant: XEROX CORPORATION
Abstract: The present disclosure discloses methods and systems for creating a multi-layered Optical Character Recognition (OCR) document, the multi-layered OCR document facilitates selection of the desired text from the multi-layered OCR document. The method includes receiving a scanned image corresponding to a document, the document includes text information. A binary image is generated from the scanned image. Then, a morphological dilation operation is performed to create one or more text groups, using a horizontal structuring element and a vertical structuring element. Thereafter, OCR operation is applied on each text group to generate a corresponding OCR layer. The one or more OCR layers are then combined while creating a multi-layered OCR document. Finally, the combined OCR layers are superimposed as invisible text layers over the scanned image to create the multi-layered OCR document.
-
Patent Agency Ranking
公开(公告)号：US10043116B1
公开(公告)日：2018-08-07
申请号：US15486401
申请日：2017-04-13
Applicant: Xerox Corporation
Inventor： Sainarayanan Gopalakrishnan , Xing Li , Rajasekar Kanagasabai , Clara Cuciurean-Zapan
Abstract: A system and method for generating a mixed raster content representation of an input image. An input image is segmented into image and text layers. Connected component analysis is performed on the image layer, with each group of connected pixels labeled. For each group, an average color is determined and when a mask layer exists for the color, the pixels in the group are enabled in the mask layer. When a mask layer does not exist for the color, a new mask layer is created and the corresponding pixels enabled. The image layer is then removed and the mask layers are combined into the text layer, whereupon a text only MRC compression file is output.
-
公开(公告)号：US09596380B1
公开(公告)日：2017-03-14
申请号：US14886172
申请日：2015-10-19
Applicant: XEROX CORPORATION
Inventor： Sainarayanan Gopalakrishnan , Xing Li , Rajasekar Kanagasabai , Clara Cuciurean-Zapan
CPC classification number: H04N1/413 , H04N1/00095 , H04N1/41 , H04N2201/0094
Abstract: According to embodiments illustrated herein there is provided a method of image compression. The method includes generating a modified image based on a compression of an image. The method further includes generating a first residual layer and a second residual layer based on a comparison of the modified image and the image. The method further includes filtering a set of pixels from the first residual layer and the second residual layer. The method further includes compressing the filtered first residual layer and the filtered second residual layer to generate a compressed first residual layer and a compressed second residual layer. Additionally, the method includes generating a second compressed image based on the modified image, the compressed first residual image and the compressed second residual image.
Abstract translation: 根据本文所示的实施例，提供了一种图像压缩方法。 该方法包括基于图像的压缩生成修改的图像。 该方法还包括基于修改图像和图像的比较来生成第一残留层和第二残留层。 该方法还包括从第一残留层和第二残留层过滤一组像素。 该方法还包括压缩经滤波的第一残留层和经滤波的第二残留层以产生压缩的第一残余层和压缩的第二残留层。 此外，该方法包括基于修正图像，压缩的第一残差图像和压缩的第二残差图像生成第二压缩图像。
-
公开(公告)号：US09288364B1
公开(公告)日：2016-03-15
申请号：US14632105
申请日：2015-02-26
Applicant: XEROX CORPORATION
Inventor： Sainarayanan Gopalakrishnan , Rajasekar Kanagasabai , Xing Li , Clara Cuciurean-Zapan , Pravin Jogdand
CPC classification number: H04N1/403 , G06F3/122 , G06F3/1229 , G06K9/46 , G06K15/1822 , G06K2009/4666 , G06T7/00 , G06T2207/10004 , H04N1/405 , H04N2201/0094
Abstract: The disclosed embodiments illustrate methods and systems for estimating a half-tone frequency of an image. The method includes combining, by one or more processors, a first binary block, obtained from a portion of the image, with one or more second binary blocks to create a third binary block. Each of the one or more second binary blocks is obtained by shifting the first binary block. The method further includes estimating, by the one or more processors, the half-tone frequency of the portion of the image, based on the first binary block and the third binary block.
Abstract translation: 所公开的实施例示出了用于估计图像的半色调频率的方法和系统。 该方法包括由一个或多个处理器将从图像的一部分获得的第一二进制块与一个或多个第二二进制块组合以创建第三二进制块。 通过移位第一二进制块来获得一个或多个第二二进制块中的每一个。 该方法还包括基于第一二进制块和第三二进制块，由一个或多个处理器估计图像的该部分的半色调频率。
-
公开(公告)号：US09237255B1
公开(公告)日：2016-01-12
申请号：US14467303
申请日：2014-08-25
Applicant: Xerox Corporation
Inventor： Sainarayanan Gopalkrishnan , Xing Li , Rajasekar Kanagasabai , Vignesh Doss , Clara Cuciurean-Zapan
CPC classification number: H04N1/40068 , H04N1/41
Abstract: Various embodiments for methods and systems for processing a document are disclosed. A font size associated with each of one or more text regions included in the document is determined. A first resolution of each of the one or more text regions is modified based on respective font size associated with each of the one or more text regions to generate a multi-resolution document.
Abstract translation: 公开了用于处理文档的方法和系统的各种实施例。 确定与文档中包括的一个或多个文本区域中的每一个相关联的字体大小。 基于与一个或多个文本区域中的每一个相关联的相应字体大小来修改一个或多个文本区域中的每一个的第一分辨率，以生成多分辨率文档。
-
公开(公告)号：US09147262B1
公开(公告)日：2015-09-29
申请号：US14467355
申请日：2014-08-25
Applicant: Xerox Corporation
Inventor： Xing Li , Sainarayanan Gopalakrishnan , Rajasekar Kanagasabai
CPC classification number: G06K15/1881 , G06T7/41 , G06T2207/10024 , G06T2207/20021 , G06T2207/30176
Abstract: The disclosed embodiments illustrate methods and systems for image processing. The method includes dividing a portion of an image into a set of blocks, each block of which is divided into a set of sub-blocks. Thereafter, a measurable block is identified from the set of blocks based on a measurability criteria that comprises determining an average pixel value for each of the sub-blocks based on one or more pixels encompassed by respective sub-block. Further, a maximum average pixel value, a minimum average pixel value, and a range of average pixel values are determined among the set of sub-blocks. The measurability criteria further includes comparing the maximum average pixel value, the minimum average pixel value, and the range of average pixel values with respective pre-determined thresholds. The method further includes estimating a half-tone frequency of the portion based on a processing of the identified measurable block.
Abstract translation: 所公开的实施例示出了用于图像处理的方法和系统。 该方法包括将图像的一部分划分成一组块，每个块的每个块被划分成一组子块。 此后，基于可测量标准，从该组块识别可测量块，其包括基于由相应子块包含的一个或多个像素来确定每个子块的平均像素值。 此外，在子块组中确定最大平均像素值，最小平均像素值和平均像素值的范围。 可测量性标准还包括将最大平均像素值，最小平均像素值和平均像素值的范围与各个预定阈值进行比较。 该方法还包括基于所识别的可测量块的处理来估计该部分的半色调频率。
-
-
-
-
-
-
-
Search Results
38
records
(took 0.02 seconds)
