-
公开(公告)号：US10891476B2
公开(公告)日：2021-01-12
申请号：US15876334
申请日：2018-01-22
Applicant: Fujitsu Limited
Inventor： Ruochen Wang , Wei Fan , Jun Sun
Abstract: A method, system, and neural network for identifying direction of a document where the method comprises: extracting a text line in the document; calculating a first normal direction result indicative of the text line probably being in a normal direction and a first upside-down direction result indicative of the text line probably being in a direction upside-down with respect to the normal direction; calculating a second normal direction result indicative of the text line after being rotated by 180 degrees probably being in the normal direction and a second upside-down direction result indicative of the text line after being rotated by 180 degrees probably being in the direction upside-down with respect to the normal direction; and determining the direction of the document according to the first normal direction result, the first upside-down direction result, the second normal direction result and the second upside-down direction result.
-
公开(公告)号：US10769499B2
公开(公告)日：2020-09-08
申请号：US16179292
申请日：2018-11-02
Applicant: FUJITSU LIMITED
Inventor： Meng Zhang , Rujie Liu , Jun Sun
Abstract: A method and apparatus for removing black eyepits and sunglasses in first actual scenario data having an image containing a face acquired from an actual scenario, to obtain second actual scenario data; counting a proportion of wearing glasses in the second actual scenario data; dividing original training data composed of an image containing a face into wearing-glasses and not-wearing-glasses first and second training data, where a proportion of wearing glasses in the original training data is lower than a proportion in the second actual scenario data; generating wearing-glasses third training data based on glasses data and the second training data; generating fourth training data in which a proportion of wearing glasses is equal to the proportion of wearing glasses in the second actual scenario data, based on the third training data and the original training data; and training a face recognition model based on the fourth training data.
-
公开(公告)号：US20180260943A1
公开(公告)日：2018-09-13
申请号：US15838591
申请日：2017-12-12
Applicant: Fujitsu Limited
CPC classification number: G06T5/50 , G06T1/0007 , G06T3/4007 , G06T3/4038 , G06T5/002 , G06T7/11 , G06T7/33 , G06T2200/32 , G06T2207/20221 , G06T2210/21
Abstract: An image processing apparatus and an image processing method where the apparatus includes: a seam line acquisitor configured to acquire a seam line of a first image in images to be stitched; a segmenter configured to segment, in an extension direction of the seam line of the first image, a center region including the seam line in the first image into blocks, where an intersection point of a block boundary with the seam line of the first image is located in a strong gradient region; a matcher configured to perform keypoint matching based on the intersection point to find a coordinate point corresponding to the intersection point in a position region corresponding to the seam line in a second image in the images to be stitched; and a fuser configured to fuse the first image with the second image based on the intersection point and the coordinate point.
-
44.发明授权公开(公告)号：US09697444B2
公开(公告)日：2017-07-04
申请号：US14448049
申请日：2014-07-31
Applicant: FUJITSU LIMITED
Inventor： Chunpeng Wu , Wei Fan , Yuan He , Jun Sun
CPC classification number: G06K9/6272 , G06K9/4628 , G06K9/6267 , G06N3/0454 , G06N3/0481
Abstract: The present invention relates to a convolutional-neural-network-based classifier, a classifying method by using a convolutional-neural-network-based classifier and a method for training the convolutional-neural-network-based classifier. The convolutional-neural-network-based classifier comprises: a plurality of feature map layers, at least one feature map in at least one of the plurality of feature map layers being divided into a plurality of regions; and a plurality of convolutional templates corresponding to the plurality of regions respectively, each of the convolutional templates being used for obtaining a response value of a neuron in the corresponding region.
-
公开(公告)号：US09524559B2
公开(公告)日：2016-12-20
申请号：US14946147
申请日：2015-11-19
Applicant: FUJITSU LIMITED
CPC classification number: G06T7/0081 , G06K9/4647 , G06K2209/01 , G06T5/005 , G06T7/11 , G06T7/194 , G06T11/60 , G06T2207/10024 , G06T2207/30176
Abstract: An image processing device includes: an image acquiring unit for acquiring an image containing pixels; a picture searching unit for searching for a picture region in the image; a background acquiring unit for performing a background connected region acquiring operation on a non-picture region of the image in which the picture region is not included and the picture region respectively, to obtain a non-picture background connected region and a picture background connected region respectively; a foreground acquiring unit for removing the non-picture background connected region and the picture background connected region from the non-picture region and the picture region respectively, to obtain a non-picture foreground region of the non-picture region and a picture foreground region of the picture region respectively; and a merging unit for merging the non-picture foreground region of the non-picture region and the picture foreground region of the picture region to obtain an ultimate image foreground region.
Abstract translation: 一种图像处理装置，包括：图像获取单元，用于获取包含像素的图像; 图像搜索单元，用于搜索图像中的图像区域; 背景获取单元，用于对不包括图像区域的图像的非图像区域和图像区域分别执行背景连接区域获取操作，以获得非图像背景连接区域和图像背景连接区域 分别; 从非图像区域和图像区域分别去除非图像背景连接区域和图像背景连接区域的前景获取单元，以获得非图像区域的非图像前景区域和图像前景区域 的图片区域; 以及用于合并非图像区域的非图像前景区域和图像区域的图像前景区域的合并单元，以获得最终图像前景区域。
-
Patent Agency Ranking
公开(公告)号：US09317766B2
公开(公告)日：2016-04-19
申请号：US14563335
申请日：2014-12-08
Applicant: FUJITSU LIMITED
CPC classification number: G06K9/3275 , G06K9/4638 , G06K2009/363 , G06T3/0031 , G06T7/13 , G06T7/181
Abstract: A method and a device for extracting a distorted straight line from an image. The method includes performing a line segment detection process on the image; for each line segment detected, finding adjacent line segments having a low non-collinear degree with a current line segment, so as to combine them together to obtain one or more line segment combinations; and extracting the distorted straight line according to the line segment combination.
Abstract translation: 一种用于从图像中提取失真直线的方法和装置。 该方法包括对图像执行线段检测处理; 对于检测到的每个线段，找到具有与当前线段的低非共线度的相邻线段，以便将它们组合在一起以获得一个或多个线段组合; 并根据线段组合提取失真的直线。
-
公开(公告)号：US09294655B2
公开(公告)日：2016-03-22
申请号：US14561786
申请日：2014-12-05
Applicant: FUJITSU LIMITED
IPC: H04N1/407
CPC classification number: H04N1/4072 , H04N2201/0458
Abstract: An apparatus for and a method of processing a document image are provided. The apparatus comprises: an estimation unit for estimating a brightness image from the document image; and a correction unit for correcting the brightness image by using brightness values of at least a part of edge pixels which lie on or in the adjacency of edges of the brightness image in parallel with x direction, wherein directions of neighboring two edges of the brightness image are set to be x, y directions respectively, and wherein compared with x direction, brightness values of pixels of the brightness image change relatively slightly or do not change along y direction; wherein the correction unit performs interpolation on a straight line extending along y direction by using the brightness values of the edge pixels on the straight line, thereby correcting brightness values of other pixels on the straight line.
Abstract translation: 提供了一种用于处理文档图像的装置和方法。 该装置包括：估计单元，用于从文档图像估计亮度图像; 以及校正单元，用于通过使用与x方向平行的亮度图像的边缘或邻近的边缘像素的至少一部分的亮度值来校正亮度图像，其中亮度图像的相邻两个边缘的方向 分别设置为x，y方向，并且与x方向相比，亮度图像的像素的亮度值相对稍微变化或不沿着y方向变化; 其中所述校正单元通过使用所述直线上的边缘像素的亮度值，沿着沿y方向延伸的直线进行插值，从而校正所述直线上的其他像素的亮度值。
-
48.发明授权Image processing device, image processing method, scanner and storage medium 有权图像处理装置，图像处理方法，扫描仪和存储介质公开(公告)号：US09239954B2
公开(公告)日：2016-01-19
申请号：US13906854
申请日：2013-05-31
Applicant: FUJITSU LIMITED
Inventor： Pan Pan , Yuan He , Jun Sun , Satoshi Naoi
CPC classification number: G06K9/00463 , G06K9/32 , G06K9/4638 , G06K2009/485 , G06K2209/01 , G06T5/002 , G06T5/40 , G06T7/12 , G06T7/181 , G06T2207/10008 , G06T2207/20192 , G06T2207/30176
Abstract: The disclosure provides an image processing device, image processing method, scanner and storage medium. The image processing device is used for tracing a boundary of an object image in an image, the boundary being continuous and the rate of change in slope between adjacent points on the boundary being slow. The image processing device includes: a boundary estimation unit, adapted to estimate the location of the boundary of the object image; an interfering gradient processing unit, adapted to process an interfering gradient near the estimated boundary, so as to reduce the interfering gradient or remove the interfering gradient from the image; and a boundary tracing unit, adapted to trace the boundary in the image having the interfering gradient processed. By using the technique of the disclosure, the accuracy of tracing a boundary of an image is improved significantly.
Abstract translation: 本公开提供了图像处理装置，图像处理方法，扫描仪和存储介质。 图像处理装置用于跟踪图像中的对象图像的边界，边界是连续的，边界上的相邻点之间的斜率变化率较慢。 图像处理装置包括：边界估计单元，适于估计对象图像的边界的位置; 干扰梯度处理单元，适于处理估计边界附近的干扰梯度，以便减少干扰梯度或从图像中去除干扰梯度; 以及边界跟踪单元，适于追踪处理了干涉梯度的图像中的边界。 通过使用本公开的技术，跟踪图像边界的准确性得到显着改善。
-
49.发明授权Image processing device, image processing method and apparatus for high precision document corners extraction 有权图像处理装置，图像处理方法和高精度文档角提取装置公开(公告)号：US09129385B2
公开(公告)日：2015-09-08
申请号：US13853544
申请日：2013-03-29
Applicant: FUJITSU LIMITED
Inventor： Shufu Xie , Yuan He , Jun Sun , Hao Yu , Satoshi Naoi
CPC classification number: G06T7/0085 , G06K9/3208 , G06K9/3233 , G06T7/12 , G06T7/136 , G06T2207/20164 , H04N1/00681
Abstract: The present invention provides an image processing device, an image processing method and an apparatus so as to improve at least the precision of extracting document corners in image processing performed on an image captured for a document. The image processing device includes: an extracting unit for extracting boundaries of a document in a first direction and roughly-detected document corners, where the first direction is a horizontal direction or a vertical direction of the document image; a determining unit for determining candidate page corners on the boundaries in the first direction around the roughly-detected document corners; and a selecting unit for determining document corners of the document among the candidate page corners. With the foregoing technology of the invention, more precise document corners can be extracted, a better effect of image processing can be obtained, and applications in the field of image processing are possible.
Abstract translation: 本发明提供一种图像处理装置，图像处理方法和装置，以便至少提高对针对文档拍摄的图像执行的图像处理中提取文档角的精度。 图像处理装置包括：提取单元，用于提取文档在第一方向上的边界和大致检测到的文档角，其中第一方向是文档图像的水平方向或垂直方向; 确定单元，用于确定围绕大致检测到的文档角的第一方向上的边界上的候选页角; 以及选择单元，用于确定候选页角中的文档的文档角。 利用本发明的上述技术，可以提取更精确的文档角，可以获得更好的图像处理效果，并且在图像处理领域中的应用是可能的。
-
公开(公告)号：US20150138610A1
公开(公告)日：2015-05-21
申请号：US14547472
申请日：2014-11-19
Applicant: FUJITSU LIMITED
IPC: H04N1/387
CPC classification number: G06T7/0085 , G06T3/0031 , G06T5/006 , H04N1/387 , H04N2201/0081 , H04N2201/0434
Abstract: Embodiments of the present invention provide a device and method for correcting a document image and a scanner. Wherein the device includes: an extracting unit configured to extract boundaries in a first direction of the document image and extract lines in the first direction according to a content of the document image, a filtering unit configured to filter the extracted lines, a constructing unit configured to extend and adjust the filtered lines and construct a correcting mesh, and a correcting unit configured to perform correcting according to the correcting mesh. An accurate correcting model can be constructed by taking document boundaries and document contents into account in constructing the correcting model and constructing a correcting mesh after filtering, extending and adjusting the extracted lines, thereby effectively eliminating distortion in the document image.
Abstract translation: 本发明的实施例提供了一种用于校正文档图像和扫描仪的装置和方法。 其中，所述设备包括：提取单元，被配置为根据所述文档图像的内容提取所述文档图像的第一方向上的边界并且提取所述第一方向上的线;滤波单元，被配置为对所提取的线进行滤波;构造单元， 扩展和调整滤波后的线并构造校正网格;以及校正单元，被配置为根据校正网格执行校正。 可以通过在构建校正模型时考虑文档边界和文档内容，并在过滤，扩展和调整提取的线之后构建校正网格，从而有效消除文档图像中的失真，从而构建精确的校正模型。
-
-
-
-
-
-
-
-
-
Search Results
51
records
(took 0.024 seconds)
