-
公开(公告)号：US09965678B2
公开(公告)日：2018-05-08
申请号：US15197595
申请日：2016-06-29
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Gang Fang
CPC classification number: G06K9/00456 , G06K9/00449 , G06T7/13 , G06T2207/20224 , G06T2207/30176 , G06T2207/30242 , G06T2210/12
Abstract: A table and flowchart detection method is disclosed. First, based on connected component analysis and the sizes of the connected components, a target connected component that corresponds to possible elements of table or flowchart is detected in the input image. The target connected component is broken into corners and edges that connect the corners. Based on the relationship between the corners and edges, it is determined whether the target connected component is a table or a flowchart. For table detection, the edges and corners are linked into horizontal sets and vertical sets, and based on corner counts in the horizontal sets and vertical sets, it is determined whether the target connected component is a table. For flowchart detection, the boundary boxes and connecting lines between boundary boxes are detected to determine whether the target connected component is a flowchart.
-
Patent Agency Ranking
公开(公告)号：US09715624B1
公开(公告)日：2017-07-25
申请号：US15084353
申请日：2016-03-29
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Gang Fang
CPC classification number: G06K9/00449 , G06K9/00456 , G06K9/52 , G06K9/6267 , G06T7/0042 , G06T7/0079 , G06T7/11 , G06T7/60 , G06T2207/20021 , G06T2207/20144 , G06T2207/30176
Abstract: In a document image segmentation method, pixels of the image are classified into different types such as background, text, table, etc., to generate an initial segmentation map. The initial segmentation map is processed multiple rounds. In each round, a working map is divided into 2×2 pixel blocks; based on pixel types in the block, a corresponding pixel in a combined map is assigned a type, and pixels in a corresponding block in the segmentation map are modified either to change some background pixels to other types or keep them unchanged. The initial segmentation map is used as the working map in the first round, and the combined map of the last round is used as the working map for the next round. After a number of rounds, remaining background pixels of the segmentation map are changed to other types based on the types of their neighboring areas.
-
公开(公告)号：US20170177931A1
公开(公告)日：2017-06-22
申请号：US14975531
申请日：2015-12-18
Applicant: Konica Minolta Laboratory U.S.A., Inc.
Inventor： Gang Fang
CPC classification number: G06K9/00422 , G06K9/4604 , G06K9/52 , G06K9/6218 , G06T3/40 , G06T5/006 , G06T7/0085 , G06T7/13 , G06T2207/20112 , G06T2207/20144 , G06T2207/20164
Abstract: A method for image processing, including: obtaining an image including a writing board and a background external to the writing board; detecting a plurality of lines within the image; determining, based on the plurality of lines, a plurality of corners of the writing board within the image; and correcting a perspective of the writing board by applying a transformation to the image based on the plurality of corners.
-
公开(公告)号：US09454688B1
公开(公告)日：2016-09-27
申请号：US14803349
申请日：2015-07-20
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Gang Fang
CPC classification number: G06K7/1417 , G06K7/10722 , G06K19/06037
Abstract: A 2D color barcode decoding method is disclosed. The barcode includes a 2D array of data cells, corner locators, and border reference cells. Each data cell and reference cell has one of four primary colors (e.g. CMYK or CMWK). The reference cells, which have known colors, are used to calculate the channel offset (a spatial offset) of each primary color and the reference color values of each primary color. The reference cells are also used to calculate a color conversion matrix between color intensity (RGB) values and the primary color. Pixel-color probabilities are calculated from the pixel color intensity values using the color conversion matrix. The color of each data cell is determined using the pixel-color probabilities, the pixel color intensity values, the reference color intensity values, and the channel offset.
Abstract translation: 公开了一种2D彩色条形码解码方法。 条形码包括数据单元，角定位器和边框参考单元的2D阵列。 每个数据单元和参考单元具有四种基色之一（例如CMYK或CMWK）。 具有已知颜色的参考单元用于计算每个原色的通道偏移（空间偏移）和每个基色的参考颜色值。 参考单元还用于计算颜色强度（RGB）值和原色之间的颜色转换矩阵。 使用颜色转换矩阵从像素颜色强度值计算像素色彩概率。 使用像素颜色概率，像素颜色强度值，参考颜色强度值和通道偏移来确定每个数据单元的颜色。
-
公开(公告)号：US20160086071A1
公开(公告)日：2016-03-24
申请号：US14956207
申请日：2015-12-01
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Gang Fang
IPC: G06K19/06
CPC classification number: G06K19/0614 , G06K7/1417 , G06K7/1426 , G06K19/06037 , G06K2019/06225
Abstract: A 2D color barcode layout is disclosed. The barcode includes a 2D array of data cells, four corner locators, and border reference cells forming four borders between the corner locators that substantially surround the array of data cells. Each data cell and border reference cell has one of four primary colors (e.g. CMYK). Most border reference cells have the same size as the data cells, except for yellow ones which are longer. The border reference cells form a repeating color sequence along the borders, and are used during decoding to calculate (1) the channel offset (a spatial offset) of each primary color at different locations along the borders and (2) the reference (average) color values of each primary color. During decoding, the color values of each data cell is measured while taking into account channel offset which is calculated by interpolating the channel offset of the border reference cells.
-
公开(公告)号：US09275030B1
公开(公告)日：2016-03-01
申请号：US14502820
申请日：2014-09-30
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Gang Fang
CPC classification number: G06F17/245 , G06K9/00449 , G06K9/346 , G06K9/4633 , G06K9/6205 , G06T5/005 , G06T5/30 , G06T2207/10008 , G06T2207/20061 , G06T2207/30176 , G06T2210/12
Abstract: Methods for removing vertical and horizontal lines from a document image. The horizontal line removal method includes: for a column of black pixels at each horizontal position along the line, removing them if their maximum stroke width is less than the median value of maximum stroke widths in a small window centered at that horizontal position; Remove connected components remaining in the horizontal line bounding box that do not extend significantly above or below the bounding box boundaries; and Perform closing operation to join broken pieces of character strokes caused by underline removal. This method preserves character strokes while removing underlines. The vertical line removal method includes: for vertical lines that have large height to width ratio, remove parts of such lines that are not at intersection of with horizontal or near-horizontal lines; remove all remaining connected components that touch neither left nor right boundary of the bounding box.
Abstract translation: 从文档图像中删除垂直和水平线的方法。 水平线移除方法包括：对于沿着线的每个水平位置的一列黑色像素，如果它们的最大行程宽度小于以该水平位置为中心的小窗口中的最大行程宽度的中值，则将其移除; 删除剩余在水平线边界框中的连接的组件，其不会显着地在边界框边界上方或下方延伸; 并执行关闭操作以加入由下划线删除导致的碎片的字符笔画。 此方法在删除下划线的同时保留字符笔画。 垂直线移除方法包括：对于具有高宽比的垂直线，去除与水平或近水平线交叉的这些线的部分; 删除所有剩下的连接的组件，这些组件不会触及边界框的左边界和右边界。
-
-
-
-
-
Search Results
16
records
(took 0.016 seconds)
