WO2017041600A1 - 一种汉信码特征图形检测方法及系统 - Google Patents

一种汉信码特征图形检测方法及系统 Download PDF

Info

Publication number
WO2017041600A1
WO2017041600A1 PCT/CN2016/092816 CN2016092816W WO2017041600A1 WO 2017041600 A1 WO2017041600 A1 WO 2017041600A1 CN 2016092816 W CN2016092816 W CN 2016092816W WO 2017041600 A1 WO2017041600 A1 WO 2017041600A1
Authority
WO
WIPO (PCT)
Prior art keywords
code
hanxin
line
data
point
Prior art date
Application number
PCT/CN2016/092816
Other languages
English (en)
French (fr)
Inventor
蒋声障
吴卫东
Original Assignee
福建联迪商用设备有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 福建联迪商用设备有限公司 filed Critical 福建联迪商用设备有限公司
Priority to EP16843538.6A priority Critical patent/EP3330887B1/en
Priority to BR112018004552-7A priority patent/BR112018004552A2/zh
Publication of WO2017041600A1 publication Critical patent/WO2017041600A1/zh
Priority to US15/895,986 priority patent/US10528781B2/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/24—Aligning, centring, orientation detection or correction of the image
    • G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
    • G06K7/1404—Methods for optical code recognition
    • G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
    • G06K7/1417—2D bar codes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
    • G06K7/1404—Methods for optical code recognition
    • G06K7/1439—Methods for optical code recognition including a method step for retrieval of the optical code
    • G06K7/1447—Methods for optical code recognition including a method step for retrieval of the optical code extracting optical codes from image or text carrying said optical code
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
    • G06K7/1404—Methods for optical code recognition
    • G06K7/1439—Methods for optical code recognition including a method step for retrieval of the optical code
    • G06K7/1452—Methods for optical code recognition including a method step for retrieval of the optical code detecting bar code edges

Definitions

  • the invention relates to the field of two-dimensional code recognition, in particular to a method and system for detecting a character pattern of a Hanxin code.
  • Hanxin code is a major science and technology plan of China's "10th Five-Year Plan". It is based on the in-depth study of 2D barcode information coding, error correction coding code and code map structure, and has developed independent intellectual property rights based on the actual needs of China's applications.
  • the two-dimensional barcode new code system the detection of the position detection pattern is one of the important steps in the two-dimensional code decoding step. In the two-dimensional code decoding process, the position detection pattern is first detected and positioned, and then the two-dimensional code can be performed. Decoding operation.
  • the position detection pattern of the Hanxin code has no rotational symmetry feature, when a certain rotation tilt occurs, it is difficult to detect the position detection pattern, because the tilt angle cannot be known in advance when decoding, so generally, the progressive scan is used. Detect position detection patterns. If the rotation angle of the two-dimensional code is large, the method of detecting the pattern of the position detection pattern may not be detected by the method of progressive scanning, because it is difficult to find the characteristic ratio of the position detection pattern of the Hanxin code during the line scanning process ( That is, the ratio of black, white, black, white, and black is 3:1:1:1:1), and the similarity is higher. Therefore, after progressive or column-by-column scanning, only 2 can be found. Position detection graphics, sometimes even a position detection pattern is not available.
  • the Chinese invention patent with the publication number CN103177235A discloses a recognition device and method for the Hanxin code in a complex background. Firstly, the image is roughly positioned according to the characteristics of the sub-region, and then the image is accurately positioned according to the scanning feature of the finder image. The specific steps are as follows: (3a) dividing the Hanxin code gray image into m ⁇ n sub-regions; (3b) calculating the contrast of each sub-region; (3c) calculating the linear scale features of each sub-region; (3d) screening the sub-regions to merge; 3e) After the coarse positioning is completed, the precise scanning is performed according to the scanning feature of the finder image. Although it has good anti-interference and robustness, it can accurately identify the bar code. However, because the calculated data volume is more and more algorithms are used, the recognition efficiency of Hanxin code needs to be improved, and the complexity needs to be reduced.
  • the technical problem to be solved by the present invention is to provide a method and system for detecting Han Wen code feature patterns with strong anti-interference ability and fast.
  • the technical solution adopted by the present invention is:
  • the invention has the advantages that the four vertices of the region where the Hanxin code is located are first searched by row-by-row column-by-column scanning, and the four boundary lines of the area where the Hanxin code is located are formed by the four vertices of the Hanxin code, and then Hanshin is formed.
  • the four boundary lines and two diagonal lines of the area where the code is located, and four characteristic line segments are found on the two diagonal lines, and the four characteristic line segments are the diagonal lines of the four position detection patterns of the Hanxin code, and finally
  • the boundary line and the data bit width of the position detection pattern of the Hanxin code are calculated. Even if the area where the Hanxin code is rotated, the position detection pattern of the Hanxin code can be quickly and accurately found, and the anti-interference ability is strong and the detection efficiency is high.
  • a Hanxin code feature graphic detection system includes a binarization module, a first search module, a formation module, a second search module, and a calculation module.
  • a binarization module for binarizing the received two-dimensional code image
  • a first searching module configured to scan the two-dimensional code image row by row by column by line to find four vertices of the region where the Hanxin code is located;
  • Forming a module configured to connect the four vertices to form four boundary lines and two diagonal lines in a region where the Hanxin code is located;
  • a second searching module configured to respectively search for four characteristic line segments and data lines of each characteristic line segment whose starting point is a vertex and the binarized value is continuous 1, 0, 1, 0, 1 on two diagonal lines end;
  • a calculation module configured to calculate a boundary line and a data bit width of the position detection pattern of the Hanxin code according to the start point and the end point of the feature line segment.
  • the invention has the advantages that the four vertices of the region where the Hanxin code is located are first searched by row-by-row scanning of the two-dimensional code image, and then four boundary lines and two regions of the region where the Hanxin code is located are formed by four vertices. The diagonal line is then used to find four characteristic line segments starting from the vertices of the two diagonal lines. The four characteristic line segments correspond to the diagonal lines of the Hanxin code position detection pattern, and are not affected by the rotation of the area where the Hanxin code is located. Strong anti-interference ability and high detection efficiency.
  • FIG. 1 is a flowchart of a method for detecting a character pattern of a Hanxin code according to Embodiment 1 of the present invention
  • FIG. 2 is a schematic diagram of row-by-row column-by-row scanning for finding four vertices in a region where a Hanxin code is located according to Embodiment 1 of the present invention
  • FIG. 3 is a schematic diagram of four boundary lines and two diagonal lines forming a region where a Hanshin code is formed according to four vertices according to Embodiment 1 of the present invention
  • FIG. 4 is a schematic diagram of finding four position detection patterns on two diagonal lines on the two diagonal lines according to the first embodiment of the present invention
  • FIG. 5 is a flowchart of a method for detecting a character pattern of a Hanxin code according to Embodiment 2 of the present invention.
  • FIG. 6 is a system block diagram of a Hanxin code feature pattern detecting system according to Embodiment 3 of the present invention.
  • FIG. 7 is a system block diagram of a Hanxin code feature pattern detecting system according to Embodiment 4 of the present invention.
  • Binarization module 2. First seeking module; 3. Forming module; 4. Second finding module; 5. Statistics module; 6. Analysis module; 7. Calculation module.
  • the most critical idea of the present invention is to first capture the four vertices of the region where the Hanxin code is located, and then find the ratio of the pixel points to consecutive 1 and continuous 0 on the two diagonal lines of the region where the Hanxin code is located.
  • the line code standard features a line segment of 3:1:1:1:1 or 1:1:1:1:3.
  • the line segment found is the diagonal of the Hanxin code position detection pattern, which is not subject to Hanxin code rotation. The influence of angle, strong anti-interference ability and high detection efficiency.
  • FIG. 1 to FIG. 5 a method for detecting a character pattern of a Hanxin code
  • the received two-dimensional code image is binarized, specifically:
  • the received two-dimensional code image is binarized according to the grayscale threshold.
  • the two-dimensional code image is scanned line by line by row to find the four vertices of the region where the Hanxin code is located, specifically:
  • the QR code image is scanned line by line.
  • the starting line data is white point.
  • the black point on the leftmost side is P1
  • the black point on the right side is P2;
  • the QR code image is scanned column by column from left to right.
  • the starting column data is white point.
  • the uppermost black point is P3, and the lowest black point is P4. ;
  • the QR code image is scanned line by line.
  • the starting line data is white point.
  • the leftmost black point is P5
  • the rightmost black point is P6. ;
  • the starting column data is white point when encountering a column.
  • the black dot at the top of the record is P7, and the black dot at the bottom is P8.
  • Predetermining the distance threshold calculating the distance between the two black points P1 and P2, P3 and P4, P5 and the two black points of any one of P6, P7 and P8, and determining whether the calculated distance is less than the distance threshold;
  • the four vertices of the Hanxin code are black dots. If the region where the Hanxin code is located has a rotation, the row or column scanned by the row-by-row column is black-pointed. The row or column, the black point on the row or column is ideally only one. In fact, if the vertices of the Han code pattern are damaged, there will be more than one black dot on the row or column, but it will be a continuous black dot.
  • the black point will exist intermittently within the width of the area where the Hanxin code is located, and the distance between the two black points that are farthest from each other on the line or column is much larger than the preset distance threshold.
  • the vertices are determined by the black points at the intersection of two intersecting rows and columns. The method has high decoding efficiency, strong anti-interference ability, and small error.
  • the two-dimensional code image is not decoded.
  • the received two-dimensional code image is an image containing the Hanxin code, which can be subsequently decoded, otherwise
  • the two-dimensional code image is decoded, and the method is reasonable, and the received two-dimensional code image is further determined to be an image about the Hanxin code, and the decoding success rate is high.
  • the similarity between the characteristic ratio and the standard feature ratio of the Hanxin code is less than the line proportional threshold.
  • the ratio of one characteristic ratio to the standard characteristic ratio of Hanxin code is 3:1:1:1:1
  • the similarity is within the proportional threshold range
  • the three characteristic ratios are in accordance with the Hanxin code standard. If the similarity of the feature ratio 1:1:1:1:3 is within the range of the proportional threshold, the two-dimensional code image is not decoded.
  • the received two-dimensional code image includes a Hanxin code, and the method is accurate.
  • calculating a boundary line of the position detection pattern of the Hanxin code according to the start point and the end point of the feature line segment specifically:
  • the square surrounded by the boundary line between the two Hanxin codes of the starting point and the calculated two straight lines is the boundary line of the position detection pattern of the Hanxin code.
  • the boundary line of the region where the Hanxin code is located is translated to obtain the boundary line of the position detection pattern of the Hanxin code, and the accuracy of the boundary line of the Hanxin code position detection pattern is improved.
  • calculating a data bit width of the position detection pattern of the Hanxin code according to the start point and the end point of the feature line segment specifically:
  • the boundary line of the position detection pattern of the Hanxin code includes 7 data bits, and the data bit width l of the position detection pattern of the Hanxin code is calculated according to the length d of the characteristic line segment, specifically:
  • one position detection pattern contains 7 data bits, so the data bit width is equal to the length of the boundary line of the position detection pattern divided by 7. The method is reasonable and the calculation is simple and rapid.
  • Embodiment 1 of the present invention is:
  • Binarizing the received two-dimensional code image specifically:
  • the two-dimensional code image is scanned line by line by row to find the four vertices of the region where the Hanxin code is located, specifically:
  • the QR code image is scanned line by line.
  • the starting line data is white point.
  • the black point on the leftmost side is P1
  • the black point on the right side is P2;
  • the QR code image is scanned column by column from left to right.
  • the starting column data is white point.
  • the uppermost black point is P3, and the lowest black point is P4. ;
  • the QR code image is scanned line by line.
  • the starting line data is white point.
  • the leftmost black point is P5
  • the rightmost black point is P6. ;
  • the QR code image is scanned column by column from right to left.
  • the starting column data is white point.
  • the black point of the record is P7, and the lowest black point is P8. ;
  • the preset distance threshold is 4, and four sets of black points P1 and P2, P3 and P4, P5 and P6, P7 and P8 are calculated. The distance between two black points in any one of the groups, and determine whether the calculated distance is less than the distance threshold;
  • the calculated distance is less than the distance threshold, taking the midpoint between P1 and P2, the midpoint between P3 and P4, the midpoint between P5 and P6, and between P7 and P8.
  • the midpoint of the four points is the area where the Hanxin code is located;
  • the midpoint between P1 and P3 is the four vertices of the area where the Hanxin code is located;
  • the four vertices are connected in pairs to form four boundary lines and two diagonal lines in the area where the Hanxin code is located;
  • the boundary line of the position detection pattern of the Hanxin code is calculated according to the start point and the end point of the characteristic line segment, and specifically:
  • the boundary formed by the boundary line between the two Hanxin codes in the starting point and the calculated two straight lines is the boundary line of the position detection pattern of the Hanxin code
  • the boundary line of the position detection pattern of the Hanxin code includes 7 data bits, and the data bit width l of the position detection pattern of the Hanxin code is calculated according to the length d of the characteristic line segment, specifically:
  • the second embodiment of the present invention is:
  • the ratio of one characteristic ratio to the standard characteristic ratio of Hanxin code is 3:1:1:1:1
  • the similarity is within the proportional threshold range
  • the three characteristic ratios are in accordance with the Hanxin code standard. If the similarity of the feature ratio 1:1:1:1:3 is within the range of the proportional threshold, the two-dimensional code image is not decoded;
  • a Hanxin code feature pattern detecting system includes a binarization module 1, a first finding module 2, a forming module 3, a second searching module 4, and a calculating module 7.
  • a binarization module 1 for binarizing the received two-dimensional code image
  • the first searching module 2 is configured to scan the two-dimensional code image row by row by column by line to find four vertices of the region where the Hanxin code is located;
  • the second searching module 4 is configured to respectively search for four characteristic line segments and each characteristic line segment composed of data whose starting point is a vertex and the binarized value is continuous 1, 0, 1, 0, 1 on two diagonal lines End point
  • the calculation module 7 is configured to calculate a boundary line and a data bit width of the position detection pattern of the Hanxin code according to the start point and the end point of the feature line segment.
  • the statistics module 5 and the analysis module 6 are further included.
  • the statistics module 5 is configured to count the number of consecutive 1, 0, 1, 0, and 1 from the starting point of the feature line segment to form a feature ratio
  • the analysis module 6 is configured to analyze whether the similarity between the feature ratio and the standard feature ratio of the Hanxin code is within a proportional threshold.
  • the statistical module 5 and the analysis module 6 determine whether the feature line segment is similar to the standard feature of the Hanxin code, and finally determine whether the received two-dimensional code image contains the Hanxin code to ensure the accuracy of the system decoding.
  • the third embodiment of the present invention is:
  • a Hanxin code feature pattern detecting system comprising a binarization module 1, a first finding module 2, a forming module 3, a second finding module 4, and a calculating module 7,
  • a binarization module 1 for binarizing the received two-dimensional code image
  • the first searching module 2 is configured to scan the two-dimensional code image row by row by column by line to find four vertices of the region where the Hanxin code is located;
  • the second searching module 4 is configured to respectively search for four characteristic line segments and each characteristic line segment composed of data whose starting point is a vertex and the binarized value is continuous 1, 0, 1, 0, 1 on two diagonal lines End point
  • the calculation module 7 is configured to calculate a boundary line and a data bit width of the position detection pattern of the Hanxin code according to the start point and the end point of the feature line segment.
  • the fourth embodiment of the present invention is:
  • a Hanxin code feature pattern detecting system comprises a binarization module 1, a first finding module 2, a forming module 3, a second finding module 4, a statistics module 5, an analysis module 6, and a calculation module 7,
  • a binarization module 1 for binarizing the received two-dimensional code image
  • the first searching module 2 is configured to scan the two-dimensional code image row by row by column by line to find four vertices of the region where the Hanxin code is located;
  • the second searching module 4 is configured to respectively search for four characteristic line segments and each characteristic line segment composed of data whose starting point is a vertex and the binarized value is continuous 1, 0, 1, 0, 1 on two diagonal lines End point
  • the statistics module 5 is configured to count the number of consecutive 1, 0, 1, 0, and 1 from the starting point of the feature line segment to form a feature ratio
  • the analysis module 6 is configured to analyze whether the similarity between the feature ratio and the standard feature ratio of the Hanxin code is within a proportional threshold range;
  • the calculation module 7 is configured to calculate a boundary line and a data bit width of the position detection pattern of the Hanxin code according to the start point and the end point of the feature line segment.
  • the present invention provides a Hanxin code feature pattern detecting method and system, which obtains four vertices and four vertices of a region where a Hanxin code is located by progressively column-by-row scanning of a received two-dimensional code image. The selection is not affected by the rotation of the area where the Hanxin code is located. The four vertices determine the four boundary lines and two diagonal lines of the area where the Hanxin code is located, and find the Hanxin code position detection pattern on the diagonal line. Diagonally, the method fully utilizes the features of the Hanxin code position detection pattern, and the method has strong anti-interference, high detection efficiency and high speed.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Electromagnetism (AREA)
  • General Health & Medical Sciences (AREA)
  • Toxicology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)
  • Character Discrimination (AREA)

Abstract

本发明提供了一种汉信码特征图形检测方法及系统，所述方法为：对接收到的二维码图像进行二值化；对二维码图像逐行逐列扫描寻找出汉信码所在区域的四个顶点；将所述的四个顶点两两连接起来形成汉信码所在区域的四条边界线及两条对角线；在两条对角线上分别寻找出起点为顶点且二值化数值为连续的1、0、1、0、1的数据组成的四条特征线段及每条特征线段的终点；根据所述的特征线段的起点和终点计算汉信码的位置探测图形的边界线及数据位宽度。所述方法防干扰能力强，且可快速地寻找和定位汉信码的位置探测图形。

Description

一种汉信码特征图形检测方法及系统 技术领域
本发明涉及二维码识别领域，特别涉及一种汉信码特征图形检测方法及系统。
背景技术
汉信码是我国“十五”国家重大科技的计划，是在深入研究二维条码信息编码、纠错编译码、码图结构的基础上，结合我国应用的实际需求开发的具有自主知识产权的二维条码新码制，其位置探测图形的检测是二维码解码步骤中的重要步骤之一，在二维码解码过程中，首先要进行位置探测图形的检测定位，之后才能进行二维码解码操作。
由于汉信码的位置探测图形没有旋转对称的特征，当出现一定旋转倾斜时，检测位置探测图形会遇到困难，因为在解码时，并不能事先知道倾斜角度，因此一般都通过逐行扫描来检测位置探测图形。如果二维码旋转角度较大，采用逐行扫描的办法通常会出现检测不到位置探测图形特征的情况，因为在行扫描的过程中比较难找到与汉信码的位置探测图形的特征比例(即黑、白、黑、白、黑的宽度比为3:1:1:1:1)相似度较高的比例数据，因此经逐行或者逐列的扫描后，会出现只能找到2个位置探测图形，有时甚至一个位置探测图形都没有的情况。
公开号为CN103177235A的中国发明专利公开了一种复杂背景下汉信码的识别装置及方法，先根据子区域特征对图像粗定位，再根据寻像图形扫描特征对图像精确定位，具体步骤为：(3a)将汉信码灰度图像分割为m×n个子区域；(3b)计算每个子区域的对比度；(3c)计算每个子区域的线性尺度特征；(3d)对子区域筛选合并；(3e)完成粗定位后，根据寻像图形扫描特征进行精确定位。虽然具有良好的抗干扰性和鲁棒性，能准确地识别条码，但是因为计算的数据量比较多，运用的算法比较多，因此汉信码的识别效率还有待提高，复杂度还有待降低。
发明内容
本发明所要解决的技术问题是：提供一种防干扰能力强且快速的汉信码特征图形检测方法及系统。
为了解决上述技术问题，本发明采用的技术方案为：
一种汉信码特征图形检测方法，
对接收到的二维码图像进行二值化；
对二维码图像逐行逐列扫描寻找出汉信码所在区域的四个顶点；
将所述的四个顶点两两连接起来形成汉信码所在区域的四条边界线及两条对角线；
在两条对角线上分别寻找出起点为顶点且二值化数值为连续的1、0、1、0、1的数据组成的四条特征线段及每条特征线段的终点；
根据所述的特征线段的起点和终点计算汉信码的位置探测图形的边界线及数据位宽度。
本发明的有益效果在于：先通过逐行逐列扫描寻找出汉信码所在区域的四个顶点，通过汉信码的四个顶点来形成汉信码所在区域的四条边界线，然后形成汉信码所在区域的四条边界线和两条对角线，并在两条对角线上寻找出四条特征线段，所述四条特征线段即为汉信码的四个位置探测图形的对角线，最终计算出汉信码的位置探测图形的边界线及数据位宽度，即使汉信码所在区域旋转，也能快速准确的将汉信码的位置探测图形寻找出来，抗干扰能力强，检测效率高。
一种汉信码特征图形检测系统，包括二值化模块、第一寻找模块、形成模块、第二寻找模块、计算模块，
二值化模块，用于对接收到的二维码图像进行二值化；
第一寻找模块，用于对二维码图像逐行逐列扫描寻找出汉信码所在区域的四个顶点；
形成模块，用于将所述的四个顶点两两连接起来形成汉信码所在区域的四条边界线及两条对角线；
第二寻找模块，用于在两条对角线上分别寻找出起点为顶点且二值化数值为连续的1、0、1、0、1的数据组成的四条特征线段及每条特征线段的终点；
计算模块，用于根据所述的特征线段的起点和终点计算汉信码的位置探测图形的边界线及数据位宽度。
本发明的有益效果在于：先通过对二维码图像的逐行逐列扫描寻找出汉信码所在区域的四个顶点，然后通过四个顶点形成汉信码所在区域的四条边界线及两条对角线，然后以两条对角线的顶点为起点寻找四条特征线段，这四条特征线段对应的就是汉信码位置探测图形的对角线，不受汉信码所在区域是否旋转的影响，防干扰能力强，检测效率高。
附图说明
图1为本发明实施例一的汉信码特征图形检测方法的流程图；
图2为本发明实施例一的逐行逐列扫描寻找汉信码所在区域四个顶点的示意图；
图3为本发明实施例一的根据四个顶点形成汉信码所在区域的四条边界线及两条对角线的示意图；
图4为本发明实施例一的在两条对角线上寻找四条特征线段得到四个位置探测图形的示意图；
图5为本发明实施例二的汉信码特征图形检测方法的流程图；
图6为本发明实施例三的汉信码特征图形检测系统的系统框图；
图7为本发明实施例四的汉信码特征图形检测系统的系统框图。
标号说明：
1、二值化模块；2、第一寻找模块；3、形成模块；4、第二寻找模块；5、统计模块；6、分析模块；7、计算模块。
具体实施方式
本发明最关键的构思在于：先捕捉汉信码所在区域的四个顶点，然后在汉信码所在区域的两条对角线上寻找像素点为连续的1和连续的0的比例满足汉 信码标准特征比例3:1:1:1:1或1:1:1:1:3的线段，寻找到的线段即为汉信码位置探测图形的对角线，不受汉信码旋转角度的影响，防干扰能力强，检测效率高。
本发明的具体实施方式为：
请参照图1至图5，一种汉信码特征图形检测方法，
对接收到的二维码图像进行二值化；
对二维码图像逐行逐列扫描寻找出汉信码所在区域的四个顶点；
将所述的四个顶点两两连接起来形成汉信码所在区域的四条边界线及两条对角线；
在两条对角线上分别寻找出起点为顶点且二值化数值为连续的1、0、1、0、1的数据组成的四条特征线段及每条特征线段的终点；
根据所述的特征线段的起点和终点计算汉信码的位置探测图形的边界线及数据位宽度。
进一步的，对接收到的二维码图像进行二值化，具体为：
采用最大类间方差法或者平均值法计算接收到的二维码图像的灰度阀值；
根据所述灰度阀值对接收到的二维码图像进行二值化。
由上述描述可知，采用最大类间方差法计算灰度阀值具有可减少背景色对前景色的影响的优点，防错分能力强；采用平均值法计算灰度阀值具有计算方法简便快速的优点，因此所述方法快速直接，误差小。
请参见图2，进一步的，对二维码图像逐行逐列扫描寻找出汉信码所在区域的四个顶点，具体为：
从上至下对二维码图像逐行扫描，起始的行数据中均为白点，当遇到一行数据中有黑点时，记录最左边的黑点为P1，最右边的黑点为P2；
从左到右对二维码图像逐列扫描，起始的列数据中均为白点，当遇到一列数据中有黑点时，记录最上的黑点为P3，最下的黑点为P4；
从下至上对二维码图像逐行扫描，起始的行数据中均为白点，当遇到一行数据中有黑点时，记录最左边的黑点为P5，最右边的黑点为P6；
从右到左对二维码图像逐列扫描，起始的列数据中均为白点，当遇到一列 数据中有黑点时，记录最上的黑点为P7，最下的黑点为P8；
预设距离阀值，计算四组黑点P1和P2、P3和P4、P5和P6、P7和P8中任意一组的两个黑点的距离，并判断计算的距离是否小于距离阀值；
若计算的距离小于距离阀值，则取P1和P2之间的中点、P3和P4之间的中点、P5和P6之间的中点、P7和P8之间的中点为汉信码所在区域的四个顶点；
若计算的距离大于等于距离阀值，则取P1和P3之间的中点、P4和P5之间的中点、P6和P8之间的中点、P7和P2之间的中点为汉信码所在区域的四个顶点。
由上述描述可知，汉信码的四个顶点均为黑点，若汉信码所在区域有发生旋转，则逐行逐列扫描到的由全是白点的行或者列到遇到有黑点的行或者列时，该行或者列上的黑点理想状态下只有一个，实际上若汉信码图形顶点破损，则该行或者列上的黑点就不止一个，但是会是连续的黑点，取这些连续的黑点的中点且通过距离阀值来消除汉信码图形顶点破损对汉信码顶点寻找造成的影响；若汉信码所在区域未发生旋转，则该行或者列上的黑点会在汉信码所在区域宽度范围内断续存在，且改行或者列上的相距最远的两个黑点之间的距离远大于预设的距离阀值，此时汉信码所在区域的顶点由两条相交的行和列相交处的黑点决定，所述方法解码效率高，防干扰能力强，且误差小。
进一步的，还包括：
预设比例阀值，从特征线段的起点开始统计连续的1、0、1、0、1的个数组成特征比例；
分析所述特征比例与汉信码标准特征比例的相似度是否在比例阀值范围内，所述汉信码标准特征比例为3:1:1:1:1或1:1:1:1:3；
若所述特征比例与汉信码标准特征比例的相似度不在比例阀值范围内，则不对所述二维码图像进行解码。
由上述描述可知，在两条对角线上寻找到四个特征线段后，添加由四个特征线段统计得到的四个特征比例是否与汉信码标准特征比例3:1:1:1:1或1:1:1:1:3的相似度在比例阀值范围内，如果为汉信码，则四个特征比例中有三个特征比例与汉信码标准特征比例1:1:1:1:3相似，有一个特征比例与汉信码标准 特征比例3:1:1:1:1相似，若四个特征比例满足这个条件，则接收到的二维码图像为包含汉信码的图像，可以对其进行后续的解码，否则不对所述二维码图像进行解码，所述方法合理，进一步确定所接收到的二维码图像为关于汉信码的图像，解码成功率高。
进一步的，分析所述特征比例与汉信码标准特征比例的相似度是否在比例阀值范围内，具体为：
将所述特征比例的起始数据转换为与汉信码标准特征比例起始数据相同的数据，并将特征比例的所有数据等比例转换得到转换后的特征比例；
计算转换后的特征比例中除起始数据外的其他数据与汉信码标准特征比例对应位上的数据的差值并取绝对值；
若每个位对应的绝对值均小于比例阀值，则所述的特征比例与汉信码标准特征比例的相似度小于行比例阀值。
由上述描述可知，通过将特征比例的起始数据转换为与汉信码标准特征比例相同的数据，并对特征比例除起始数据外的其他数据进行等比例转换，最后取特征比例与汉信码标准特征比例对应位上的数据的差值的绝对值与预设的比例阀值进行比较，相似度分析过程简便直接快速。
进一步的，还包括：
在四个特征比例中，若不满足有一个特征比例与汉信码标准特征比例3:1:1:1:1的相似度在比例阀值范围内，且三个特征比例与汉信码标准特征比例1:1:1:1:3的相似度在比例阀值范围内，则不对所述二维码图像进行解码。
由上述描述可知，如果满足上述条件，则接收到的二维码图像中包含汉信码，所述方法准确。
请参见图4，进一步的，根据所述的特征线段的起点和终点计算汉信码的位置探测图形的边界线，具体为：
计算与过所述特征线段起点的两条汉信码所在区域的边界线平行且穿过特征线段终点的两条直线；
过所述起点的两条汉信码所在区域的边界线与计算得到的两条直线所围成的正方形即为汉信码的位置探测图形的边界线。
由上述描述可知，根据特征线段的起点和终点，对汉信码所在区域的边界线平移来得到汉信码的位置探测图形的边界线，提高汉信码位置探测图形边界线的准确性。
进一步的，根据所述的特征线段的起点和终点计算汉信码的位置探测图形的数据位宽度，具体为：
根据所述的特征线段的起点和终点计算得到所述特征线段的长度d；
已知汉信码的位置探测图形的边界线上包含7个数据位，根据所述特征线段的长度d计算汉信码的位置探测图形的数据位宽度l，具体为：
Figure PCTCN2016092816-appb-000001
由上述描述可知，通过特征线段的长度和得到位置探测图形的边界线的长度，一个位置探测图形上包含7个数据位，因此数据位宽等于位置探测图形的边界线的长度除以7得到，所述方法合理，计算简便快速。
请参照图1至图4，本发明的实施例一为：
对接收到的二维码图像进行二值化，具体为：
采用最大类间方差法计算接收到的二维码图像的灰度阀值；
根据所述灰度阀值对接收到的二维码图像进行二值化；
请参见图2，对二维码图像逐行逐列扫描寻找出汉信码所在区域的四个顶点，具体为：
从上至下对二维码图像逐行扫描，起始的行数据中均为白点，当遇到一行数据中有黑点时，记录最左边的黑点为P1，最右边的黑点为P2；
从左到右对二维码图像逐列扫描，起始的列数据中均为白点，当遇到一列数据中有黑点时，记录最上的黑点为P3，最下的黑点为P4；
从下至上对二维码图像逐行扫描，起始的行数据中均为白点，当遇到一行数据中有黑点时，记录最左边的黑点为P5，最右边的黑点为P6；
从右到左对二维码图像逐列扫描，起始的列数据中均为白点，当遇到一列数据中有黑点时，记录最上的黑点为P7，最下的黑点为P8；
预设距离阀值为4，计算四组黑点P1和P2、P3和P4、P5和P6、P7和P8 中任意一组的两个黑点的距离，并判断计算的距离是否小于距离阀值；
从图2中可以看出，计算的距离小于距离阀值，则取P1和P2之间的中点、P3和P4之间的中点、P5和P6之间的中点、P7和P8之间的中点为汉信码所在区域的四个顶点；
只有当汉信码所在区域没有发生旋转时，计算的距离大于等于距离阀值，则取P1和P3之间的中点、P4和P5之间的中点、P6和P8之间的中点、P7和P2之间的中点为汉信码所在区域的四个顶点；
请参见图3，将所述的四个顶点两两连接起来形成汉信码所在区域的四条边界线及两条对角线；
在两条对角线上分别寻找出起点为顶点且二值化数值为连续的1、0、1、0、1的数据组成的四条特征线段及每条特征线段的终点；
请参见图4，根据所述的特征线段的起点和终点计算汉信码的位置探测图形的边界线，具体为：
计算与过所述特征线段起点的两条汉信码所在区域的边界线平行且穿过特征线段终点的两条直线；
过所述起点的两条汉信码所在区域的边界线与计算得到的两条直线所围成的正方形即为汉信码的位置探测图形的边界线；
根据所述的特征线段的起点和终点计算汉信码的位置探测图形的数据位宽度，具体为：
根据所述的特征线段的起点和终点计算得到所述特征线段的长度d；
已知汉信码的位置探测图形的边界线上包含7个数据位，根据所述特征线段的长度d计算汉信码的位置探测图形的数据位宽度l，具体为：
Figure PCTCN2016092816-appb-000002
请参照图5，本发明的实施例二为：
对接收到的二维码图像进行二值化；
对二维码图像逐行逐列扫描寻找出汉信码所在区域的四个顶点；
将所述的四个顶点两两连接起来形成汉信码所在区域的四条边界线及两条 对角线；
在两条对角线上分别寻找出起点为顶点且二值化数值为连续的1、0、1、0、1的数据组成的四条特征线段及每条特征线段的终点；
预设比例阀值，从特征线段的起点开始统计连续的1、0、1、0、1的个数组成特征比例；
分析所述特征比例与汉信码标准特征比例的相似度是否在比例阀值范围内，所述汉信码标准特征比例为3:1:1:1:1或1:1:1:1:3，具体为：
将所述特征比例的起始数据转换为与汉信码标准特征比例起始数据相同的数据，并将特征比例的所有数据等比例转换得到转换后的特征比例；
计算转换后的特征比例中除起始数据外的其他数据与汉信码标准特征比例对应位上的数据的差值并取绝对值；
若每个位对应的绝对值均小于比例阀值，则所述的特征比例与汉信码标准特征比例的相似度小于行比例阀值；
若所述特征比例与汉信码标准特征比例的相似度不在比例阀值范围内，则不对所述二维码图像进行解码；
在四个特征比例中，若不满足有一个特征比例与汉信码标准特征比例3:1:1:1:1的相似度在比例阀值范围内，且三个特征比例与汉信码标准特征比例1:1:1:1:3的相似度在比例阀值范围内，则不对所述二维码图像进行解码；
根据所述的特征线段的起点和终点计算汉信码的位置探测图形的边界线及数据位宽度。
请参见图6至图7，一种汉信码特征图形检测系统，包括二值化模块1、第一寻找模块2、形成模块3、第二寻找模块4、计算模块7，
二值化模块1，用于对接收到的二维码图像进行二值化；
第一寻找模块2，用于对二维码图像逐行逐列扫描寻找出汉信码所在区域的四个顶点；
形成模块3，用于将所述的四个顶点两两连接起来形成汉信码所在区域的四条边界线及两条对角线；
第二寻找模块4，用于在两条对角线上分别寻找出起点为顶点且二值化数值为连续的1、0、1、0、1的数据组成的四条特征线段及每条特征线段的终点；
计算模块7，用于根据所述的特征线段的起点和终点计算汉信码的位置探测图形的边界线及数据位宽度。
进一步的，还包括统计模块5、分析模块6，
统计模块5，用于从特征线段的起点开始统计连续的1、0、1、0、1的个数组成特征比例；
分析模块6，用于分析所述特征比例与汉信码标准特征比例的相似度是否在比例阀值范围内。
由上述描述可知，通过统计模块5和分析模块6对特征线段是否与汉信码标准特征比例相似进行判断，最终确定接收到的二维码图像是否包含汉信码，保证系统解码的准确性。
请参照图6，本发明的实施例三为：
一种汉信码特征图形检测系统，包括二值化模块1、第一寻找模块2、形成模块3、第二寻找模块4、计算模块7，
二值化模块1，用于对接收到的二维码图像进行二值化；
第一寻找模块2，用于对二维码图像逐行逐列扫描寻找出汉信码所在区域的四个顶点；
形成模块3，用于将所述的四个顶点两两连接起来形成汉信码所在区域的四条边界线及两条对角线；
第二寻找模块4，用于在两条对角线上分别寻找出起点为顶点且二值化数值为连续的1、0、1、0、1的数据组成的四条特征线段及每条特征线段的终点；
计算模块7，用于根据所述的特征线段的起点和终点计算汉信码的位置探测图形的边界线及数据位宽度。
请参照图7，本发明的实施例四为：
一种汉信码特征图形检测系统，包括二值化模块1、第一寻找模块2、形成模块3、第二寻找模块4、统计模块5、分析模块6、计算模块7，
二值化模块1，用于对接收到的二维码图像进行二值化；
第一寻找模块2，用于对二维码图像逐行逐列扫描寻找出汉信码所在区域的四个顶点；
形成模块3，用于将所述的四个顶点两两连接起来形成汉信码所在区域的四条边界线及两条对角线；
第二寻找模块4，用于在两条对角线上分别寻找出起点为顶点且二值化数值为连续的1、0、1、0、1的数据组成的四条特征线段及每条特征线段的终点；
统计模块5，用于从特征线段的起点开始统计连续的1、0、1、0、1的个数组成特征比例；
分析模块6，用于分析所述特征比例与汉信码标准特征比例的相似度是否在比例阀值范围内；
计算模块7，用于根据所述的特征线段的起点和终点计算汉信码的位置探测图形的边界线及数据位宽度。
综上所述，本发明提供的一种汉信码特征图形检测方法及系统，通过对接收到的二维码图像的逐行逐列扫描得到汉信码所在区域的四个顶点，四个顶点的选取不受汉信码所在区域是否旋转的影响，通过四个顶点确定出汉信码所在区域的四条边界线及两条对角线，并在对角线上寻找汉信码位置探测图形的对角线，所述方法充分利用了汉信码位置探测图形的特征，所述方法抗干扰性强，检测效率高、速度快。

Claims (10)

  1. 一种汉信码特征图形检测方法，其特征在于，
    对接收到的二维码图像进行二值化；
    对二维码图像逐行逐列扫描寻找出汉信码所在区域的四个顶点；
    将所述的四个顶点两两连接起来形成汉信码所在区域的四条边界线及两条对角线；
    在两条对角线上分别寻找出起点为顶点且二值化数值为连续的1、0、1、0、1的数据组成的四条特征线段及每条特征线段的终点；
    根据所述的特征线段的起点和终点计算汉信码的位置探测图形的边界线及数据位宽度。
  2. 根据权利要求1所述的汉信码特征图形检测方法，其特征在于，对接收到的二维码图像进行二值化，具体为：
    采用最大类间方差法或者平均值法计算接收到的二维码图像的灰度阀值；
    根据所述灰度阀值对接收到的二维码图像进行二值化。
  3. 根据权利要求1所述的汉信码特征图形检测方法，其特征在于，对二维码图像逐行逐列扫描寻找出汉信码所在区域的四个顶点，具体为：
    从上至下对二维码图像逐行扫描，起始的行数据中均为白点，当遇到一行数据中有黑点时，记录最左边的黑点为P1，最右边的黑点为P2；
    从左到右对二维码图像逐列扫描，起始的列数据中均为白点，当遇到一列数据中有黑点时，记录最上的黑点为P3，最下的黑点为P4；
    从下至上对二维码图像逐行扫描，起始的行数据中均为白点，当遇到一行数据中有黑点时，记录最左边的黑点为P5，最右边的黑点为P6；
    从右到左对二维码图像逐列扫描，起始的列数据中均为白点，当遇到一列数据中有黑点时，记录最上的黑点为P7，最下的黑点为P8；
    预设距离阀值，计算四组黑点P1和P2、P3和P4、P5和P6、P7和P8中任意一组的两个黑点的距离，并判断计算的距离是否小于距离阀值；
    若计算的距离小于距离阀值，则取P1和P2之间的中点、P3和P4之间的中点、P5和P6之间的中点、P7和P8之间的中点为汉信码所在区域的四个顶点；
    若计算的距离大于等于距离阀值，则取P1和P3之间的中点、P4和P5之 间的中点、P6和P8之间的中点、P7和P2之间的中点为汉信码所在区域的四个顶点。
  4. 根据权利要求1所述的汉信码特征图形检测方法，其特征在于，还包括：
    预设比例阀值，从特征线段的起点开始统计连续的1、0、1、0、1的个数组成特征比例；
    分析所述特征比例与汉信码标准特征比例的相似度是否在比例阀值范围内，所述汉信码标准特征比例为3:1:1:1:1或1:1:1:1:3；
    若所述特征比例与汉信码标准特征比例的相似度不在比例阀值范围内，则不对所述二维码图像进行解码。
  5. 根据权利要求4所述的汉信码特征图形检测方法，其特征在于，分析所述特征比例与汉信码标准特征比例的相似度是否在比例阀值范围内，具体为：
    将所述特征比例的起始数据转换为与汉信码标准特征比例起始数据相同的数据，并将特征比例的所有数据等比例转换得到转换后的特征比例；
    计算转换后的特征比例中除起始数据外的其他数据与汉信码标准特征比例对应位上的数据的差值并取绝对值；
    若每个位对应的绝对值均小于比例阀值，则所述的特征比例与汉信码标准特征比例的相似度小于行比例阀值。
  6. 根据权利要求5所述的汉信码特征图形检测方法，其特征在于，还包括：
    在四个特征比例中，若不满足有一个特征比例与汉信码标准特征比例3:1:1:1:1的相似度在比例阀值范围内，且三个特征比例与汉信码标准特征比例1:1:1:1:3的相似度在比例阀值范围内，则不对所述二维码图像进行解码。
  7. 根据权利要求1所述的汉信码特征图形检测方法，其特征在于，根据所述的特征线段的起点和终点计算汉信码的位置探测图形的边界线，具体为：
    计算与过所述特征线段起点的两条汉信码所在区域的边界线平行且穿过特征线段终点的两条直线；
    过所述起点的两条汉信码所在区域的边界线与计算得到的两条直线所围成的正方形即为汉信码的位置探测图形的边界线。
  8. 根据权利要求1所述的汉信码特征图形检测方法，其特征在于，根据所 述的特征线段的起点和终点计算汉信码的位置探测图形的数据位宽度，具体为：
    根据所述的特征线段的起点和终点计算得到所述特征线段的长度d；
    已知汉信码的位置探测图形的边界线上包含7个数据位，根据所述特征线段的长度d计算汉信码的位置探测图形的数据位宽度l，具体为：
    Figure PCTCN2016092816-appb-100001
  9. 一种汉信码特征图形检测系统，其特征在于，包括二值化模块、第一寻找模块、形成模块、第二寻找模块、计算模块，
    二值化模块，用于对接收到的二维码图像进行二值化；
    第一寻找模块，用于对二维码图像逐行逐列扫描寻找出汉信码所在区域的四个顶点；
    形成模块，用于将所述的四个顶点两两连接起来形成汉信码所在区域的四条边界线及两条对角线；
    第二寻找模块，用于在两条对角线上分别寻找出起点为顶点且二值化数值为连续的1、0、1、0、1的数据组成的四条特征线段及每条特征线段的终点；
    计算模块，用于根据所述的特征线段的起点和终点计算汉信码的位置探测图形的边界线及数据位宽度。
  10. 根据权利要求9所述的汉信码特征图形检测系统，其特征在于，还包括统计模块、分析模块，
    统计模块，用于从特征线段的起点开始统计连续的1、0、1、0、1的个数组成特征比例；
    分析模块，用于分析所述特征比例与汉信码标准特征比例的相似度是否在比例阀值范围内。
PCT/CN2016/092816 2015-09-07 2016-08-02 一种汉信码特征图形检测方法及系统 WO2017041600A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP16843538.6A EP3330887B1 (en) 2015-09-07 2016-08-02 Chinese-sensitive code feature pattern detection method and system
BR112018004552-7A BR112018004552A2 (zh) 2015-09-07 2016-08-02 A Method and System for Detecting Characteristic Pattern of Chinese Code
US15/895,986 US10528781B2 (en) 2015-09-07 2018-02-13 Detection method and system for characteristic patterns of Han Xin codes

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510561307.3A CN105095822B (zh) 2015-09-07 2015-09-07 一种汉信码特征图形检测方法及系统
CN201510561307.3 2015-09-07

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/895,986 Continuation US10528781B2 (en) 2015-09-07 2018-02-13 Detection method and system for characteristic patterns of Han Xin codes

Publications (1)

Publication Number Publication Date
WO2017041600A1 true WO2017041600A1 (zh) 2017-03-16

Family

ID=54576218

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/092816 WO2017041600A1 (zh) 2015-09-07 2016-08-02 一种汉信码特征图形检测方法及系统

Country Status (5)

Country Link
US (1) US10528781B2 (zh)
EP (1) EP3330887B1 (zh)
CN (1) CN105095822B (zh)
BR (1) BR112018004552A2 (zh)
WO (1) WO2017041600A1 (zh)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105095822B (zh) * 2015-09-07 2018-07-06 福建联迪商用设备有限公司 一种汉信码特征图形检测方法及系统
CN106951810B (zh) * 2017-03-09 2019-12-24 江苏智联天地科技有限公司 一种基于ewma模型的汉信码定位方法
CN109739233B (zh) * 2018-12-29 2022-06-14 歌尔光学科技有限公司 Agv小车定位方法、装置及系统
CN109871723B (zh) * 2019-01-16 2022-06-21 王诗会 图像融合信息的处理方法及系统
CN110414649B (zh) * 2019-07-29 2023-06-06 广州柔视智能科技有限公司 Dm码的定位方法、装置、终端及存储介质
CN112651260B (zh) * 2020-12-30 2024-01-30 凌云光技术股份有限公司 一种自适应离散码转连续码的方法及系统
CN112837334B (zh) * 2021-04-02 2022-07-05 河南大学 一种汉简图像的自动缀合方法
CN113496135B (zh) * 2021-08-31 2023-06-20 北京紫光青藤微系统有限公司 码图的定位方法、装置、电子设备及存储介质
CN114417904A (zh) * 2022-01-18 2022-04-29 南京信息职业技术学院 一种基于深度学习的条形码识别方法及图书检索系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0672994A1 (en) * 1994-03-14 1995-09-20 Nippondenso Co., Ltd. Method and apparatus for reading an optically two-dimensional code
CN102831428A (zh) * 2012-06-30 2012-12-19 东南大学 图像内快速响应矩阵码区域的提取方法
CN103177235A (zh) * 2013-04-18 2013-06-26 河海大学常州校区 一种复杂背景下汉信码的识别装置及方法
CN105095822A (zh) * 2015-09-07 2015-11-25 福建联迪商用设备有限公司 一种汉信码特征图形检测方法及系统

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100866490B1 (ko) * 2007-01-17 2008-11-03 삼성전자주식회사 영상의 색 수차를 보정하기 위한 장치 및 방법
CN103390183B (zh) * 2012-05-09 2019-07-19 顾泽苍 一种适用于手机识别的防伪代码的生成方法
EP2800027A1 (en) * 2013-05-02 2014-11-05 Giesecke & Devrient GmbH Method and apparatus for transmission of visually encoded data
CN104517090B (zh) * 2013-09-29 2017-09-05 北大方正集团有限公司 一种qr码探测图形的检测方法及系统
CN103914675B (zh) * 2014-03-17 2016-11-16 东华大学 一种服装的快速响应矩阵二维码识别方法
CN104298947B (zh) * 2014-08-15 2017-03-22 广东顺德中山大学卡内基梅隆大学国际联合研究院 一种对二维条码精确定位的方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0672994A1 (en) * 1994-03-14 1995-09-20 Nippondenso Co., Ltd. Method and apparatus for reading an optically two-dimensional code
CN102831428A (zh) * 2012-06-30 2012-12-19 东南大学 图像内快速响应矩阵码区域的提取方法
CN103177235A (zh) * 2013-04-18 2013-06-26 河海大学常州校区 一种复杂背景下汉信码的识别装置及方法
CN105095822A (zh) * 2015-09-07 2015-11-25 福建联迪商用设备有限公司 一种汉信码特征图形检测方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3330887A4 *

Also Published As

Publication number Publication date
EP3330887A4 (en) 2018-10-03
US20180181785A1 (en) 2018-06-28
EP3330887B1 (en) 2019-05-01
EP3330887A1 (en) 2018-06-06
CN105095822A (zh) 2015-11-25
US10528781B2 (en) 2020-01-07
CN105095822B (zh) 2018-07-06
BR112018004552A2 (zh) 2018-10-09

Similar Documents

Publication Publication Date Title
WO2017041600A1 (zh) 一种汉信码特征图形检测方法及系统
WO2017016448A1 (zh) 一种qr码特征检测方法及系统
WO2017016445A1 (zh) 二维码分块解码方法及系统
CN102184378B (zh) 一种pdf417标准二维条码图像切割的办法
CN105989317B (zh) 一种二维码的识别方法及装置
CN107609451A (zh) 一种基于二维码的高精度视觉定位方法及系统
Doermann et al. A new algorithm for detecting text line in handwritten documents
CN110363202B (zh) 指针式仪表数值读取方法及计算机终端
Das et al. A fast algorithm for skew detection of document images using morphology
CN113177959B (zh) 一种快速运动过程中qr码实时提取方法
CN105654015A (zh) 解码二维矩阵符号的方法和系统
CN106446894A (zh) 一种基于轮廓识别球型目标物位置的方法
WO2013044875A1 (zh) 线性条码识别方法和系统
CN104008359A (zh) 一种用于qr码识别的精确网格采样方法
CN109948521B (zh) 图像纠偏方法和装置、设备及存储介质
CN103489254B (zh) 彩票的识别方法及系统
CN109190434B (zh) 一种基于亚像素级角点检测的条码识别算法
Liang et al. A new wavelet-Laplacian method for arbitrarily-oriented character segmentation in video text lines
CN108256518B (zh) 文字区域检测方法及装置
CN108256375A (zh) 一种一维条形码扫描方法
CN111275049B (zh) 一种文字图像骨架特征描述符获取的方法及装置
Liang et al. An extraction and classification algorithm for concrete cracks based on machine vision
CN113793309B (zh) 一种基于形态学特征的亚像素级椭圆检测方法
CN112419225B (zh) 一种基于引脚分割的sop型芯片检测方法及系统
CN112036232A (zh) 一种图像表格结构识别方法、系统、终端以及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16843538

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2016843538

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112018004552

Country of ref document: BR

ENP Entry into the national phase

Ref document number: 112018004552

Country of ref document: BR

Kind code of ref document: A2

Effective date: 20180307