CN110674771A - Signature identification and verification method of Nixing pottery pottery - Google Patents
Signature identification and verification method of Nixing pottery potteryDownload PDFInfo
- Publication number
- CN110674771A CN110674771ACN201910934504.3ACN201910934504ACN110674771ACN 110674771 ACN110674771 ACN 110674771ACN 201910934504 ACN201910934504 ACN 201910934504ACN 110674771 ACN110674771 ACN 110674771A
- Authority
- CN
- China
- Prior art keywords
- signature
- data
- concave
- plane
- ceramic
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/30—Writer recognition; Reading and verifying signatures
- G06V40/33—Writer recognition; Reading and verifying signatures based only on signature image, e.g. static signature recognition
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Collating Specific Patterns (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明涉及立体签名识别领域，尤其涉及坭兴陶陶器签名识别验证方法。The invention relates to the field of three-dimensional signature recognition, in particular to a signature recognition and verification method for Nixing pottery pottery.
背景技术Background technique
手写签名识别系统利用计算机自动识别手写签名样本是某个特定人亲自签署的“真签名”还是别人模仿的“伪签名”。在办公自动化和公共安全方面，签名识别的重要性日益明显，在大多数企业，尤其是经常需要颁布或签署文件的行政部门来说，通过辨识签名的真伪来确定身份的方式易于被人们所接受。由于签名识别具有良好的应用前景和巨大的商业价值，世界各国许多学者和研究机构都已表现出极大兴趣，国内近几年也逐步开始了对中文签名认证的研究工作。The handwritten signature recognition system uses a computer to automatically identify whether a handwritten signature sample is a "true signature" signed by a specific person or a "false signature" imitated by others. In office automation and public safety, the importance of signature recognition is becoming more and more obvious. For most enterprises, especially the administrative departments that often need to issue or sign documents, the way to determine the identity by identifying the authenticity of the signature is easy to be recognized by people. accept. Due to the good application prospects and huge commercial value of signature recognition, many scholars and research institutions around the world have shown great interest. In recent years, domestic research on Chinese signature authentication has gradually begun.
手写字符识别涉及模式识别、图像处理、数字信号处理、自然语言理解、人丁智能、模糊数学、信息论、计算机、中文信息处理等学科，是一门综合性技术，它在中文信息处理、办公室自动化、人工智能等高技术领域，都有着重要的实用价值和理论意义D1。手写文本、信封、票据表格和签名等的计算机自动阅读都具有十分诱人的应用背景，因此吸引了许多研究者的关注。手写字符和数字识别技术一旦研究成功并投入应用，将产生巨大的社会和经济效益。Handwritten character recognition involves pattern recognition, image processing, digital signal processing, natural language understanding, human intelligence, fuzzy mathematics, information theory, computer, Chinese information processing and other disciplines. , artificial intelligence and other high-tech fields, have important practical value and theoretical significance D1. Computer automatic reading of handwritten text, envelopes, receipt forms, and signatures all have very attractive application backgrounds, so they have attracted the attention of many researchers. Once the handwritten character and number recognition technology is successfully researched and put into application, it will produce huge social and economic benefits.
陶瓷签名已经越来越流行，但是伪签名也越来越多，现有的签名识别都是平面的签名识别，还没有立体签名的相关的方法，需要设计一种陶瓷签名识别方法。Ceramic signatures have become more and more popular, but there are also more and more fake signatures. The existing signature recognition is a flat signature recognition, and there is no related method for a three-dimensional signature. It is necessary to design a ceramic signature recognition method.
发明内容SUMMARY OF THE INVENTION
本发明的目的在于提供坭兴陶陶器签名识别验证方法，解决现有陶瓷签名无法识别真伪的技术问题。The purpose of the present invention is to provide a method for identifying and verifying the signature of Nixing pottery pottery, and to solve the technical problem that the existing ceramic signature cannot identify the authenticity.
坭兴陶陶器签名识别验证方法，所述方法包括如下步骤：A method for identifying and verifying signatures of Nixing pottery pottery, the method comprising the following steps:
步骤1：使用超声波微测距探头扫描陶瓷光滑表面获得扫描距离数据；Step 1: Scan the ceramic smooth surface with an ultrasonic micro-ranging probe to obtain scanning distance data;
步骤2：建立三维坐标系，把扫描距离数据放入三维坐标系，最初扫描点为原点，得到弧面模型；Step 2: Establish a three-dimensional coordinate system, put the scanning distance data into the three-dimensional coordinate system, and initially scan the point as the origin to obtain the camber model;
步骤3：使用超声波微测距探头扫描陶瓷签名表面，得到签名表面凹凸数据；Step 3: Use the ultrasonic micro ranging probe to scan the ceramic signature surface to obtain the signature surface bump data;
步骤4：把签名表面凹凸数据与弧面模型进行对比，去除高凸数据，得到立体签名数据；Step 4: Compare the concave and convex data on the signature surface with the curved surface model, remove the high convex data, and obtain the three-dimensional signature data;
步骤5：对立体签名数据进行形状特征提取得到凹陷形态特征；Step 5: perform shape feature extraction on the three-dimensional signature data to obtain concave morphological features;
步骤6：把立体签名数据的中间凹陷数据去除，取凹陷数据两边的最大数据，并把数据连线得到平面签名；Step 6: remove the middle concave data of the three-dimensional signature data, take the largest data on both sides of the concave data, and connect the data to obtain a plane signature;
步骤7：对平面签名数据进行形状特征提取得到形态特征；Step 7: perform shape feature extraction on the plane signature data to obtain morphological features;
步骤8：对平面签名数据进行动态特征提取得到动态特征；Step 8: perform dynamic feature extraction on the plane signature data to obtain dynamic features;
步骤9：把凹陷形态特征、形态特征和动态特征输入分类器进行计算，根据计算的阀值确定识别结果。Step 9: Input the sag morphological features, morphological features and dynamic features into the classifier for calculation, and determine the recognition result according to the calculated threshold.
进一步地，所述步骤1中，扫描的陶瓷光滑表面的与签名处的表面是相同的弧面或者平面，即陶瓷光滑表面与签名处的表面的弧形半径相同，光滑度相同，陶瓷光滑表面与签名处的表面均是同一个陶瓷上不同方向的表面。Further, in the step 1, the scanned ceramic smooth surface is the same arc or plane as the surface at the signature, that is, the ceramic smooth surface has the same arc radius and the same smoothness as the surface at the signature, and the ceramic smooth surface has the same arc radius as the surface at the signature. The surface with the signature is the same ceramic surface in different directions.
进一步地，所述步骤1中，扫描的具体过程为：超声波微测距探头以网格结构进行运动对陶瓷光滑表面进行扫描，网格结构的横向间距和纵向间距均为2μm，网格线条采集得到各个点的距离与位置数据，然后把距离数据与预设数据做差值得到扫描距离数据，预设数据即为初始扫描点与超声波微测距探头的距离。Further, in the step 1, the specific process of scanning is as follows: the ultrasonic micro-ranging probe moves with a grid structure to scan the ceramic smooth surface, the horizontal and vertical spacing of the grid structure are both 2 μm, and the grid lines are collected. The distance and position data of each point are obtained, and then the difference between the distance data and the preset data is obtained to obtain the scanning distance data. The preset data is the distance between the initial scanning point and the ultrasonic micro-ranging probe.
进一步地，所述步骤2中的弧面模型，超声波微测距探头行走的网格横向和纵向为三维坐标系的X轴数据和Y轴数据，扫描距离数据即为Z轴数据。Further, in the camber model in the step 2, the horizontal and vertical directions of the grid on which the ultrasonic micro ranging probe travels are the X-axis data and the Y-axis data of the three-dimensional coordinate system, and the scanning distance data is the Z-axis data.
进一步地，所述步骤4中，去除高凸数据的具体过程为，把识别的Z轴数据与弧面模型的Z轴数据进行做差值，得到签名数据，如果差值得到的值为正值数据时，把该数据丢弃，并用零取代。Further, in the step 4, the specific process of removing the high-convex data is to make a difference between the identified Z-axis data and the Z-axis data of the camber model to obtain the signature data, if the value obtained by the difference is a positive value. data, discard the data and replace it with zero.
进一步地，所述步骤5中凹陷形态特征包括凹陷面积、凹陷斜面连通域个数、凹陷笔画倾斜方向，其中凹陷面积包括凹陷区域倾斜面面积和凹陷面总面积，凹陷斜面连通域个数即为弧面模型X轴和Y轴平面的最小单元方格数量，凹陷笔画倾斜方向即为各个凹陷斜面的倾斜方向和凹陷底部的走向方向。Further, in the described step 5, the morphological features of the depression include the depression area, the number of the connected domains of the depression slope, and the inclination direction of the depression stroke, wherein the depression area includes the slope area of the depression area and the total area of the depression surface, and the number of the connected domains of the depression slope is: The minimum number of cells in the X-axis and Y-axis planes of the camber model. The inclination direction of the concave strokes is the inclination direction of each concave slope and the direction of the bottom of the concave.
进一步地，所述步骤6中对立体签名数据进行取边缘数据，去除中间数据，并用连线把边缘数据连接起来得到平面签名。Further, in the step 6, edge data is taken from the three-dimensional signature data, intermediate data is removed, and the edge data is connected by connecting lines to obtain a plane signature.
进一步地，所述步骤7中平面签名数据形态特征的具体过程为：Further, the specific process of the morphological feature of the plane signature data in the step 7 is:
平面签名图像的高宽比，获取平面签名在X轴和Y轴的宽度，然后相互比较得到比例系数；The aspect ratio of the plane signature image, obtain the width of the plane signature on the X axis and the Y axis, and then compare with each other to get the scale coefficient;
平面签名点面积与总面积比，把平面签名外围轮廓包围部分用黑色填充，然后对填充平面签名进行二值化处理，二值化签名图像中黑点数量，即签名对象点与总像素数的比怕；The ratio of the area of the plane signature point to the total area, fill the part surrounded by the outline of the plane signature with black, and then binarize the filled plane signature to binarize the number of black points in the signature image, that is, the difference between the signature object points and the total number of pixels. than afraid
识别平面签名图像X轴和Y轴平面的最小单元方格数量；Identify the minimum number of cells in the X-axis and Y-axis planes of the plane signature image;
平面签名轮廓的倾斜方向，对于轮廓上某一点p(x，y)，如果p'＝(x-1,y+1)非零，则p'为负方向倾斜点；如果p'＝(x+1，y)非零，则称p'为垂直方向倾斜点；如果p'＝(x+1，y+1)非零，则称p'为正方向倾斜点，对签名轮廓的倾斜方向向量进行累加，得到三维向量V(d1，d2，d3)，然后将这个向量归一化即可得到笔迹方向的特征，计算公式如下：The inclined direction of the plane signature contour, for a certain point p(x, y) on the contour, if p'=(x-1, y+1) is non-zero, then p' is a negative inclined point; if p'=(x +1, y) is non-zero, then p' is the tilt point in the vertical direction; if p'=(x+1, y+1) is non-zero, then p' is the tilt point in the positive direction. The vectors are accumulated to obtain a three-dimensional vector V(d1, d2, d3), and then the vector is normalized to obtain the characteristics of the handwriting direction. The calculation formula is as follows:
V1(d1,d2,d3)＝V(d1/D,d2/D,d3/D)V1 (d1,d2,d3)＝V(d1/D,d2/D,d3/D)
D＝d1+d2+d3。D=d1+d2+d3.
进一步地，所述步骤8中动态特征识别的具体过程为：Further, the specific process of dynamic feature recognition in the step 8 is:
识别平面签名骨架方向灰度特征，对二值签名图像细化骨架上的点进行灰度还原，成为灰度骨架，并对其上各点在水平、垂直、正倾斜和负倾斜四个方向上累计灰度，由此形成一个四维向量(G1，G2，G3，G4)，最后将G1，G2，G3，G4规范化到0，1之间，便得到骨架方向的灰度特征。Identify the grayscale features of the plane signature skeleton direction, and restore the grayscale points on the refined skeleton of the binary signature image to become a grayscale skeleton. The grayscale is accumulated to form a four-dimensional vector (G1, G2, G3, G4), and finally G1, G2, G3, and G4 are normalized to between 0 and 1 to obtain the grayscale feature of the skeleton direction.
进一步地，所述步骤9中的具体过程为：Further, the specific process in the step 9 is:
把凹陷形态特征、形态特征和动态特征与已知样本签名的特征向量相比较，首先通过一定数量的训练样本得到一组n维特征向量S0作为标准特征向量，其中S0＝{S0(i)|i＝1,2,...,n}，然后计算由待测图像得到的向量S与S0的欧式距离U，Compare the concave morphological features, morphological features and dynamic features with the feature vectors of known sample signatures, first obtain a set of n-dimensional feature vectors S0 as standard feature vectors through a certain number of training samples, where S0 ={S0 ( i)|i=1,2,...,n}, then calculate the Euclidean distance U between the vector S and S0 obtained from the image to be tested,
其中T为阈值，R＝0表示待测签名识别为假，反之则为匹配。Among them, T is the threshold value, and R=0 indicates that the signature to be tested is identified as false, otherwise it is a match.
本发明采用了上述技术方案，本发明具有以下技术效果：The present invention adopts the above-mentioned technical scheme, and the present invention has the following technical effects:
本发明通过使用超声波微测距探头扫描识别出陶瓷签名中的立体模型，然后对模型进行识别对，从立体的凹陷的签名的深度、倾斜面的进行识别对比，同时结合平面识别对比一起，使得识别更加的精准，更好的识别陶瓷签名，可以实现对陶瓷签名的伪签名进行打假。The present invention scans and recognizes the three-dimensional model in the ceramic signature by using the ultrasonic micro ranging probe, and then identifies and compares the model, and identifies and compares the depth of the three-dimensional concave signature and the inclined surface, and at the same time combines the plane identification and comparison, so that the The identification is more accurate, and the ceramic signature can be better recognized, and the counterfeiting of the false signature of the ceramic signature can be realized.
附图说明Description of drawings
图1是本发明的方法流程图。Figure 1 is a flow chart of the method of the present invention.
具体实施方式Detailed ways
为使本发明的目的、技术方案及优点更加清楚明白，以下参照附图并举出优选实施例，对本发明进一步详细说明。然而，需要说明的是，说明书中列出的许多细节仅仅是为了使读者对本发明的一个或多个方面有一个透彻的理解，即便没有这些特定的细节也可以实现本发明的这些方面。In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail below with reference to the accompanying drawings and preferred embodiments. It is to be understood, however, that many of the details set forth in the specification are merely provided to provide the reader with a thorough understanding of one or more aspects of the invention, and that aspects of the invention may be practiced without these specific details.
如图1所示，根据本发明的坭兴陶陶器签名识别验证方法，所述方法包括如下步骤：As shown in Figure 1, according to the method for identifying and verifying the signature of Nixing pottery pottery of the present invention, the method comprises the steps:
步骤1：使用超声波微测距探头扫描陶瓷光滑表面获得扫描距离数据。扫描的陶瓷光滑表面的与签名处的表面是相同的弧面或者平面，即陶瓷光滑表面与签名处的表面的弧形半径相同，光滑度相同，陶瓷光滑表面与签名处的表面均是同一个陶瓷上不同方向的表面。Step 1: Scan the ceramic smooth surface with an ultrasonic micro-ranging probe to obtain scanning distance data. The scanned ceramic smooth surface is the same arc or plane as the surface at the signature, that is, the ceramic smooth surface and the surface at the signature have the same arc radius and the same smoothness, and the ceramic smooth surface and the surface at the signature are the same Surfaces in different orientations on ceramics.
扫描的具体过程为：超声波微测距探头以网格结构进行运动对陶瓷光滑表面进行扫描，网格结构的横向间距和纵向间距均为2μm，网格线条采集得到各个点的距离与位置数据，然后把距离数据与预设数据做差值得到扫描距离数据，预设数据即为初始扫描点与超声波微测距探头的距离。The specific process of scanning is as follows: the ultrasonic micro ranging probe scans the smooth surface of the ceramic by moving the grid structure. The horizontal and vertical spacing of the grid structure are both 2 μm, and the distance and position data of each point are collected by the grid lines. Then, the difference between the distance data and the preset data is made to obtain the scanning distance data, and the preset data is the distance between the initial scanning point and the ultrasonic micro-ranging probe.
步骤2：建立三维坐标系，把扫描距离数据放入三维坐标系，最初扫描点为原点，得到弧面模型。超声波微测距探头行走的网格横向和纵向为三维坐标系的X轴数据和Y轴数据，扫描距离数据即为Z轴数据。Step 2: Establish a three-dimensional coordinate system, put the scanning distance data into the three-dimensional coordinate system, and initially scan the point as the origin to obtain the arc surface model. The horizontal and vertical directions of the grid of the ultrasonic micro ranging probe are the X-axis data and the Y-axis data of the three-dimensional coordinate system, and the scanning distance data is the Z-axis data.
步骤3：使用超声波微测距探头扫描陶瓷签名表面，得到签名表面凹凸数据；Step 3: Use the ultrasonic micro ranging probe to scan the ceramic signature surface to obtain the signature surface bump data;
步骤4：把签名表面凹凸数据与弧面模型进行对比，去除高凸数据，得到立体签名数据。去除高凸数据的具体过程为，把识别的Z轴数据与弧面模型的Z轴数据进行做差值，得到签名数据，如果差值得到的值为正值数据时，把该数据丢弃，并用零取代。Step 4: Compare the concave-convex data on the signature surface with the arc surface model, remove the high-convex data, and obtain the three-dimensional signature data. The specific process of removing the highly convex data is to make the difference between the identified Z-axis data and the Z-axis data of the camber model to obtain the signature data. If the value obtained by the difference is positive data, discard the data and use Zero substitution.
步骤5：对立体签名数据进行形状特征提取得到凹陷形态特征。凹陷形态特征包括凹陷面积、凹陷斜面连通域个数、凹陷笔画倾斜方向，其中凹陷面积包括凹陷区域倾斜面面积和凹陷面总面积，凹陷斜面连通域个数即为弧面模型X轴和Y轴平面的最小单元方格数量，凹陷笔画倾斜方向即为各个凹陷斜面的倾斜方向和凹陷底部的走向方向。Step 5: Perform shape feature extraction on the three-dimensional signature data to obtain concave morphological features. The morphological features of the concave include the concave area, the number of connected domains on the concave slope, and the inclination direction of the concave stroke. The concave area includes the area of the sloped surface in the concave region and the total area of the concave surface. The number of connected domains on the concave slope is the X axis and the Y axis of the arc model. The minimum number of unit squares in the plane, the inclination direction of the concave strokes is the inclination direction of each concave slope and the direction of the bottom of the concave.
步骤6：把立体签名数据的中间凹陷数据去除，取凹陷数据两边的最大数据，并把数据连线得到平面签名。对立体签名数据进行取边缘数据，去除中间数据，并用连线把边缘数据连接起来得到平面签名。Step 6: Remove the middle concave data of the three-dimensional signature data, take the largest data on both sides of the concave data, and connect the data to obtain a plane signature. The three-dimensional signature data is taken from the edge data, the intermediate data is removed, and the edge data is connected with the connection line to obtain the plane signature.
步骤7：对平面签名数据进行形状特征提取得到形态特征。Step 7: Extracting shape features from the plane signature data to obtain shape features.
平面签名图像的高宽比，获取平面签名在X轴和Y轴的宽度，然后相互比较得到比例系数；The aspect ratio of the plane signature image, obtain the width of the plane signature on the X axis and the Y axis, and then compare with each other to get the scale coefficient;
平面签名点面积与总面积比，把平面签名外围轮廓包围部分用黑色填充，然后对填充平面签名进行二值化处理，二值化签名图像中黑点数量，即签名对象点与总像素数的比怕；The ratio of the area of the plane signature point to the total area, fill the part surrounded by the outline of the plane signature with black, and then binarize the filled plane signature to binarize the number of black points in the signature image, that is, the difference between the signature object points and the total number of pixels. than afraid
识别平面签名图像X轴和Y轴平面的最小单元方格数量；Identify the minimum number of cells in the X-axis and Y-axis planes of the plane signature image;
平面签名轮廓的倾斜方向，对于轮廓上某一点p(x，y)，如果p'＝(x-1,y+1)非零，则p'为负方向倾斜点；如果p'＝(x+1，y)非零，则称p'为垂直方向倾斜点；如果p'＝(x+1，y+1)非零，则称p'为正方向倾斜点，对签名轮廓的倾斜方向向量进行累加，得到三维向量V(d1，d2，d3)，然后将这个向量归一化即可得到笔迹方向的特征，计算公式如下：The inclined direction of the plane signature contour, for a certain point p(x, y) on the contour, if p'=(x-1, y+1) is non-zero, then p' is a negative inclined point; if p'=(x +1, y) is non-zero, then p' is the tilt point in the vertical direction; if p'=(x+1, y+1) is non-zero, then p' is the tilt point in the positive direction. The vectors are accumulated to obtain a three-dimensional vector V(d1, d2, d3), and then the vector is normalized to obtain the characteristics of the handwriting direction. The calculation formula is as follows:
V1(d1,d2,d3)＝V(d1/D,d2/D,d3/D)V1 (d1,d2,d3)＝V(d1/D,d2/D,d3/D)
D＝d1+d2+d3。D=d1+d2+d3.
步骤8：对平面签名数据进行动态特征提取得到动态特征。识别平面签名骨架方向灰度特征，对二值签名图像细化骨架上的点进行灰度还原，成为灰度骨架，并对其上各点在水平、垂直、正倾斜和负倾斜四个方向上累计灰度，由此形成一个四维向量(G1，G2，G3，G4)，最后将G1，G2，G3，G4规范化到0，1之间，便得到骨架方向的灰度特征。Step 8: Perform dynamic feature extraction on the plane signature data to obtain dynamic features. Identify the grayscale features of the plane signature skeleton direction, and restore the grayscale points on the refined skeleton of the binary signature image to become a grayscale skeleton. The grayscale is accumulated to form a four-dimensional vector (G1, G2, G3, G4), and finally G1, G2, G3, and G4 are normalized to between 0 and 1 to obtain the grayscale feature of the skeleton direction.
步骤9：把凹陷形态特征、形态特征和动态特征输入分类器进行计算，根据计算的阀值确定识别结果。把凹陷形态特征、形态特征和动态特征与已知样本签名的特征向量相比较，首先通过一定数量的训练样本得到一组n维特征向量S0作为标准特征向量，其中S0＝{S0(i)|i＝1,2,...,n}，然后计算由待测图像得到的向量S与S0的欧式距离U，Step 9: Input the sag morphological features, morphological features and dynamic features into the classifier for calculation, and determine the recognition result according to the calculated threshold. Compare the concave morphological features, morphological features and dynamic features with the feature vectors of known sample signatures, first obtain a set of n-dimensional feature vectors S0 as standard feature vectors through a certain number of training samples, where S0 ={S0 ( i)|i=1,2,...,n}, then calculate the Euclidean distance U between the vector S and S0 obtained from the image to be tested,
其中T为阈值，R＝0表示待测签名识别为假，反之则为匹配。Among them, T is the threshold value, and R=0 indicates that the signature to be tested is identified as false, otherwise it is a match.
以上所述仅是本发明的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明原理的前提下，还可以作出若干改进和润饰，这些改进和润饰也应视为本发明的保护范围。The above are only the preferred embodiments of the present invention. It should be pointed out that for those skilled in the art, without departing from the principles of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be It is regarded as the protection scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910934504.3ACN110674771B (en) | 2019-09-29 | 2019-09-29 | Nixing pottery ware signature identification and verification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910934504.3ACN110674771B (en) | 2019-09-29 | 2019-09-29 | Nixing pottery ware signature identification and verification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110674771Atrue CN110674771A (en) | 2020-01-10 |
| CN110674771B CN110674771B (en) | 2022-04-01 |
Family
ID=69080092
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910934504.3AActiveCN110674771B (en) | 2019-09-29 | 2019-09-29 | Nixing pottery ware signature identification and verification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110674771B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6160914A (en)* | 1996-11-08 | 2000-12-12 | Cadix Inc. | Handwritten character verification method and apparatus therefor |
| US20070036437A1 (en)* | 2003-02-27 | 2007-02-15 | Arizona Board Of Regents/Arizona State University | Comparative and analytic apparatus method for converting two-dimentional bit map data into three-dimensional data |
| CN102252621A (en)* | 2011-05-11 | 2011-11-23 | 谭国清 | Handwriting identification method |
| CN104101310A (en)* | 2014-07-22 | 2014-10-15 | 电子科技大学 | Three-dimensional showing method for character indentations |
| CN104200239A (en)* | 2014-09-09 | 2014-12-10 | 河海大学常州校区 | Image feature fusion identification based signature authentic identification system and method |
| CN104266604A (en)* | 2014-10-09 | 2015-01-07 | 孟凡语 | Handwriting authentication method |
| CN107122766A (en)* | 2017-05-23 | 2017-09-01 | 刘青 | A kind of method of handwriting verification |
- 2019
- 2019-09-29CNCN201910934504.3Apatent/CN110674771B/enactiveActive
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6160914A (en)* | 1996-11-08 | 2000-12-12 | Cadix Inc. | Handwritten character verification method and apparatus therefor |
| US20070036437A1 (en)* | 2003-02-27 | 2007-02-15 | Arizona Board Of Regents/Arizona State University | Comparative and analytic apparatus method for converting two-dimentional bit map data into three-dimensional data |
| CN102252621A (en)* | 2011-05-11 | 2011-11-23 | 谭国清 | Handwriting identification method |
| CN104101310A (en)* | 2014-07-22 | 2014-10-15 | 电子科技大学 | Three-dimensional showing method for character indentations |
| CN104200239A (en)* | 2014-09-09 | 2014-12-10 | 河海大学常州校区 | Image feature fusion identification based signature authentic identification system and method |
| CN104266604A (en)* | 2014-10-09 | 2015-01-07 | 孟凡语 | Handwriting authentication method |
| CN107122766A (en)* | 2017-05-23 | 2017-09-01 | 刘青 | A kind of method of handwriting verification |
Non-Patent Citations (1)
| Title |
|---|
| 孙晓红: "基于邻域特征的笔迹鉴定算法的研究", 《中国优秀博硕士学位论文全文数据库（硕士） 信息科技辑》* |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110674771B (en) | 2022-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106778586B (en) | Off-line handwritten signature identification method and system | |
| AU2004271639B2 (en) | Systems and methods for biometric identification using handwriting recognition | |
| CN111339990B (en) | Face recognition system and method based on dynamic update of face features | |
| US7724958B2 (en) | Systems and methods for biometric identification using handwriting recognition | |
| CN101561866B (en) | Character recognition method based on SIFT feature and gray scale difference value histogram feature | |
| CN104809715B (en) | Banknote image slant correction and method for extracting region | |
| CN102629322B (en) | Character feature extraction method based on stroke shape of boundary point and application thereof | |
| CN104200239A (en) | Image feature fusion identification based signature authentic identification system and method | |
| CN110222660B (en) | A signature authentication method and system based on the fusion of dynamic and static features | |
| CN111126240A (en) | A three-channel feature fusion face recognition method | |
| CN104680154B (en) | An identity recognition method based on the fusion of face features and palmprint features | |
| CN108960088A (en) | The detection of facial living body characteristics, the recognition methods of specific environment | |
| Babu et al. | Handwritten digit recognition using structural, statistical features and k-nearest neighbor classifier | |
| CN112132117A (en) | A Converged Identity Authentication System Assisting Coercion Detection | |
| CN108038495A (en) | A kind of incompleteness Chinese characters recognition method | |
| CN102136074B (en) | Man-machine interface (MMI) based wood image texture analyzing and identifying method | |
| CN110188750A (en) | A text recognition method for natural scene pictures based on deep learning | |
| CN111339932B (en) | A kind of palmprint image preprocessing method and system | |
| CN107103289B (en) | Method and system for handwriting identification using handwriting outline features | |
| CN104463084A (en) | Off-line handwritten signature recognition method based on non-negative matrix factorization | |
| CN112395919B (en) | Off-line signature authentication method and system based on multi-feature metric learning | |
| CN107977600A (en) | A kind of signature false distinguishing method based on side palm feature | |
| Hristov et al. | A software system for classification of archaeological artefacts represented by 2D plans | |
| CN1912889A (en) | Deformed fingerprint identification method based on local triangle structure characteristic collection | |
| Vohra et al. | Signature verification using support vector machine and convolution neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |