CN113378609A - Method and device for identifying agent signature - Google Patents
Method and device for identifying agent signature Download PDFInfo
- Publication number
- CN113378609A CN113378609A CN202010162874.2A CN202010162874A CN113378609A CN 113378609 A CN113378609 A CN 113378609A CN 202010162874 A CN202010162874 A CN 202010162874A CN 113378609 A CN113378609 A CN 113378609A
- Authority
- CN
- China
- Prior art keywords
- agent
- signature
- handwriting
- verified
- image
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a method and a device for identifying agent-agency signature, wherein the method comprises the steps of acquiring an agent-agency handwriting image and identifying handwriting content information contained in the agent-agency handwriting image; classifying the handwritten script image of the agent according to the handwritten content information and the channel information of the agent, and forming an agent script library according to the classification result; when a signature handwriting image to be verified is received, identifying signature content information to be verified contained in the signature handwriting image to be verified; extracting matched agent handwritten script images from an agent handwriting library according to the content information of the signature to be verified and agent channel information corresponding to the signature handwriting images to be verified; training a first handwriting recognition model based on the matched agent handwriting image; inputting the handwriting image of the signature to be verified into the first handwriting recognition model for calculation to obtain a first similarity result, and determining whether the signature to be verified is an agent signature according to the first similarity result.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a device for identifying an agent signature.
Background
With the development of various services, the service risk is increased while the brought traffic and the user increase, and the phenomenon that the service index is finished in an unknown ordering mode has appeared at present. For online business or business handling in a self-service hall, prevention and control are currently performed through means such as authentication comparison, portrait comparison, secondary order determination and the like; at the agent level, audit verification of customer signatures is also required in addition to conventional identification card verification.
Currently, the commonly used auditing methods include the following two methods:
the first mode, aiming at the identification of signature characters, comprises: 1. judging whether a signature exists; 2. whether the signature is a Chinese character; 3. whether the signed content is consistent with the name of the accepted client; 4. whether the live signature is consistent with the signature originally retained by the customer. The main technology is signature recognition, with the evolution of handwriting recognition technology, the recognition rate of the handwriting is improved, the signature content can be recognized, and therefore judgment on whether the signature is in compliance is made.
The second mode is realized by aiming at the identification of non-personal signature based on the comparison between a real signature and a signature to be verified, and the realization of the mode depends on the following two preconditions: the method is provided with a real client signature feature library for comparison, and has enough real client handwriting as training data.
However, the inventor finds out in the process of implementing the invention that: the first method can solve the problem of whether the signature is the name of the person and ensure the signature to be consistent with the name of the person to be accepted, but cannot solve the problem of whether the identification agent uses the proxy signature by identifying the signature characters. In the second method, firstly, for a new client, there is no service transaction record before, and there is no signature available for comparison; secondly, under the condition that the number of times that the client transacts business is not large, the handwriting of the client is not enough to be used as training data, and the problem that the historical signature of the client is also a substitute signature exists, so that the two preconditions are usually difficult to meet.
Disclosure of Invention
In view of the above, the present invention has been made to provide a method and apparatus for identifying an agent signature that overcomes or at least partially solves the above-mentioned problems.
According to an aspect of the present invention, there is provided a method for identifying an agent signature, including:
acquiring a handwritten script image of an agent, and identifying handwritten content information contained in the handwritten script image of the agent;
classifying the handwritten script image of the agent according to the handwritten content information and the channel information of the agent, and forming an agent script library according to the classification result;
when a signature handwriting image to be verified is received, identifying signature content information to be verified contained in the signature handwriting image to be verified;
extracting matched agent handwritten script images from an agent handwriting library according to the content information of the signature to be verified and agent channel information corresponding to the signature handwriting images to be verified;
training a first handwriting recognition model based on the matched agent handwriting image;
inputting the handwriting image of the signature to be verified into the first handwriting recognition model for calculation to obtain a first similarity result, and determining whether the signature to be verified is an agent signature according to the first similarity result.
Optionally, after obtaining the handwritten script image of the agent, the method further includes:
preprocessing the handwritten handwriting image of the agent; wherein the pretreatment comprises one or more of the following treatments: binarization processing, smoothing processing and character segmentation processing.
Optionally, the classifying the handwritten ink image of the agent according to the handwritten content information and the channel information of the agent, and the forming the agent ink library according to the classification result further includes:
if the word senses of the handwritten content information of the plurality of agent handwritten ink images are the same, an index is established for the word senses, and the plurality of agent handwritten ink images are stored under the index of the word senses to form an agent handwriting library.
Optionally, the method further comprises:
acquiring client information according to the content information of the signature to be verified;
according to the client information, whether signature retention data of the client at other agents exist is retrieved;
if so, training a second handwriting recognition model according to the signature retention data;
inputting the signature handwriting image to be verified to a second handwriting recognition model for calculation to obtain a second similarity result;
and determining whether the signature handwriting to be verified is the client real signature handwriting according to the second similarity result.
Optionally, the first handwriting recognition model and the second handwriting recognition model are trained based on a convolutional neural network algorithm.
Optionally, the method further comprises:
and under the condition that the signature to be verified is determined to be the agent signature according to the first similarity result, marking the signature handwriting image to be verified as an agent handwriting image sample, and bringing the proxy handwriting image sample into an agent handwriting library.
According to another aspect of the present invention, there is provided an agent signature identification apparatus, including:
the acquisition module is suitable for acquiring the handwritten handwriting image of the agent;
the first recognition module is suitable for recognizing the handwritten content information contained in the handwritten script image of the agent;
the classification and storage module is suitable for classifying the handwritten handwriting images of the agents according to the handwritten content information and the channel information of the agents and forming an agent handwriting library according to the classification result;
the second identification module is suitable for identifying the signature content information to be verified contained in the signature handwriting image to be verified when the signature handwriting image to be verified is received;
the matching module is suitable for extracting matched agent handwriting images from an agent handwriting library according to the content information of the signature to be verified and agent channel information corresponding to the signature handwriting images to be verified;
the model training module is suitable for training a first handwriting recognition model based on the matched agent handwriting image;
the computation module is suitable for inputting the signature handwriting image to be verified into the first handwriting recognition model for computation to obtain a first similarity result;
and the judging module is suitable for determining whether the signature to be verified is the agent proxy signature or not according to the first similarity result.
Optionally, the apparatus further comprises:
the preprocessing module is suitable for preprocessing the handwritten script image of the agent after acquiring the handwritten script image of the agent; wherein the pretreatment comprises one or more of the following treatments: binarization processing, smoothing processing and character segmentation processing.
Optionally, the categorizing warehousing module is further adapted to: if the word senses of the handwritten content information of the plurality of agent handwritten ink images are the same, an index is established for the word senses, and the plurality of agent handwritten ink images are stored under the index of the word senses to form an agent handwriting library.
Optionally, the apparatus further comprises:
the client information module is suitable for acquiring client information according to the content information of the signature to be verified;
the data retrieval module is suitable for retrieving whether signature retention data of the client at other agents exist or not according to the client information;
the model training module is further adapted to: training a second handwriting recognition model according to the signature retention data;
the calculation module is further adapted to: inputting the signature handwriting image to be verified to a second handwriting recognition model for calculation to obtain a second similarity result;
the determination module is further adapted to: and determining whether the signature handwriting to be verified is the client real signature handwriting according to the second similarity result.
Optionally, the first handwriting recognition model and the second handwriting recognition model are trained based on a convolutional neural network algorithm.
Optionally, the apparatus further comprises: a marking and warehousing module: and under the condition that the signature to be verified is determined to be the agent signature according to the first similarity result, the signature handwriting image to be verified is marked as an agent handwriting image sample and is brought into an agent handwriting library. .
According to yet another aspect of the present invention, there is provided a computing device comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the identification method of the agent signature.
According to yet another aspect of the present invention, a computer storage medium is provided, in which at least one executable instruction is stored, and the executable instruction causes a processor to perform operations corresponding to the identification method of the proxy signature.
According to the method and the device for identifying the proxy signature, the method comprises the following steps: acquiring a handwritten script image of an agent, and identifying handwritten content information contained in the handwritten script image of the agent; classifying the handwritten script image of the agent according to the handwritten content information and the channel information of the agent, and forming an agent script library according to the classification result; when a signature handwriting image to be verified is received, identifying signature content information to be verified contained in the signature handwriting image to be verified; extracting matched agent handwritten script images from an agent handwriting library according to the content information of the signature to be verified and agent channel information corresponding to the signature handwriting images to be verified; training a first handwriting recognition model based on the matched agent handwriting image; inputting the handwriting image of the signature to be verified into the first handwriting recognition model for calculation to obtain a first similarity result, and determining whether the signature to be verified is an agent signature according to the first similarity result. The agent proxy signature identification method provided by the invention is opposite to the traditional method, the traditional method relies on the historical signature of a client as a sample to identify the similarity relation between the signature handwriting to be verified and the historical signature handwriting of the client, while the embodiment method relies on the signature handwriting of the agent as a sample to construct an identification model, and the identification model is used for calculating the similarity relation between the signature handwriting to be verified and the handwritten handwriting of the agent, thereby identifying whether the signature handwriting to be verified is the agent proxy signature. Compared with the traditional mode, the mode reduces the difficulty of data collection, improves the technical application range, and is beneficial to preventing the risk that the client does not know to customize the service.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow diagram illustrating an embodiment of a method for identifying an agent signature of the present invention;
FIG. 2 is a flow diagram illustrating another embodiment of a method for identifying agent signature of the present invention;
FIG. 3 shows a schematic diagram of a convolutional network in an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an agent signature identification device provided by an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a computing device provided by an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The theory basis of handwriting recognition is introduced firstly, handwriting habits are dynamic setting expressions, and although a person with fixed handwriting habits is integrally controlled by personal consciousness during handwriting, specific handwriting actions are automatically realized by the writing habits. This automated repeated reproduction keeps the individual's signature or handwriting relatively stable. Even if the same person is in different time periods and different writing environments, handwriting signatures are inconsistent, so that the judgment cannot be made by only depending on certain fixed features, namely the handwriting signatures cannot be identified by only depending on manually preset handwriting feature points, and the handwriting signatures need to be realized in a mode of combining key feature points and integral image features from the aspect of integrity.
In an actual business scenario, an agent is usually regional, and business handling personnel of the same agent are relatively fixed, which results in that personnel who perform signing actions on behalf of a certain agent may be the same as the personnel who perform business handling, so that if a certain signature is to be identified by the agent business staff, the identification of the signature can be converted from verification with a real client to verification with historical handwritten data of the agent by detecting whether the signature and other signatures of the agent are signed by the same person, and both verification data and training data can be guaranteed.
In the embodiment of the invention, automatic identification is realized by mainly utilizing a convolutional neural network, and an artificial neural network is a network system which is established in an artificial mode by utilizing a large number of processing units which are widely interconnected in order to simulate the structure and the function of a human brain nervous system, wherein the large number of processing units are called artificial neurons. The artificial neural network is actually a directed network structure in which artificial neurons are used as nodes and are connected by directed weights. The positive and negative weights correspond to the excitability or inhibitivity of the synaptic connection. The full connection network is characterized in that all input information can affect the subsequent training, but the method is meaningless for image data.
Convolutional networks have two important concepts: 1. local receptive field; 2. and sharing the weight value. The local receptive field is characterized in that the relevance of points which are far away from each other in a picture is not high, so that a part of parameters are saved in a full-connection mode, only local operation is carried out, and the number of operation parameters is reduced. For "weight sharing", it is actually the same way of calculation for one image, that is, the same way of feature extraction; when the convolution is continuously performed on the input image in a sliding mode, the data in the Filter are calculated in the same mode, so that the parameter sharing is realized, and the parameter value can be reduced.
Convolutional Neural Networks (CNN) are a type of model for deep Neural networks and are guided by deep learning architectural ideas. It is particularly well-established for processing and recognizing images. The structure of the convolutional neural network comprises: input layer, convolution layer, down-sampling layer (pooling layer), full-link layer.
An input layer: the input to the entire network is typically a pixel matrix of an image, and in the above figures, the input is seen to be a three-dimensional structure, because the general image has the notion of depth, as we see a color image of RGB in general, in the form of a b c, where the first two dimensions specify the length and width of the image, the third dimension is the depth, the depth of color RGB is 3, and the depth of the black and white image in the MNIST we see before is 1.
Convolutional layer (convolutional layer): and (3) extracting features from a bottom layer to a high layer from the image by utilizing convolution operation, and ensuring local relevance and space invariance of the image. And (3) Filter: can be understood as neurons implementing a defined convolution kernel. Step size Stride: for an area, sliding is performed after the calculation is completed, and the moving distance when sliding is the Stride. Padding: considering the convolution calculation process, for the pixels near the middle of the image, we can see that the pixels at the edge are calculated "overlapping" many times, compared with the pixels at the edge which are calculated only once, and in order to ensure that the calculation times are relatively uniform, the edge is filled with some values to ensure that the pixels are also calculated many times.
Depth: the depth here does not refer to an image, but refers to the number of neurons (filters) in a certain layer, and the output is not a Feature Map but a solid composed of several Feature maps, where one Filter can process an input image into a Feature Map, the features of different Filter emphasis processes are different, and it is necessary to set multiple filters to obtain different Feature maps, so that each Filter process one Feature Map, and multiple filters can obtain multiple Feature maps, and stacking these Feature maps together is the output solid, so it can be seen that the number of filters and Feature maps is the same, and this number is the depth.
Downsampling layer (pooling layer) (sub-sampling layer): and performing down-sampling operation. And filtering out unimportant high-frequency information through convolution output of local maximum (max-pooling) and average (avg-pooling) values in the characteristic diagram. The pooling layer has several functions: 1. feature extraction is carried out on the Feature Map again, which is also an operation for reducing the data volume; 2. more abstract features are obtained, overfitting is prevented, and generalization performance is improved; 3. through the processing, the small change of the input is more tolerant, namely if the data has some noise, the influence of the noise is reduced to a certain extent through the characteristic extraction process.
Fully connected layer (full connected layer): the neurons of each layer in the network are all connected. The convolutional layer and the fully-connected layer are usually followed by a nonlinear change processing layer to enhance the expression capability of the network to the features.
The image recognition model using the convolutional neural network mainly consists of two important characteristics of the image: local correlation and spatial invariance. By repeatedly using convolution and operation, the characteristics of the image can be well reflected. When the convolution layer extracts the features, the input and output data have relevance, the relative relation between the features is reserved, the features are not extracted in an isolated way in a linear relation, and the nonlinear combination of the image internal information is represented in a local relevance way. Meanwhile, when the characteristics are mapped, because weights are shared among neurons of the convolutional network, the number of parameters is greatly reduced, the complexity is reduced, and the information effectiveness is greatly improved.
Fig. 1 shows a flow chart of an embodiment of the method for identifying a proxy signature according to the present invention, which, as shown in fig. 1, comprises the following steps:
and S101, acquiring the handwritten script image of the agent, and identifying handwritten content information contained in the handwritten script image of the agent.
The method of the embodiment of the invention needs to archive and record the handwritten handwriting of the agent, and uniformly collects all the handwritten fonts of the business documents transacted by the agent channel so as to form an agent handwriting library.
Firstly, handwriting images of various agents are obtained, wherein the handwriting comprises but is not limited to signature handwriting, and the character contents of Chinese characters or English and the like contained in the handwriting images of the agents are identified by utilizing an identification technology. The method for acquiring the handwritten script image of the agent is not limited, and the handwritten script image of the agent can be acquired in a scanning or photographing mode.
And S102, classifying the handwritten script image of the agent according to the handwritten content information and the channel information of the agent, and forming an agent handwriting library according to the classification result.
Wherein, the channel information of the agent may refer to an agent number. According to the handwritten content information contained in the handwritten script images of the agents and the corresponding agent channel information, the handwritten script images of the agents, which are consistent with the handwritten content information, of the same agent are classified into one class and are merged into a library for storage. In a specific implementation, the first category may be established according to the agent number, and the second category subordinate to the first category may be established according to the handwritten content information under the first category, which, of course, is not limited thereto.
And step S103, when the signature handwriting image to be verified is received, identifying the signature content information to be verified contained in the signature handwriting image to be verified.
Step S101-step S102 are processing procedures for establishing an agent handwriting library, and step S103-step S106 are identification procedures for judging whether the signature to be verified is an agent proxy signature. Firstly, receiving a signature handwriting image to be verified, and recognizing character contents such as Chinese or English and the like contained in the signature handwriting image to be verified by using a recognition technology to obtain signature content information to be verified. The to-be-verified signature handwriting image is an electronic signature document, which can be obtained by scanning or shooting a paper signature document, and certainly, some documents are electronic documents.
And step S104, extracting the matched agent handwriting image from the agent handwriting library according to the content information of the signature to be verified and the agent channel information corresponding to the signature handwriting image to be verified.
And then, searching in an agent handwriting library according to the content information of the signature to be verified and the agent number corresponding to the signature handwriting image for agent verification to obtain a matched agent handwriting image.
And step S105, training a first handwriting recognition model based on the matched agent handwriting image.
The extracted handwritten script image of the agent is used as a training sample to train the first handwriting recognition model, for example, the first handwriting recognition model can be trained through a convolutional neural network algorithm.
And S106, inputting the handwriting image of the signature to be verified into the first handwriting recognition model for calculation to obtain a first similarity result, and determining whether the signature to be verified is an agent proxy signature or not according to the first similarity result.
And finally, inputting the signature handwriting image to be verified into the first handwriting recognition model for calculation, outputting a first similarity result, and if the first similarity exceeds a preset threshold, indicating that the similarity between the signature handwriting to be verified and the handwritten handwriting of the agent is higher, judging that the signature to be verified is the agent signature. Otherwise, if the first similarity does not exceed the preset threshold, the handwriting of the signature to be verified is not similar to the handwriting of the agent, and the signature to be verified is determined not to be signed by the agent.
The embodiment of the invention combines the recognition comparison of Chinese characters and the verification of specific characteristics in a specific agent handwriting recognition scene. The method comprises the steps of firstly identifying characters consistent with a signature to be verified from handwritten contents of an agent, and then verifying whether the characters are similar in overall characteristics and local characteristics by utilizing a neural network so as to determine whether the signature is signed by an agent business worker.
Therefore, the agent proxy signature identification method provided by the embodiment of the invention is opposite to the traditional method, the traditional method relies on the historical signature of a client as a sample to identify the similarity between the signature handwriting to be verified and the historical signature handwriting of the client, and the embodiment of the invention relies on the signature handwriting of the agent as a sample to construct an identification model, and the identification model is used for calculating the similarity between the signature handwriting to be verified and the handwritten handwriting of the agent, so as to identify whether the signature handwriting to be verified is the agent proxy signature. Compared with the traditional mode, the mode reduces the difficulty of data collection, improves the technical application range, and is beneficial to preventing the risk that the client does not know to customize the service.
Fig. 2 is a flow chart of another embodiment of the method for identifying a proxy signature of the present invention, as shown in fig. 2, the method comprising the steps of:
step S201, acquiring the agent handwriting image, and identifying the handwriting content information contained in the agent handwriting image.
Firstly, acquiring handwriting images of various agents, and identifying Chinese characters contained in the handwriting images of the agents by using an identification technology.
Optionally, after the handwritten image of the agent is acquired, preprocessing is performed first to form a clear and independent single Chinese character image which is convenient to compare and maintain. In this case, the handwritten trace image after the preprocessing is recognized, so as to obtain the handwritten content information included in the handwritten trace image.
Wherein, the pretreatment mainly comprises the following three treatments:
binarization processing of the handwriting image: the signature Chinese character image is processed into (0, 1) digital information, namely the gray value of a pixel point on the image is set to be 0 or 255, namely the whole image presents an obvious black and white effect. The binary image is obtained, so that the image is beneficial to further processing, the collective property of the image is only related to the position of a point with a pixel value of 0 or 255, the multi-level value of the pixel is not related, the processing is simple, and the processing and compression amount of data are small.
And (3) smoothing the handwriting image: in order to reduce edge noise of handwriting, smooth noise reduction processing needs to be performed on the binarized signature image. The smoothing filtering in the spatial domain is generally performed by a simple averaging method, that is, an average luminance value of neighboring pixel points is obtained. The size of the neighborhood is directly related to the smoothing effect, the larger the neighborhood is, the better the smoothing effect is, but the larger the neighborhood is, the larger the edge information loss is due to the fact that the smoothing effect is, so that the output image becomes fuzzy, and therefore the size of the neighborhood needs to be reasonably selected. In the embodiment of the invention, in order to ensure the definition of the smoothed handwriting, the edge of the handwriting needs to be protected from blurring, so that a median filtering method is selected for image smoothing noise reduction treatment, namely, the median of each pixel of an image is replaced by the median of a neighborhood (a square area taking the current pixel as the center) pixel, so that the impulse noise is well filtered, and particularly, the edge of a signal can be protected from blurring while the noise is filtered, but the edge of the signal can be washed away from the texture in a uniform medium area.
Chinese character segmentation treatment: in order to improve the accuracy of verification, matching verification is carried out according to a single Chinese character in the embodiment of the invention. After the two steps, the handwriting content is still in the form of sentences or phrases, which does not meet the requirement of matching and checking according to a single Chinese character in the follow-up process, so that the handwriting content needs to be segmented, and is finally stored in the form of independent Chinese characters. The Chinese character segmentation is mainly completed by judging the width of space white left by the Chinese characters and the connection handwriting. The width judgment of the space margin is mainly based on the identification of the transverse width, because the left-right spacing is the main mode for identifying a single Chinese character structurally. The specific width judgment is obtained by self-learning of the historical handwriting, and can also be realized by means of manual characteristic setting.
And S202, classifying the handwritten handwriting images of the agent according to the handwritten content information and the channel information of the agent, and forming an agent handwriting library according to a classification result.
In specific implementation, a first category can be established according to the agent number, and a second category subordinate to the first category is established according to the handwritten content information under the first category. For example, a plurality of agent handwritten ink images of an agent a are acquired, it is recognized that handwritten content information of the agent handwritten ink images includes "zhang san", "lie ye", and the like, the agent number is "agent a", a first category "agent a" is established, and a second category "zhang san", "lie ye", and the like are established, all agent handwritten ink images of the agent a with the text content of zhang san are stored under the category "agent a-zhang", and all agent handwritten ink images of the agent a with the text content of lie ye are stored under the category "agent-lie ye". Of course, the present invention is only an example, and the classification manner of the present invention is not limited thereto, as long as the handwritten handwriting images of the same agent and the handwritten content information of the same agent are classified into one category.
In an optional implementation mode, the handwritten handwriting images of the agents can be classified by combining time information and/or business information to form an agent handwriting library.
In an alternative embodiment, the agent handwriting images can be further classified by combining word senses to form an agent handwriting library. Specifically, if the word senses of the handwritten content information of a plurality of agent handwritten ink images are the same, an index is established for the word senses, and the plurality of agent handwritten ink images are stored under the index of the word senses to form an agent handwriting library. For example, in a plurality of electronic business documents, if different handwriting exists but the word senses are the same, an index is established according to the word senses, and a plurality of pens with all the word senses are stored under the index. In the subsequent process, the handwriting to be compared can be quickly searched according to the word sense.
Step S203, when the signature handwriting image to be verified is received, identifying the signature content information to be verified contained in the signature handwriting image to be verified.
And receiving the signature handwriting image to be verified, and recognizing Chinese characters contained in the signature handwriting image to be verified by using a character recognition technology to obtain the signature content information to be verified. The to-be-verified signature handwriting image is an electronic signature document, which can be obtained by scanning or shooting a paper signature document, and certainly, some documents are electronic documents. The step is also to identify the handwriting in the image of the signature handwriting to be verified and judge which Chinese characters the signature is.
And S204, extracting the matched agent handwriting image from the agent handwriting library according to the content information of the signature to be verified and the agent channel information corresponding to the signature handwriting image to be verified.
And then, searching in an agent handwriting library according to the content information of the signature to be verified and the agent number corresponding to the signature handwriting image to be verified to obtain a matched agent handwriting image. Following the above example, if a signature handwriting image to be verified of the agent a is received, the content information of the signature to be verified is identified as "lie four", and the agent is encoded as "agent a", then in the agent handwriting library, the agent handwriting image under the category "agent a-lie four" is extracted.
And S205, training a first handwriting recognition model based on the matched agent handwriting image.
And training a first handwriting recognition model based on the extracted handwritten script image of the agent. And dividing the matched agent handwriting image into training data and verification data, enabling the training data to enter a convolution network for iterative training, extracting and recognizing image characteristics in batches, and performing a large amount of detection on the verification data after obtaining complete iteration, thereby continuously reducing the recognition error rate.
Fig. 3 shows a schematic diagram of a convolution network in an embodiment of the present invention, a neural network including two layers of convolutions is formed in the embodiment of the present invention, a convolution neural network algorithm extracts an input handwriting image, a certain number of feature maps (such as angles, textures, gray scales, and the like) are obtained at an a1 convolution layer, then sampling operation calculation (such as weighted values, biasing, and the like) is performed on an a1 feature map, feature mapping information of a1 is obtained through a function, a sampling layer B1 is obtained, then one convolution is repeated, that is, a2 and a B2 are performed again, the obtained data is constructed in a fully-connected hierarchy and input to a classifier, and a conclusion is obtained through recognition, so that one iterative training is ended. And continuously adjusting process parameters according to the output result to carry out continuous iteration. 4 hidden layers are set, and the learning and feature extraction are sequentially carried out on the image layer by layer in a halving mode.
Step S206, inputting the handwriting image of the signature to be verified into the first handwriting recognition model for calculation to obtain a first similarity result, and determining whether the signature to be verified is an agent proxy signature or not according to the first similarity result.
And inputting the signature handwriting image to be verified into a first handwriting recognition model for calculation, outputting a first similarity result, if the first similarity exceeds a preset threshold, indicating that the similarity between the signature handwriting to be verified and the proxy handwriting is higher, determining that the signature to be verified is a proxy signature, marking the signature handwriting image to be verified as a proxy handwriting image sample, and bringing the proxy handwriting image sample into a proxy handwriting library. Otherwise, if the first similarity does not exceed the preset threshold, the handwriting of the signature to be verified is not similar to the handwriting of the agent, and the signature to be verified is determined not to be signed by the agent.
And step S207, acquiring customer information according to the signature content information to be verified, and searching whether signature retention data of the customer at other agents exist or not according to the customer information.
And then, acquiring the customer information according to the content information of the signature to be verified, wherein in practical application, the name of the customer is generally signed on the document, and the identified content information of the signature to be verified, namely the name of the customer, can acquire the identity information of the customer according to the name of the customer. Then, the past business acceptance record and paperless authentication record of the client are searched according to the client information, whether the records of the business acceptance record and the signature retention of other agents exist or not is judged, and the signature retention is the historical real handwriting image of the client without considering the condition of the proxy signing of other agents. For example, if the signature script image to be verified belongs to the agent a, there is client signature retention data associated with the client information in the business records of other agents except the agent a.
And S208, if the second handwriting recognition model exists, training the second handwriting recognition model according to the signature retention data.
And if signature retention data of the client at other agents exist, extracting the part of signature retention data, and training a second handwriting recognition model according to the signature retention data.
And S209, inputting the signature handwriting image to be verified into a second handwriting recognition model for calculation to obtain a second similarity result, and determining whether the signature handwriting to be verified is the real signature handwriting of the client according to the second similarity result.
And inputting the signature handwriting image to be verified into a second handwriting recognition model for calculation, outputting a second similarity result, and if the second similarity exceeds a preset threshold, indicating that the similarity between the signature handwriting to be verified and the historical signature handwriting of the customer is higher, determining that the signature to be verified is the real handwriting of the customer and is not the proxy signature handwriting. Otherwise, if the second similarity does not exceed the preset threshold, the signature handwriting to be verified is not similar to the historical signature handwriting of the customer, and the agent signing risk is determined to exist.
During specific implementation, the identification mode can be selected according to specific retrieved information, and if the matched agent handwritten script image is retrieved, a model is constructed based on the matched agent handwritten script image and is used for identifying whether the signature handwriting to be verified is similar to the agent handwritten handwriting; if the retention data of the client at other agents is retrieved, a model is built based on the retention data to identify whether the signature handwriting to be verified is the real handwriting of the client; if both are searched, two identification modes are adopted at the same time, and the results of the two identification modes are integrated to judge whether the signature handwriting to be verified is the agent signature.
In summary, in the embodiments of the present invention, on the one hand, an agent to-be-signed recognition method based on agent signature handwriting is provided, and under the condition that matched agent handwritten handwriting can be retrieved, a recognition model is constructed based on the agent handwritten handwriting as a sample, and the recognition model is used to calculate a similarity relationship between the to-be-verified signature handwriting and the agent handwritten handwriting, so as to recognize whether the to-be-verified signature is an agent signature, which reduces data collection difficulty and improves technical application range. On the other hand, the to-be-verified signature handwriting recognition method based on the client reserved handwriting data is provided, under the condition that the client handwriting reservation can be retrieved, a recognition model is established based on the client reserved handwriting as a sample, and the model is used for recognizing the similarity relation between the to-be-verified signature handwriting and the historical real handwriting of the client, so that whether the to-be-verified signature handwriting is the client real handwriting is recognized. The two modes are combined, the identification accuracy rate of the agent signature can be improved, the corresponding identification mode can be selected according to different data retrieval results, the flexibility is higher, the agent with the agent signature behavior can be effectively identified, and the risk that the client does not know to customize the service is also prevented.
Fig. 4 is a schematic structural diagram of an embodiment of the identifying apparatus for agent signature according to the present invention. As shown in fig. 4, the apparatus includes:
an obtaining module 41 adapted to obtain a handwritten script image of an agent;
a first recognition module 42 adapted to recognize handwritten content information contained in the agent handwritten image;
a classification and storage module 43, adapted to classify the handwritten script images of the agent according to the handwritten content information and the channel information of the agent, and form an agent handwriting library according to the classification result;
the second identification module 44 is adapted to identify the signature content information to be verified contained in the signature handwriting image to be verified when the signature handwriting image to be verified is received;
the matching module 45 is suitable for extracting matched agent handwriting images from an agent handwriting library according to the content information of the signature to be verified and agent channel information corresponding to the signature handwriting images to be verified;
a model training module 46 adapted to train a first handwriting recognition model based on the matched agent handwriting image;
the calculation module 47 is suitable for inputting the signature handwriting image to be verified into the first handwriting recognition model for calculation to obtain a first similarity result;
and the judging module 48 is adapted to determine whether the signature to be verified is the agent proxy signature according to the first similarity result.
Optionally, the apparatus further comprises:
the preprocessing module is suitable for preprocessing the handwritten script image of the agent after acquiring the handwritten script image of the agent; wherein the pretreatment comprises one or more of the following treatments: binarization processing, smoothing processing and character segmentation processing.
Optionally, the categorizing-binning module 43 is further adapted to: if the word senses of the handwritten content information of the plurality of agent handwritten ink images are the same, an index is established for the word senses, and the plurality of agent handwritten ink images are stored under the index of the word senses to form an agent handwriting library.
Optionally, the apparatus further comprises:
the client information module is suitable for acquiring client information according to the content information of the signature to be verified;
the data retrieval module is suitable for retrieving whether signature retention data of the client at other agents exist or not according to the client information;
the model training module 46 is further adapted to: training a second handwriting recognition model according to the signature retention data;
the calculation module 47 is further adapted to: inputting the signature handwriting image to be verified to a second handwriting recognition model for calculation to obtain a second similarity result;
the determination module 48 is further adapted to: and determining whether the signature handwriting to be verified is the client real signature handwriting according to the second similarity result.
Optionally, the first handwriting recognition model and the second handwriting recognition model are trained based on a convolutional neural network algorithm.
Optionally, the apparatus further comprises:
a marking and warehousing module: and under the condition that the signature to be verified is determined to be the agent signature according to the first similarity result, the signature handwriting image to be verified is marked as an agent handwriting image sample and is brought into an agent handwriting library.
The embodiment of the invention provides a nonvolatile computer storage medium, wherein at least one executable instruction is stored in the computer storage medium, and the computer executable instruction can execute the identification method of the agent proxy signature in any method embodiment.
The executable instructions may be specifically configured to cause the processor to:
acquiring a handwritten script image of an agent, and identifying handwritten content information contained in the handwritten script image of the agent;
classifying the handwritten script image of the agent according to the handwritten content information and the channel information of the agent, and forming an agent script library according to the classification result;
when a signature handwriting image to be verified is received, identifying signature content information to be verified contained in the signature handwriting image to be verified;
extracting matched agent handwritten script images from an agent handwriting library according to the content information of the signature to be verified and agent channel information corresponding to the signature handwriting images to be verified;
training a first handwriting recognition model based on the matched agent handwriting image;
inputting the handwriting image of the signature to be verified into the first handwriting recognition model for calculation to obtain a first similarity result, and determining whether the signature to be verified is an agent signature according to the first similarity result.
In an alternative, the executable instructions cause the processor to:
after acquiring the handwritten script image of the agent, preprocessing the handwritten script image of the agent; wherein the pretreatment comprises one or more of the following treatments: binarization processing, smoothing processing and character segmentation processing.
In an alternative, the executable instructions cause the processor to:
if the word senses of the handwritten content information of the plurality of agent handwritten ink images are the same, an index is established for the word senses, and the plurality of agent handwritten ink images are stored under the index of the word senses to form an agent handwriting library.
In an alternative, the executable instructions cause the processor to:
acquiring client information according to the content information of the signature to be verified;
according to the client information, whether signature retention data of the client at other agents exist is retrieved;
if so, training a second handwriting recognition model according to the signature retention data;
inputting the signature handwriting image to be verified to a second handwriting recognition model for calculation to obtain a second similarity result;
and determining whether the signature handwriting to be verified is the client real signature handwriting according to the second similarity result.
In an alternative mode, the first handwriting recognition model and the second handwriting recognition model are obtained by training based on a convolutional neural network algorithm.
In an alternative, the executable instructions cause the processor to:
and under the condition that the signature to be verified is determined to be the agent signature according to the first similarity result, marking the signature handwriting image to be verified as an agent handwriting image sample, and bringing the proxy handwriting image sample into an agent handwriting library.
Fig. 5 is a schematic structural diagram of an embodiment of a computing device according to the present invention, and a specific embodiment of the present invention does not limit a specific implementation of the computing device.
As shown in fig. 5, the computing device may include: a processor (processor)502, a Communications Interface 504, a memory 506, and a communication bus 508.
Wherein: the processor 502, communication interface 504, and memory 506 communicate with one another via a communication bus 508. A communication interface 504 for communicating with network elements of other devices, such as clients or other servers. Processor 502, configured to execute program 510, may specifically perform relevant steps in the above-described embodiments of a method for identifying an agent signature for a computing device.
In particular, program 510 may include program code that includes computer operating instructions.
The processor 502 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement an embodiment of the present invention. The computing device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 506 for storing a program 510. The memory 506 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 510 may specifically be used to cause the processor 502 to perform the following operations:
acquiring a handwritten script image of an agent, and identifying handwritten content information contained in the handwritten script image of the agent;
classifying the handwritten script image of the agent according to the handwritten content information and the channel information of the agent, and forming an agent script library according to the classification result;
when a signature handwriting image to be verified is received, identifying signature content information to be verified contained in the signature handwriting image to be verified;
extracting matched agent handwritten script images from an agent handwriting library according to the content information of the signature to be verified and agent channel information corresponding to the signature handwriting images to be verified;
training a first handwriting recognition model based on the matched agent handwriting image;
inputting the handwriting image of the signature to be verified into the first handwriting recognition model for calculation to obtain a first similarity result, and determining whether the signature to be verified is an agent signature according to the first similarity result.
In an alternative, the program 510 causes the processor 502 to:
preprocessing the handwritten handwriting image of the agent; wherein the pretreatment comprises one or more of the following treatments: binarization processing, smoothing processing and character segmentation processing.
In an alternative, the program 510 causes the processor 502 to:
if the word senses of the handwritten content information of the plurality of agent handwritten ink images are the same, an index is established for the word senses, and the plurality of agent handwritten ink images are stored under the index of the word senses to form an agent handwriting library.
In an alternative, the program 510 causes the processor 502 to:
acquiring client information according to the content information of the signature to be verified;
according to the client information, whether signature retention data of the client at other agents exist is retrieved;
if so, training a second handwriting recognition model according to the signature retention data;
inputting the signature handwriting image to be verified to a second handwriting recognition model for calculation to obtain a second similarity result;
and determining whether the signature handwriting to be verified is the client real signature handwriting according to the second similarity result.
In an alternative mode, the first handwriting recognition model and the second handwriting recognition model are obtained by training based on a convolutional neural network algorithm.
In an alternative, the program 510 causes the processor 502 to:
and under the condition that the signature to be verified is determined to be the agent signature according to the first similarity result, marking the signature handwriting image to be verified as an agent handwriting image sample, and bringing the proxy handwriting image sample into an agent handwriting library.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
Claims (10)
1. A method of identifying an agent signature, comprising:
acquiring a handwritten script image of an agent, and identifying handwritten content information contained in the handwritten script image of the agent;
classifying the handwritten script image of the agent according to the handwritten content information and channel information of the agent, and forming an agent script library according to a classification result;
when a signature handwriting image to be verified is received, identifying signature content information to be verified contained in the signature handwriting image to be verified;
extracting matched agent handwritten script images from the agent handwriting library according to the content information of the signature to be verified and agent channel information corresponding to the signature handwriting images to be verified;
training a first handwriting recognition model based on the matched agent handwriting image;
and inputting the handwriting image of the signature to be verified into the first handwriting recognition model for calculation to obtain a first similarity result, and determining whether the signature to be verified is an agent signature according to the first similarity result.
2. The method of claim 1, wherein after the obtaining of the agent handwriting image, the method further comprises:
preprocessing the handwritten handwriting image of the agent; wherein the pre-treatment comprises one or more of the following treatments: binarization processing, smoothing processing and character segmentation processing.
3. The method of claim 1, wherein the classifying the agent handwriting images according to the handwriting information and channel information of the agent, and the forming an agent handwriting library according to the classification result further comprises:
if the word senses of the handwritten content information of the plurality of agent handwritten ink images are the same, an index is established for the word senses, and the plurality of agent handwritten ink images are stored under the index of the word senses to form an agent handwriting library.
4. The method of claim 1, further comprising:
acquiring client information according to the signature content information to be verified;
according to the customer information, retrieving whether signature retention data of the customer at other agents exist or not;
if so, training a second handwriting recognition model according to the signature retention data;
inputting the signature handwriting image to be verified to the second handwriting recognition model for calculation to obtain a second similarity result;
and determining whether the signature handwriting to be verified is the client real signature handwriting according to the second similarity result.
5. A method according to claim 1 or 4, characterized in that the first and second handwriting recognition models are trained on convolutional neural network algorithms.
6. The method of claim 1, further comprising:
and under the condition that the signature to be verified is determined to be the agent signature according to the first similarity result, marking the signature handwriting image to be verified as an agent handwriting image sample and bringing the sample into an agent handwriting library.
7. An apparatus for identifying an agent signature, comprising:
the acquisition module is suitable for acquiring the handwritten handwriting image of the agent;
the first recognition module is suitable for recognizing the handwritten content information contained in the handwritten script image of the agent;
the classification and storage module is suitable for classifying the handwritten script images of the agents according to the handwritten content information and the channel information of the agents and forming an agent handwriting library according to a classification result;
the second identification module is suitable for identifying the signature content information to be verified contained in the signature handwriting image to be verified when the signature handwriting image to be verified is received;
the matching module is suitable for extracting matched agent handwriting images from the agent handwriting library according to the content information of the signature to be verified and agent channel information corresponding to the signature handwriting images to be verified;
the model training module is suitable for training a first handwriting recognition model based on the matched agent handwriting image;
the computation module is suitable for inputting the signature handwriting image to be verified into the first handwriting recognition model for computation to obtain a first similarity result;
and the judging module is suitable for determining whether the signature to be verified is the agent proxy signature or not according to the first similarity result.
8. The apparatus of claim 7, further comprising:
the preprocessing module is suitable for preprocessing the handwritten script image of the agent after acquiring the handwritten script image of the agent; wherein the pre-treatment comprises one or more of the following treatments: binarization processing, smoothing processing and character segmentation processing.
9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction which causes the processor to execute the operation corresponding to the identification method of the agent proxy signature as claimed in any one of claims 1-6.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the method of identifying agent proxy signatures of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010162874.2A CN113378609B (en) | 2020-03-10 | 2020-03-10 | Agent proxy signature identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010162874.2A CN113378609B (en) | 2020-03-10 | 2020-03-10 | Agent proxy signature identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113378609A true CN113378609A (en) | 2021-09-10 |
| CN113378609B CN113378609B (en) | 2023-07-21 |
Family
ID=77568851
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010162874.2A Active CN113378609B (en) | 2020-03-10 | 2020-03-10 | Agent proxy signature identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113378609B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610064A (en) * | 2021-10-09 | 2021-11-05 | 北京世纪好未来教育科技有限公司 | Handwriting recognition method and device |
| CN114241463A (en) * | 2021-11-12 | 2022-03-25 | 中国南方电网有限责任公司 | Signature verification method and device, computer equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6424728B1 (en) * | 1999-12-02 | 2002-07-23 | Maan Ammar | Method and apparatus for verification of signatures |
| US20030179912A1 (en) * | 2002-03-19 | 2003-09-25 | Fujitsu Prime Software Technologies Limited | Hand-written signature authentication program, method, and apparatus |
| CN1701323A (en) * | 2001-10-15 | 2005-11-23 | 西尔弗布鲁克研究有限公司 | Digital ink database searching using handwriting feature synthesis |
| US20070047817A1 (en) * | 2005-08-29 | 2007-03-01 | Microsoft Corporation | Style aware use of writing input |
| US20150078665A1 (en) * | 2012-09-28 | 2015-03-19 | Jerry Wang | Handwritten signature detection, validation, and confirmation |
| CN104820924A (en) * | 2015-05-13 | 2015-08-05 | 重庆邮电大学 | Online safe payment system based on handwriting authentication |
| CN106803082A (en) * | 2017-01-23 | 2017-06-06 | 重庆邮电大学 | A kind of online handwriting recognition methods based on conditional generation confrontation network |
| CN108985297A (en) * | 2018-06-04 | 2018-12-11 | 平安科技（深圳）有限公司 | Handwriting model training, hand-written image recognition methods, device, equipment and medium |
| US20190050406A1 (en) * | 2017-08-08 | 2019-02-14 | Microsoft Technology Licensing, Llc | Intelligent query system for attachments |
| CN109446905A (en) * | 2018-09-26 | 2019-03-08 | 深圳壹账通智能科技有限公司 | Sign electronically checking method, device, computer equipment and storage medium |
| CN110096977A (en) * | 2019-04-18 | 2019-08-06 | 中金金融认证中心有限公司 | The training method and handwriting verification method, equipment and medium of handwriting verification model |
| TW201942803A (en) * | 2018-03-31 | 2019-11-01 | 華南商業銀行股份有限公司 | Transaction system based on face recognition for verification and method thereof |
| WO2019232853A1 (en) * | 2018-06-04 | 2019-12-12 | 平安科技（深圳）有限公司 | Chinese model training method, chinese image recognition method, device, apparatus and medium |
| CN114241463A (en) * | 2021-11-12 | 2022-03-25 | 中国南方电网有限责任公司 | Signature verification method and device, computer equipment and storage medium |
-
2020
- 2020-03-10 CN CN202010162874.2A patent/CN113378609B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6424728B1 (en) * | 1999-12-02 | 2002-07-23 | Maan Ammar | Method and apparatus for verification of signatures |
| CN1701323A (en) * | 2001-10-15 | 2005-11-23 | 西尔弗布鲁克研究有限公司 | Digital ink database searching using handwriting feature synthesis |
| US20030179912A1 (en) * | 2002-03-19 | 2003-09-25 | Fujitsu Prime Software Technologies Limited | Hand-written signature authentication program, method, and apparatus |
| US20070047817A1 (en) * | 2005-08-29 | 2007-03-01 | Microsoft Corporation | Style aware use of writing input |
| US20150078665A1 (en) * | 2012-09-28 | 2015-03-19 | Jerry Wang | Handwritten signature detection, validation, and confirmation |
| CN104820924A (en) * | 2015-05-13 | 2015-08-05 | 重庆邮电大学 | Online safe payment system based on handwriting authentication |
| CN106803082A (en) * | 2017-01-23 | 2017-06-06 | 重庆邮电大学 | A kind of online handwriting recognition methods based on conditional generation confrontation network |
| US20190050406A1 (en) * | 2017-08-08 | 2019-02-14 | Microsoft Technology Licensing, Llc | Intelligent query system for attachments |
| TW201942803A (en) * | 2018-03-31 | 2019-11-01 | 華南商業銀行股份有限公司 | Transaction system based on face recognition for verification and method thereof |
| CN108985297A (en) * | 2018-06-04 | 2018-12-11 | 平安科技（深圳）有限公司 | Handwriting model training, hand-written image recognition methods, device, equipment and medium |
| WO2019232853A1 (en) * | 2018-06-04 | 2019-12-12 | 平安科技（深圳）有限公司 | Chinese model training method, chinese image recognition method, device, apparatus and medium |
| CN109446905A (en) * | 2018-09-26 | 2019-03-08 | 深圳壹账通智能科技有限公司 | Sign electronically checking method, device, computer equipment and storage medium |
| CN110096977A (en) * | 2019-04-18 | 2019-08-06 | 中金金融认证中心有限公司 | The training method and handwriting verification method, equipment and medium of handwriting verification model |
| CN114241463A (en) * | 2021-11-12 | 2022-03-25 | 中国南方电网有限责任公司 | Signature verification method and device, computer equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| LI MA等: "Personal identification based on iris texture analysis", 《IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》, pages 1519 - 1533 * |
| 张云: "多因子融合的移动终端用户身份识别机制研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, pages 138 - 6617 * |
| 杨子华等: "基于纹理分析的笔迹识别系统", 《湖南工程学院学报（自然科学版）》, pages 67 - 69 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610064A (en) * | 2021-10-09 | 2021-11-05 | 北京世纪好未来教育科技有限公司 | Handwriting recognition method and device |
| CN113610064B (en) * | 2021-10-09 | 2022-02-08 | 北京世纪好未来教育科技有限公司 | Handwriting recognition method and device |
| CN114241463A (en) * | 2021-11-12 | 2022-03-25 | 中国南方电网有限责任公司 | Signature verification method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113378609B (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kiran et al. | Offline signature recognition using image processing techniques and back propagation neuron network system | |
| CN111191568B (en) | Method, device, equipment and medium for identifying flip image | |
| CN111353491B (en) | Text direction determining method, device, equipment and storage medium | |
| CN111428593A (en) | Character recognition method and device, electronic equipment and storage medium | |
| CN112862024B (en) | Text recognition method and system | |
| WO2022247539A1 (en) | Living body detection method, estimation network processing method and apparatus, computer device, and computer readable instruction product | |
| CN113011253B (en) | Facial expression recognition method, device, equipment and storage medium based on ResNeXt network | |
| CN105335760A (en) | Image number character recognition method | |
| CN113378609B (en) | Agent proxy signature identification method and device | |
| Kamboj et al. | CED-Net: context-aware ear detection network for unconstrained images | |
| Jain et al. | Signature verification using geometrical features and artificial neural network classifier | |
| CN113111880A (en) | Certificate image correction method and device, electronic equipment and storage medium | |
| CN117558011B (en) | Image text tampering detection method based on self-consistency matrix and multi-scale loss | |
| Agarwal et al. | A utility of pores as level 3 features in latent fingerprint identification | |
| CN114971294A (en) | Data acquisition method, device, equipment and storage medium | |
| Lavanya et al. | Particle Swarm Optimization Ear Identification System | |
| CN117058723B (en) | Palmprint recognition method, palmprint recognition device and storage medium | |
| Kavitha et al. | Fuzzy local ternary pattern and skin texture properties based countermeasure against face spoofing in biometric systems | |
| Houtinezhad et al. | Writer-independent signature verification based on feature extraction fusion | |
| CN116758622A (en) | Data processing method, device, system and medium for attendance management system | |
| Li | Saliency prediction based on multi-channel models of visual processing | |
| CN115620315A (en) | Handwritten text detection method, device, server and storage medium | |
| Cai et al. | Bank card and ID card number recognition in Android financial APP | |
| CN115880702A (en) | Data processing method, device, equipment, program product and storage medium | |
| CN115188031A (en) | Fingerprint identification method, computer program product, storage medium and electronic device |
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 |