CN110245616A - A kind of falseness order for arrest method for early warning and device - Google Patents
A kind of falseness order for arrest method for early warning and device Download PDFInfo
- Publication number
- CN110245616A CN110245616A CN201910522072.5A CN201910522072A CN110245616A CN 110245616 A CN110245616 A CN 110245616A CN 201910522072 A CN201910522072 A CN 201910522072A CN 110245616 A CN110245616 A CN 110245616A
- Authority
- CN
- China
- Prior art keywords
- picture
- wanted
- false
- detected
- pictures
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012545 processing Methods 0.000 claims description 34
- 238000012549 training Methods 0.000 claims description 26
- 238000007781 pre-processing Methods 0.000 claims description 18
- 230000009466 transformation Effects 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 abstract 1
- 238000013527 convolutional neural network Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Tourism & Hospitality (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of false order for arrest method for early warning and device, method includes: to obtain false order for arrest picture sample, is pre-processed to false order for arrest picture, and be cut into several part pictures；The corresponding initial model of construction each section picture in advance is obtained, and is trained verifying, generates corresponding identification model；Order for arrest picture to be detected is obtained, order for arrest picture is pre-processed, and is cut into several part pictures to be detected；Each section picture to be detected is inputted into corresponding identification model, obtains recognition result；If there is one or more identification models to identify picture as false picture in recognition result, order for arrest picture to be detected is false order for arrest, and is issued warning signal.The embodiment of the present invention can identify the false order for arrest spread on network, improve the hitting dynamics of order for arrest swindle, reduce the property loss of the people, improve the property safety of the people.
Description
Technical Field
The invention relates to the technical field of information security, in particular to a false wanted instruction early warning method and device.
Background
Since 2011, the number of telecommunication fraud cases is increased rapidly, and the number of information fraud cases is increased, so that the whole situation is high. The number of people receiving fraud information nationwide exceeds 5 hundred million, which means that at least 1 person per 3 people nationwide has received fraud information. The information fraud has been upgraded from a network-casting type to a precise and high-tech, and the information fraud perpetrators are in a youthful state. With the increase of information fraud cases and important cases, the whole situation is high, the lost amount of a single case is more than 1 billion yuan at most, and cases with more than one million yuan are frequently lost, so that the adverse effect is caused.
The wanted fraud amount is the most huge and the influence is the worst. Fraud molecules fraud the masses through counterfeiting wanted orders, pretend to be public inspection personnel, fraud the masses through network telephones, the masses are very easy to cheat due to meticulous means of fraud, and the masses are often all accumulated to be cheated to be empty. Therefore, false wanted crimes cannot be identified in the prior art, so that the wanted crimes are effectively struck, and the property safety of citizens is protected.
Accordingly, the prior art is yet to be improved and developed.
Disclosure of Invention
In view of the defects of the prior art, the invention aims to provide a false wanted instruction early warning method and a false wanted instruction early warning device, and aims to solve the problems that false wanted instructions cannot be identified in the prior art, so that wanted instruction crimes are effectively struck, and the property safety of citizens is protected.
The technical scheme of the invention is as follows:
a false wanted early warning method, the method comprising:
acquiring a sample of a false wanted picture, preprocessing the false wanted picture, and cutting the preprocessed false wanted picture into a plurality of partial pictures;
acquiring an initial model corresponding to each part of picture which is constructed in advance, and training and verifying the corresponding initial model according to each part of picture to generate a corresponding recognition model;
acquiring wanted pictures to be detected, preprocessing the wanted pictures, and cutting the preprocessed wanted pictures to be detected into a plurality of parts of pictures to be detected;
inputting each part of picture to be detected into a corresponding recognition model to obtain a recognition result;
and if one or more identification models identify the pictures as false pictures in the identification result, the wanted pictures to be detected are false wanted pictures, and an early warning signal is sent out.
Optionally, the obtaining a sample of the false wanted picture, preprocessing the false wanted picture, and dividing the preprocessed false wanted picture into a plurality of parts of pictures includes:
acquiring a sample of a false wanted picture, and carrying out gray level processing and scale transformation on the false wanted picture;
and after the picture cutting is carried out on the false wanted picture after the gray level processing and the scale conversion, a certificate photographic picture, an identity card number picture and a name picture which are formed after the picture cutting are obtained.
Optionally, the obtaining of the initial model corresponding to each pre-constructed part of the picture, and performing training verification on the corresponding initial model according to each part of the picture to generate the corresponding recognition model includes:
acquiring a pre-constructed certificate photo initial model, and training and verifying the certificate photo initial model according to the certificate photo to generate a certificate photo identification model;
acquiring a pre-constructed identification number initial model, and training and verifying the identification number initial model according to an identification number picture to generate an identification model of the identification number;
and acquiring a pre-constructed name picture initial model, and training and verifying the name picture initial model according to the name picture to generate a name picture identification model.
Optionally, the acquiring the wanted picture to be detected, preprocessing the wanted picture, and cutting the preprocessed wanted picture to be detected into a plurality of partial pictures to be detected includes:
acquiring wanted pictures to be detected, and carrying out gray processing and scale transformation on the wanted pictures to be detected;
and after carrying out picture cutting on the wanted picture to be detected after gray processing and scale conversion, acquiring the certificate photographic picture to be detected, the ID card number picture and the name picture which are formed after cutting.
Optionally, the inputting each part of the picture to be detected into the corresponding recognition model to obtain the recognition result includes:
inputting the certificate photo to be detected into a certificate photo identification model, and acquiring a certificate photo identification result;
inputting an identification card number picture to be detected into an identification card number picture input identification model to obtain an identification card number identification result;
and inputting the name picture to be detected into a name picture identification model to obtain a name picture identification result.
Optionally, if one or more identification models identify that the picture is a false picture in the identification result, the wanted picture to be detected is a false wanted picture, and an early warning signal is sent, including:
if any one or more of three conditions that the certificate photo identification model identifies that the certificate photo is a false certificate photo, the identity card number identification model identifies that the identity card number picture is a false identity card number picture and the name picture identification model identifies that the name picture is a false name picture appear in the identification result, the wanted picture to be detected is a false wanted picture and an early warning signal is sent out.
Optionally, the performing gray processing and scale transformation on the false wanted picture includes:
after carrying out gray level processing on the false wanted picture, acquiring a gray level picture corresponding to the false wanted picture;
and after the gray level picture is subjected to scale conversion processing, false wanted pictures with uniform sizes are generated.
Yet another embodiment of the present invention further provides a false wanted early warning device, comprising at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the above-described false wanted pre-warning method.
Yet another embodiment of the present invention provides a non-transitory computer-readable storage medium storing computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform the above-described method of false wanted pre-warning.
Another embodiment of the invention provides a computer program product comprising a computer program stored on a non-volatile computer readable storage medium, the computer program comprising program instructions which, when executed by a processor, cause the processor to perform the above-mentioned false wanted pre-warning method.
Has the advantages that: compared with the prior art, the false wanted instruction early warning method and device can identify false wanted instructions which flow on the network, improve the strike strength of wanted instruction fraud, reduce the property loss of people and improve the property safety of people.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a flow chart of a preferred embodiment of a false wanted warning method according to the present invention;
fig. 2 is a schematic diagram of a hardware structure of a preferred embodiment of the false wanted warning device of the present invention.
Detailed Description
In order to make the objects, technical solutions and effects of the present invention clearer and clearer, the present invention is described in further detail below. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. Embodiments of the present invention will be described below with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a flowchart illustrating a false wanted warning method according to a preferred embodiment of the present invention. As shown in fig. 1, it includes the steps of:
s100, obtaining a sample of a false wanted picture, preprocessing the false wanted picture, and cutting the preprocessed false wanted picture into a plurality of partial pictures;
s200, acquiring an initial model corresponding to each part of picture which is constructed in advance, and training and verifying the corresponding initial model according to each part of picture to generate a corresponding recognition model;
step S300, acquiring wanted pictures to be detected, preprocessing the wanted pictures, and cutting the preprocessed wanted pictures to be detected into a plurality of partial pictures to be detected;
s400, inputting each part of picture to be detected into a corresponding recognition model to obtain a recognition result;
and S500, if one or more identification models identify the pictures as false pictures in the identification result, the wanted pictures to be detected are false wanted pictures, and an early warning signal is sent out.
In specific implementation, the embodiment of the invention collects a large number of existing false wanted picture samples, and the number of the false wanted picture samples is not less than 1000 in order to ensure the accuracy of the model.
Acquiring false wanted pictures as training data, and preprocessing the data; the data preprocessing comprises but is not limited to gray processing, scale conversion and picture cutting, and the false wanted photo is cut into a plurality of partial photos through the picture cutting, for example, the partial photos can be divided into a certified photo picture, an identity card number and a name picture; and storing the cut photos in local.
And acquiring an initial model corresponding to each pre-constructed part of the picture, wherein the initial model can adopt a convolutional neural network, and the convolutional neural network includes but is not limited to vgnetand resnet. And training and verifying the initial model according to a large number of partial picture samples formed by dividing the false wanted order to generate a corresponding recognition model. VGGNet (visual GeometryGroup Net) is a deep convolution network jointly developed by computer vision group of Oxford university and deep Mind company, a second name of a classified item and a first name of a positioning item are obtained on ILSVRC competition in 2014, VggNet has six different network structures, but each structure comprises 5 groups of convolutions, each group of convolutions uses a convolution kernel of 3x3, each group of convolutions is subjected to 2x2 maximum pooling, and three full connection layers are arranged. The ResNet (residual Neural network) is proposed by four people such as Kaiming He of Microsoft research institute, 152 layers of Neural networks are successfully trained by using the ResNet Unit, and champions are obtained in the ILSVRC2015 game, the error rate on top5 is 3.57%, the number of parameters is lower than that of VGGNet, and the effect is very prominent. The structure of ResNet can accelerate the training of the neural network very fast, and the accuracy of the model is greatly improved. Meanwhile, the popularization of ResNet is very good, and even the ResNet can be directly used in an IncepotionNet network.
The main idea of ResNet is to add a direct connection channel, i.e. the idea of Highway Network, in the Network. Previous Network architectures have performed a non-linear transformation of the performance input, while the Highway Network allows a certain proportion of the output of the previous Network layer to be preserved. The idea of ResNet is also very similar to that of Highway Network, allowing the original input information to pass directly to the following layers.
And carrying out data preprocessing on wanted pictures to be detected and wanted pictures, wherein the data preprocessing comprises but is not limited to gray processing, scale conversion and picture cutting, and after the pictures are cut, cutting the wanted pictures to be detected into a plurality of partial pictures, such as certificate pictures, identity card numbers and name pictures.
And acquiring the output result of each sub-model, and when the output result of at least one sub-model is a false wanted command, determining that the wanted command to be identified is the false wanted command, and sending out an early warning signal to prevent a user from being cheated.
In a further embodiment, obtaining a sample of a false wanted picture, preprocessing the false wanted picture, and dividing the preprocessed false wanted picture into a plurality of partial pictures, including:
acquiring a sample of a false wanted picture, and carrying out gray level processing and scale transformation on the false wanted picture;
and after the picture cutting is carried out on the false wanted picture after the gray level processing and the scale conversion, a certificate photographic picture, an identity card number picture and a name picture which are formed after the picture cutting are obtained.
In specific implementation, the gray processing and the scale transformation of the picture belong to a data preprocessing stage, the picture has three primary colors and brightness signals, the gray processing is to take only the gray signals, namely the brightness signals, and discard the color signals, the scale transformation mainly refers to the consistent (w, h) sizes of all pictures, and the specific implementation can use an image processing library in opencv, so that the dimensionality of the picture data before the model training is input is consistent and is the requirement of the model.
The image segmentation belongs to the object detection, and needs to be modeled separately, and the rcnn or sdd algorithm is used for extracting the boundary of the object region, and the boundary is present, so that the image of the object region also exists. The boundaries of the target region are identified according to the rcnn or sdd algorithm and a picture cut is made. The full name of R-CNN is Region-CNN, which is the first algorithm to successfully apply deep learning to target detection. The R-CNN realizes a target detection technology based on algorithms such as a Convolutional Neural Network (CNN), linear regression, a Support Vector Machine (SVM) and the like. The sdd algorithm is a target detection algorithm based on deep learning, and adopts a convolution kernel to predict category scores and offsets of a series of defaultoutgoing boxes on a feature map, and predicts on feature maps with different scales in order to improve detection accuracy.
Further, acquiring an initial model corresponding to each part of the picture which is constructed in advance, training and verifying the corresponding initial model according to each part of the picture, and generating a corresponding recognition model, wherein the method comprises the following steps:
acquiring a pre-constructed certificate photo initial model, and training and verifying the certificate photo initial model according to the certificate photo to generate a certificate photo identification model;
acquiring a pre-constructed identification number initial model, and training and verifying the identification number initial model according to an identification number picture to generate an identification model of the identification number;
and acquiring a pre-constructed name picture initial model, and training and verifying the name picture initial model according to the name picture to generate a name picture identification model.
In the specific implementation, the certificate photo initial model, the identity card number initial model and the name picture initial model are different models which are independent models. In the constructed initial model, the training process of the model is simply: initializing network parameters; performing a forward operation according to input picture data through a network, and subtracting a result of the data from a true value label; according to the difference of the results, feeding back from back to front step by step, wherein the algorithm is a bp algorithm, so that the network parameters are updated; through continuous iteration, given the condition that the model training stops, such as setting the number of loop iteration, error smaller than a certain threshold value and the like; and when a certain condition is reached, the model training is finished, and the model is saved.
The training and verification process of the model specifically comprises the following steps: the verification of the model generally adopts n-fold cross verification, namely, the whole sample data set is divided into n parts, wherein n-1 parts are used for training, one part is used for verification, the n times of results are averaged after n times of training of different long-mouth hard scaled fishes, and the test set is one of the n parts as the result of the model.
Further, carrying out gray level processing and scale transformation on the false wanted picture, comprising the following steps:
after carrying out gray level processing on the false wanted picture, acquiring a gray level picture corresponding to the false wanted picture;
and after the gray level picture is subjected to scale conversion processing, false wanted pictures with uniform sizes are generated.
In specific implementation, the gray processing is to only take a gray signal, that is, a luminance signal, and discard a color signal, the scaling mainly means that the sizes of all pictures are the same (w, h), and the specific implementation can use an image processing library in opencv, so that the dimensionality of picture data before the input model training is the same, which is a requirement of the model.
Further, acquiring wanted pictures to be detected, preprocessing the wanted pictures, and cutting the preprocessed wanted pictures to be detected into a plurality of partial pictures to be detected, wherein the steps of the method comprise:
acquiring wanted pictures to be detected, and carrying out gray processing and scale transformation on the wanted pictures to be detected;
and after carrying out picture cutting on the wanted picture to be detected after gray processing and scale conversion, acquiring the certificate photographic picture to be detected, the ID card number picture and the name picture which are formed after cutting.
In specific implementation, the gray processing and scale transformation of the picture belong to a data preprocessing stage, a wanted picture to be detected is obtained, the gray processing and scale transformation are carried out on the wanted picture to be detected, specifically, the gray processing is carried out on the wanted picture to be detected, wherein the gray processing is to only take gray signals, namely brightness signals, and discard color signals; the scale transformation mainly means that all pictures are consistent in size (w, h), and an image processing library in opencv can be used, so that the dimensionality of the picture to be detected is consistent with the dimensionality of picture data before the input model is trained, and the accuracy of model identification is improved. .
Further, inputting each part of the picture to be detected into the corresponding recognition model, and acquiring a recognition result, including:
inputting the certificate photo to be detected into a certificate photo identification model, and acquiring a certificate photo identification result;
inputting an identification card number picture to be detected into an identification card number picture input identification model to obtain an identification card number identification result;
and inputting the name picture to be detected into a name picture identification model to obtain a name picture identification result.
When the method is implemented specifically, a new wanted picture is put into the network: outputting a target picture through picture segmentation, wherein the target picture is a certificate picture to be detected, an identity card number picture and a name picture, such as a certificate picture; and sending the identification photo picture, the identification number picture and the name picture to be detected into respective corresponding models for identification to obtain corresponding output.
Further, if one or more identification models identify that the picture is a false picture in the identification result, the wanted picture to be detected is a false wanted picture, and an early warning signal is sent out, wherein the early warning signal comprises:
if any one or more of three conditions that the certificate photo identification model identifies that the certificate photo is a false certificate photo, the identity card number identification model identifies that the identity card number picture is a false identity card number picture and the name picture identification model identifies that the name picture is a false name picture appear in the identification result, the wanted picture to be detected is a false wanted picture and an early warning signal is sent out.
In specific implementation, if the result output by any model is detected to be a false wanted picture, the wanted picture to be detected is a false wanted picture, and an early warning signal is sent to prompt a user that the current wanted picture is the false wanted picture, so that the user is prevented from being cheated.
Another embodiment of the present invention provides a false wanted early warning device, as shown in fig. 2, the device 10 includes:
one or more processors 110 and a memory 120, where one processor 110 is illustrated in fig. 2, the processor 110 and the memory 120 may be connected by a bus or other means, and the connection by the bus is illustrated in fig. 2.
Processor 110 is used to implement various control logic for apparatus 10, which may be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a single chip microcomputer, an ARM (Acorn RISCMache) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination of these components. Also, the processor 110 may be any conventional processor, microprocessor, or state machine. Processor 110 may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.
The memory 120 is a non-volatile computer readable storage medium and may be used to store non-volatile software programs, non-volatile computer executable programs, and modules, such as program instructions corresponding to the false wanted warning method in the embodiment of the present invention. The processor 110 executes various functional applications and data processing of the apparatus 10, i.e. implements the false wanted pre-warning method in the above-described method embodiments, by running non-volatile software programs, instructions and units stored in the memory 120.
The memory 120 may include a storage program area and a storage data area, wherein the storage program area may store an application program required for operating the device, at least one function; the storage data area may store data created according to the use of the device 10, and the like. Further, the memory 120 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 120 optionally includes memory located remotely from processor 110, which may be connected to device 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
One or more units are stored in the memory 120, which when executed by the one or more processors 110, perform the false wanted pre-warning method in any of the above-described method embodiments, e.g. performing the above-described method steps S100 to S500 in fig. 1.
Embodiments of the present invention provide a non-transitory computer-readable storage medium storing computer-executable instructions for execution by one or more processors, for example, to perform method steps S100-S500 of fig. 1 described above.
By way of example, non-volatile storage media can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), electrically erasable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM), which acts as external cache memory. By way of illustration and not limitation, RAM is available in many forms such as Synchronous RAM (SRAM), dynamic RAM, (DRAM), Synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The disclosed memory components or memory of the operating environment described herein are intended to comprise one or more of these and/or any other suitable types of memory.
Another embodiment of the invention provides a computer program product comprising a computer program stored on a non-volatile computer readable storage medium, the computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method of false wanted pre-warning of the above method embodiment. For example, the method steps S100 to S500 in fig. 1 described above are performed.
The above-described embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the embodiment.
Through the above description of the embodiments, those skilled in the art will clearly understand that the embodiments may be implemented by software plus a general hardware platform, and may also be implemented by hardware. With this in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer electronic device (which may be a personal computer, a server, or a network electronic device, etc.) to execute the methods of the various embodiments or some parts of the embodiments.
Conditional language such as "can," "might," or "may" is generally intended to convey that a particular embodiment can include (yet other embodiments do not include) particular features, elements, and/or operations, among others, unless specifically stated otherwise or otherwise understood within the context as used. Thus, such conditional language is not generally intended to imply that features, elements, and/or operations are in any way required for one or more embodiments or that one or more embodiments necessarily include logic for deciding, with or without student input or prompting, whether such features, elements, and/or operations are included or are to be performed in any particular embodiment.
What has been described herein in the specification and drawings includes examples of methods and apparatus capable of providing false wanted warnings. It will, of course, not be possible to describe every conceivable combination of components and/or methodologies for purposes of describing the various features of the disclosure, but it can be appreciated that many further combinations and permutations of the disclosed features are possible. It is therefore evident that various modifications can be made to the disclosure without departing from the scope or spirit thereof. In addition, or in the alternative, other embodiments of the disclosure may be apparent from consideration of the specification and drawings and from practice of the disclosure as presented herein. It is intended that the examples set forth in this specification and the drawings be considered in all respects as illustrative and not restrictive. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.
Claims (10)
1. A false wanted early warning method is characterized by comprising the following steps:
acquiring a sample of a false wanted picture, preprocessing the false wanted picture, and cutting the preprocessed false wanted picture into a plurality of partial pictures;
acquiring an initial model corresponding to each part of picture which is constructed in advance, and training and verifying the corresponding initial model according to each part of picture to generate a corresponding recognition model;
acquiring wanted pictures to be detected, preprocessing the wanted pictures, and cutting the preprocessed wanted pictures to be detected into a plurality of parts of pictures to be detected;
inputting each part of picture to be detected into a corresponding recognition model to obtain a recognition result;
and if one or more identification models identify the pictures as false pictures in the identification result, the wanted pictures to be detected are false wanted pictures, and an early warning signal is sent out.
2. The false wanted early warning method according to claim 1, wherein the obtaining of the sample of the false wanted picture, the preprocessing of the false wanted picture, and the dividing of the preprocessed false wanted picture into several parts of pictures comprise:
acquiring a sample of a false wanted picture, and carrying out gray level processing and scale transformation on the false wanted picture;
and after the picture cutting is carried out on the false wanted picture after the gray level processing and the scale conversion, a certificate photographic picture, an identity card number picture and a name picture which are formed after the picture cutting are obtained.
3. The false wanted early warning method according to claim 2, wherein the obtaining of the corresponding initial model of each part of the picture is constructed in advance, and the training and verification of the corresponding initial model according to each part of the picture are performed to generate the corresponding recognition model, and the method comprises:
acquiring a pre-constructed certificate photo initial model, and training and verifying the certificate photo initial model according to the certificate photo to generate a certificate photo identification model;
acquiring a pre-constructed identification number initial model, and training and verifying the identification number initial model according to an identification number picture to generate an identification model of the identification number;
and acquiring a pre-constructed name picture initial model, and training and verifying the name picture initial model according to the name picture to generate a name picture identification model.
4. The false wanted warning method according to claim 3, wherein the obtaining of wanted pictures to be detected, the preprocessing of the wanted pictures, and the cutting of the preprocessed wanted pictures to be detected into parts of pictures to be detected comprises:
acquiring wanted pictures to be detected, and carrying out gray processing and scale transformation on the wanted pictures to be detected;
and after carrying out picture cutting on the wanted picture to be detected after gray processing and scale conversion, acquiring the certificate photographic picture to be detected, the ID card number picture and the name picture which are formed after cutting.
5. The false wanted early warning method according to claim 4, wherein the step of inputting each part of the picture to be detected into a corresponding recognition model to obtain a recognition result comprises:
inputting the certificate photo to be detected into a certificate photo identification model, and acquiring a certificate photo identification result;
inputting an identification card number picture to be detected into an identification card number picture input identification model to obtain an identification card number identification result;
and inputting the name picture to be detected into a name picture identification model to obtain a name picture identification result.
6. The false wanted early warning method according to claim 5, wherein if one or more identification models in the identification result identify that the picture is a false picture, the wanted picture to be detected is a false wanted picture, and an early warning signal is sent out, comprising:
if any one or more of three conditions that the certificate photo identification model identifies that the certificate photo is a false certificate photo, the identity card number identification model identifies that the identity card number picture is a false identity card number picture and the name picture identification model identifies that the name picture is a false name picture appear in the identification result, the wanted picture to be detected is a false wanted picture and an early warning signal is sent out.
7. A false wanted pre-warning method according to claim 2, wherein the grey scale processing and scale transformation of the false wanted pictures comprises:
after carrying out gray level processing on the false wanted picture, acquiring a gray level picture corresponding to the false wanted picture;
and after the gray level picture is subjected to scale conversion processing, false wanted pictures with uniform sizes are generated.
8. A false wanted pre-warning device, characterized in that the device comprises at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of false wanted warning according to any one of claims 1-7.
9. A non-transitory computer-readable storage medium storing computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform the method of false wanted pre-warning according to any one of claims 1-7.
10. A computer program product, characterized in that the computer program product comprises a computer program stored on a non-volatile computer readable storage medium, the computer program comprising program instructions that, when executed by a processor, cause the processor to perform the method of false wanted pre-warning according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910522072.5A CN110245616B (en) | 2019-06-17 | 2019-06-17 | False wanted order early warning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910522072.5A CN110245616B (en) | 2019-06-17 | 2019-06-17 | False wanted order early warning method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110245616A true CN110245616A (en) | 2019-09-17 |
| CN110245616B CN110245616B (en) | 2023-04-18 |
Family
ID=67887642
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910522072.5A Active CN110245616B (en) | 2019-06-17 | 2019-06-17 | False wanted order early warning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110245616B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101662581A (en) * | 2009-09-09 | 2010-03-03 | 谭洪舟 | Multifunctional certificate information collection system |
| CN105528602A (en) * | 2015-10-30 | 2016-04-27 | 小米科技有限责任公司 | Region identification method and device |
| CN107122987A (en) * | 2017-06-20 | 2017-09-01 | 深圳安巽科技有限公司 | A kind of early warning system and method for order for arrest swindle |
| CN108259680A (en) * | 2016-12-28 | 2018-07-06 | 广东世纪网通信设备股份有限公司 | Fraudulent call recognition methods, device and the server for identifying fraudulent call |
| CN109446900A (en) * | 2018-09-21 | 2019-03-08 | 平安科技（深圳）有限公司 | Certificate authenticity verification method, apparatus, computer equipment and storage medium |
| CN109543551A (en) * | 2018-10-26 | 2019-03-29 | 平安科技（深圳）有限公司 | Identity card identifies processing method, device, computer equipment and storage medium |
| US20190180086A1 (en) * | 2017-06-30 | 2019-06-13 | Beijing Didi Infinity Technology And Development Co. Ltd. | Systems and methods for verifying authenticity of id photo |
-
2019
- 2019-06-17 CN CN201910522072.5A patent/CN110245616B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101662581A (en) * | 2009-09-09 | 2010-03-03 | 谭洪舟 | Multifunctional certificate information collection system |
| CN105528602A (en) * | 2015-10-30 | 2016-04-27 | 小米科技有限责任公司 | Region identification method and device |
| CN108259680A (en) * | 2016-12-28 | 2018-07-06 | 广东世纪网通信设备股份有限公司 | Fraudulent call recognition methods, device and the server for identifying fraudulent call |
| CN107122987A (en) * | 2017-06-20 | 2017-09-01 | 深圳安巽科技有限公司 | A kind of early warning system and method for order for arrest swindle |
| US20190180086A1 (en) * | 2017-06-30 | 2019-06-13 | Beijing Didi Infinity Technology And Development Co. Ltd. | Systems and methods for verifying authenticity of id photo |
| CN109446900A (en) * | 2018-09-21 | 2019-03-08 | 平安科技（深圳）有限公司 | Certificate authenticity verification method, apparatus, computer equipment and storage medium |
| CN109543551A (en) * | 2018-10-26 | 2019-03-29 | 平安科技（深圳）有限公司 | Identity card identifies processing method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110245616B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11176393B2 (en) | Living body recognition method, storage medium, and computer device | |
| US11195037B2 (en) | Living body detection method and system, computer-readable storage medium | |
| CN111080628A (en) | Image tampering detection method and device, computer equipment and storage medium | |
| CN109800682B (en) | Driver attribute identification method and related product | |
| CN113469088B (en) | SAR image ship target detection method and system under passive interference scene | |
| CN108805016B (en) | Head and shoulder area detection method and device | |
| CN111242852A (en) | Boundary aware object removal and content filling | |
| CN108427927A (en) | Target recognition methods and device, electronic equipment, program and storage medium again | |
| CN111027628B (en) | Model determination method and system | |
| CN112651333B (en) | Silence living body detection method, silence living body detection device, terminal equipment and storage medium | |
| CN111639667B (en) | Image recognition method, device, electronic equipment and computer readable storage medium | |
| CN111144398A (en) | Target detection method, target detection device, computer equipment and storage medium | |
| CN108875509A (en) | Biopsy method, device and system and storage medium | |
| WO2021042544A1 (en) | Facial verification method and apparatus based on mesh removal model, and computer device and storage medium | |
| CN109165654B (en) | Training method of target positioning model and target positioning method and device | |
| CN112052746A (en) | Target detection method and device, electronic equipment and readable storage medium | |
| CN109522970A (en) | Image classification method, apparatus and system | |
| WO2022134354A1 (en) | Vehicle loss detection model training method and apparatus, vehicle loss detection method and apparatus, and device and medium | |
| CN115082752A (en) | Target detection model training method, device, equipment and medium based on weak supervision | |
| CN113283388B (en) | Training method, device, equipment and storage medium of living body face detection model | |
| CN110490058A (en) | Training method, device, system and the computer-readable medium of pedestrian detection model | |
| CN111046755A (en) | Character recognition method, character recognition device, computer equipment and computer-readable storage medium | |
| CN117315678B (en) | Digital image tampering identification method, system, equipment and storage medium | |
| CN114092947A (en) | Text detection method and device, electronic equipment and readable storage medium | |
| CN111507135A (en) | Face detection method and device, computer equipment and storage medium |
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 |