CN113742421B - Network identity authentication method based on distributed storage and image processing - Google Patents
Network identity authentication method based on distributed storage and image processing Download PDFInfo
- Publication number
- CN113742421B CN113742421B CN202110958553.8A CN202110958553A CN113742421B CN 113742421 B CN113742421 B CN 113742421B CN 202110958553 A CN202110958553 A CN 202110958553A CN 113742421 B CN113742421 B CN 113742421B
- Authority
- CN
- China
- Prior art keywords
- image
- information
- circumference
- matching
- memories
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a network identity authentication method based on distributed storage and image processing, which comprises the following steps: extracting a plurality of round images from the original image, and taking the original image from which the round images are removed as a template image; extracting image related information of an original image; obtaining the information duty ratio of each memory and complementarily pairing the information duty ratios; storing the image related information in different memories respectively, and enabling paired memories to mutually backup the image related information of the other party; when an image to be identified is acquired, carrying out position matching on the first image information and the second image information, and after matching is completed, carrying out rotary matching on each piece of first circumference information and each piece of second circumference information until the first circumference information and the second circumference information are completely matched, so as to obtain a standard original image with the matched completion; and carrying out identity verification on the image to be identified and all standard original images, and judging the identity information of the image to be identified. The embodiment of the invention can improve the storage safety of the original image in the authentication process.
Description
Technical Field
The invention relates to the technical field of distributed storage and image processing, in particular to a network identity authentication method based on distributed storage and image processing.
Background
Identity authentication is an essential link in the current aspects of the aspects of network penetration life. There are many methods of identity authentication, which can be basically divided into: identity authentication based on a shared key, identity authentication based on biological characteristics, and identity authentication based on a public key encryption algorithm. One image can correspond to one identity information, and the images are consistent, namely the representative identities are consistent.
For security, a plurality of communities or companies currently perform identity authentication by using face information to manage personnel access, a card punching system collects the face information to generate images, and the images are compared with face images reserved by the personnel in the system to determine the identity information of the personnel, so that the identity authentication of the personnel is completed. Meanwhile, the reserved face image and the face image collected each time are stored in a card punching system and used for storing the in-out information of each person.
The common card punching system directly stores the acquired face images, and cannot meet the level requirements on the safety and privacy of face information.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a network identity authentication method based on distributed storage and image processing, and the adopted technical scheme is as follows:
one embodiment of the invention provides a network identity authentication method based on distributed storage and image processing, which comprises the following steps:
extracting a plurality of round images with equal size from an acquired original image, and taking the original image from which the round images are removed as a template image;
extracting image related information of the original image; the image related information comprises first image information and corresponding first circumference information of the circle image, and second image information and corresponding second circumference information of each round hole of the template image;
obtaining the information duty ratio of each memory according to the performance of the memory, and complementarily pairing the memories; storing the image related information in different memories according to the information proportion, and enabling paired memories to mutually backup the image related information of the other party;
when an image to be identified is acquired, reading the image related information, performing position matching on the first image information and the second image information, and performing rotary matching on each piece of first circumference information and the second circumference information after matching is completed until complete matching is achieved, so as to obtain a standard original image after matching is completed;
and carrying out identity verification on the image to be identified and all the standard original images, and judging the identity information of the image to be identified.
Preferably, the method for extracting the circular image comprises the following steps:
and generating a plurality of non-overlapping circles with the total area accounting for the original image and the proportion of the non-overlapping circles being larger than a preset threshold value by taking any position in the original image as a circle center and taking any length in a preset range as a radius, and dividing and extracting the connected domains corresponding to each circle to obtain a plurality of circle images.
Preferably, the step of acquiring the image-related information includes:
performing lossless compression on the circle image and the template image to obtain compressed first image information and second image information;
and respectively acquiring the first circumference information and the second circumference information according to the pixel values on the circumferences of the circle image and the template image.
Preferably, the method for acquiring the first circumference information and the second circumference information includes:
and sequentially recording the pixel values on the circumference in a clockwise direction or a counterclockwise direction by taking any pixel point on the circumference corresponding to the circle image and the template image as a starting point to obtain the first circumference information and the second circumference information.
Preferably, the method for acquiring the information duty ratio comprises the following steps:
taking the probability that the storage and the reading of the storage are not damaged in the using process as the performance index of the storage; taking the duty ratio of the performance index in the sum of all the memory performance indexes as the information duty ratio of each memory.
Preferably, the complementary pairing method is as follows:
sorting the memories according to the size of the performance index, and when the number of the memories is even, sequentially pairing the sorted memories end to end;
when the number of the memories is odd, the two memories with the minimum performance index are shared and matched with the memory with the maximum performance index, and the rest memories are paired in sequence from head to tail.
Preferably, the step of matching the positions includes:
forming a first information sequence of the circular image by the first image information, the first circumference information, the serial numbers of the original images corresponding to the circular image and the serial numbers of the circular image;
forming a second information sequence of the template image by the second image information, the second circumference information, the number corresponding to the second circumference information and the number of the original image corresponding to the template image;
and matching the first information sequence with the second information sequence to complete the position matching of each circle image and the corresponding template image.
Preferably, the rotation matching method comprises the following steps:
embedding the round image into a round hole which is correspondingly matched with the template image, taking the circumference of the round image as an inner ring, taking the round hole as an outer ring, obtaining a rotation angle according to the number of pixel points of the inner ring, rotating the round image by the rotation angle each time, and judging whether the round image is matched with the round hole.
Preferably, the step of completely matching includes:
taking the pixel points on the inner ring and the pixel points on the outer ring with the pixel values identical to each other as identical pixel points;
calculating the distribution concentration degree of the consistent pixel points under each rotation angle;
and selecting the optimal rotation angle with the greatest distribution concentration degree, so that the round image rotates by the optimal rotation angle to achieve complete matching.
The embodiment of the invention has at least the following beneficial effects:
1. the original image is divided into a circle image and a template image, the circle image and the template image are stored in a distributed mode, when the image to be identified is acquired, the circle image and the template image are matched to obtain a standard original image, and the standard original image is compared with the image to be identified to obtain identity information of the image to be identified. According to the embodiment of the invention, the matching restoration of the original image can be completed on the basis of the segmentation of the original image, the storage of the complete original image is converted into the distributed storage of the corresponding segmented image, and the security level of the image storage is improved.
2. And the image related information is stored in a distributed mode based on the importance degree of the image data and the performance of the memory, so that the reliability and fault tolerance of the data are improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of steps of a network identity authentication method based on distributed storage and image processing according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following description refers to the specific implementation, structure, characteristics and effects of a visual measurement method for structural member production information according to the invention by combining the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of a network identity authentication method based on distributed storage and image processing.
Referring to fig. 1, a flowchart of a network identity authentication method based on distributed storage and image processing according to an embodiment of the present invention is shown, where the method includes the following steps:
and S001, extracting a plurality of round images with equal size from the acquired original images, and taking the original images from which the round images are removed as template images.
Specifically, with any position in an original image as a circle center and any length in a preset range as a radius, a plurality of non-overlapping circles with the total area accounting for the original image more than a preset threshold value are generated, and connected domains corresponding to each circle are segmented and extracted to obtain a plurality of circle images.
As an example, the preset range in the embodiment of the invention is thatWherein p represents the long side size of the original image, and q represents the short side size of the original image; the preset threshold is 3/4.
In the original image, k circles meeting the requirements are generated, and the connected domain corresponding to each circle is segmented and extracted from the original image, so that k circle images are obtained. And setting IDs for each circle image according to the sequence of the circle centers from top to bottom and from left to right, wherein the IDs represent the corresponding positions of each circle image in the template image.
In the original image, setting the pixel values of k connected domains corresponding to the circle image to 0, namely removing the image information corresponding to the circle image from the original image, and obtaining a template image containing a plurality of round holes.
Step S002, extracting the image related information of the original image; the image-related information includes first image information of a circle image and corresponding first circumference information, and second image information of a template image and corresponding second circumference information of each circular hole.
The method comprises the following specific steps of:
1. and carrying out lossless compression on the circle image and the template image to obtain compressed first image information and second image information.
As an example, the embodiment of the present invention adopts a JPEG lossless compression method to obtain the first image information x of the compressed round image and the second image information m of the template image.
2. And respectively acquiring first circumference information and second circumference information according to pixel values on circumferences of the circle image and the template image.
The method comprises the following specific steps of:
2.1 graying the circle image and the template image.
The color space of each pixel point in the image is RGB three channels, and the comparison between the pixel point values is not easy to carry out. Therefore, it is necessary to gray the circle image and the template image, and contrast matching is performed based on the gray value of each pixel.
And 2.2, sequentially recording pixel values on the circumference by taking any pixel point on the circumference corresponding to the circle image and the template image as a starting point and clockwise or anticlockwise to obtain first circumference information and second circumference information.
Because the circumference of the circular image and the circumference of the round hole of the template are two concentric and adjacent circles, a circular ring with the width of two pixel points is formed, the circumference of the circular image is used as an inner ring, and the circumference of the corresponding round hole in the template image is used as an outer ring.
And randomly selecting clockwise or anticlockwise by taking any pixel point of the inner ring and the outer ring as a starting point, and sequentially recording gray values of the pixel points on the circumference to respectively obtain first circumference information y of the inner ring circumference and second circumference information n of the round hole.
The starting point and the direction are randomly selected, and the round image and the template image can be encrypted.
The information length of the first circumference information y and the second circumference information n and the length difference between the two types of information are related to the radius of the circle.
Step S003, the information duty ratio of each memory is obtained according to the performance of the memory, and the information duty ratios are complementarily matched; storing the image related information in different memories according to the information duty ratio, and enabling the paired memories to mutually backup the image related information of the other party.
The method comprises the following specific steps of:
1. taking the probability that the storage and the read data of the storage are not damaged in the using process as the performance index of the storage; the information duty ratio of each memory is taken as the duty ratio of the performance index in the sum of all the memory performance indexes.
And calculating the probability that the storage and the read data are not damaged in the normal use process of the storage as a performance index a of the storage, and representing the quality of the storage.
The performance and the storage information are in positive correlation, the memory with better performance is provided with more storage information, the memory with poorer performance is provided with less storage information. The stored information duty cycle b of each memory is the ratio of the performance index a of each memory to the sum of all memory performance indexes.
2. The image-related information is stored in different memories according to the information duty ratio, respectively.
And forming a first information sequence of the circular image by the first image information, the first circumference information, the serial numbers of the original images corresponding to the circular image and the serial numbers of the circular image.
For k Zhang Yuantu images, the information of each image includes the number M of the original image, the image ID, the first image information x and the first circumference information y, so as to obtain a first information sequence (M, ID, x, y), and k Zhang Yuantu corresponds to k first information sequences.
And forming a second information sequence of the template image by the second image information, the second circumference information, the number corresponding to the second circumference information and the number of the original image corresponding to the template image.
For the template image, one template image corresponds to k circular holes, so that the image related information thereof comprises the number M of the original image, the second image information M and k second circumference information n, and a second information sequence (M, n1, …, nk) of the template image is obtained.
Thus, one original image includes k+1 information sequences.
The fault tolerance of the data is considered when the distributed storage is carried out, and k+1 information sequences are distributed to c memories according to the importance degree and the memory performance of the data.
The template image is the basis of image matching, the information sequence of which is most important in k+1 information sequences, and the template information can be read when part of memories are damaged, so that the template information sequences are stored in c memories. The rest information sequences are stored according to the information duty ratio of the memories, and the number si= [ b x k ] +1 stored in each memory, that is, the smallest integer greater than b x k, is s=s1+s2+ … +sc.
The c memories are ordered according to the performance, firstly, the 1 st to s1 st information sequences are stored in a first memory, then the s1 st to s1+s2 st information sequences are stored in a second memory, and so on until the kth information sequence is stored.
At this time, each information sequence is stored once, but k < s, so that the partial memory has not reached the storage amount.
Thus, starting again from the 1 st information sequence, the subsequent storage is performed so that the amount of stored information in each memory remains consistent with si.
3. And sorting the memories according to the size of the performance index, and when the number of the memories is even, sequentially pairing the sorted memories head and tail.
And (3) sequencing the c memories according to the performance, if c is an even number, pairing the c memory with the 1 st memory, pairing the c-1 st memory with the 2 nd memory, and the like, and sequentially pairing the memories from beginning to end to finish the pairing of the memories.
4. When the number of the memories is odd, the two memories with the minimum performance index are shared and matched with the memory with the maximum performance index, and the rest memories are paired in sequence from beginning to end.
If c is odd, the c-th and c-1-th memories are paired with the 1 st memory, and the rest memories are paired end to end in turn, namely the c-2-th memory is paired with the 2 nd memory, and the like, so that the pairing of the memories is completed.
Each information sequence is stored in a group of memories, so that the information can be backed up, and high fault tolerance is ensured; the memories are paired according to the performances of the memories, so that the relative balance of the performances of each group of memories is ensured, and the storage space can be utilized to the greatest extent while the high fault tolerance is ensured.
The lower the memory performance, the more needed is to store a backup in the good-performing memory, thus pairing the bad-performing and good-performing memories; and if the performance is medium, performing storage backup in the storage with the same medium performance, namely pairing the storage with each other.
For each group of memories, the storage information of the low-performance memories is backed up in the high-performance memories so as to ensure high fault tolerance of the data. The distributed storage of the image information is completed through storage allocation of the information sequences, group pairing of the memories and backup of the information sequences.
And step S004, when the image to be identified is acquired, reading image related information, performing position matching on the first image information and the second image information, and performing rotary matching on each piece of first circumference information and each piece of second circumference information after the matching is completed until the complete matching is achieved, so as to obtain a standard original image after the matching is completed.
The method comprises the following specific steps of:
1. and reading image related information, and matching the first information sequence with the second information sequence to complete the position matching of each circle image and the corresponding template image.
Firstly, matching a circle image and a template image belonging to the same original image according to the serial numbers of the original images, and further performing position matching according to the ID of the circle image and the template image.
2. And embedding the circular image into a circular hole which is correspondingly matched with the template image, taking the circumference of the circular image as an inner ring, taking the circular hole as an outer ring, obtaining a rotation angle according to the number of pixel points of the inner ring, rotating the circular image by the rotation angle each time, and judging whether the circular image is matched with the circular hole.
The method comprises the following specific steps of:
2.1 obtaining the rotation angle.
In order to make the angle of rotation fine enough, the circle image is rotated clockwise by one pixel, i.e. the rotation angle Δθ is related to the total number w of inner ring pixels, Δθ=360°/w.
When rotated clockwise t times, the clockwise rotation angle of the circular image is θ=t×Δθ.
And 2.2, taking the pixel points with the same pixel values as the pixel points on the inner ring and the pixel points on the outer ring as the same pixel points.
And finding out a consistent pixel point based on the gradient change of the inner ring pixel point, and extracting a pixel point with the gradient of 0 between the inner ring pixel point and the adjacent outer ring pixel point as the consistent pixel point.
2.3 calculating the distribution concentration degree of the consistent pixel points under each rotation angle.
And generating a group of continuous consistent pixel points, and obtaining a corresponding distribution sequence F= [ F1, F2, …, fe ] according to the continuous condition of the consistent pixel point distribution. Wherein e is the number of groups of consecutive uniform pixels, and f is the number of uniform pixels in each group.
When f is greater than a preset threshold, the consistent pixel points of the groups are distributed in a concentrated manner, and the more the number of groups distributed in a concentrated manner in the distribution sequence is, the higher the distribution concentration degree of the consistent pixel points in the distribution sequence is.
As an example, in the embodiment of the present invention, the preset threshold is 5.
Updating the distribution sequence by discarding groups smaller than a preset threshold value in the distribution sequence to obtain a distribution concentrated sequence G= [ G1, G2, …, gj ]]Wherein j is the number of groups satisfying F > 5 in the distribution sequence F, G is the number of corresponding consistent pixel points of each group, and the distribution concentration degree of the consistent pixel points of the distribution concentration sequence G
For the round image in the initial state, the rotation angle θ=0, and the uniform pixel distribution concentration degree W in the state can be obtained 0 Similarly, when the pixel is rotated clockwise t times, the uniform pixel distribution concentration degree in the state is W t 。
2.4, the circle image and the template image are completely matched.
And rotating the round image for one circle, calculating the distribution concentration degree under each rotation angle, and obtaining the optimal rotation angle corresponding to the maximum distribution concentration degree, so that the round image rotates by the optimal rotation angle to achieve complete matching.
After each circle image is completely matched with the template image, a standard original image is obtained.
And step S005, carrying out identity verification on the image to be identified and the standard original image, and judging the identity information of the image to be identified.
Comparing the image to be identified with all the obtained standard original images, and obtaining identity information corresponding to the standard original image with the maximum similarity of the image to be identified, namely the identity information of the image to be identified.
Preferably, the same division storage can be performed on each image to be identified, so as to obtain the access information of the corresponding person in a certain time period.
In summary, in the embodiment of the invention, a plurality of round images with equal size are extracted from the collected original images, and the original images from which the round images are removed are used as template images; extracting image related information of an original image; the image related information comprises first image information of a circle image and corresponding first circumference information, and second image information of a template image and corresponding second circumference information of each round hole; obtaining the information duty ratio of each memory according to the performance of the memory, and complementarily pairing the memories; storing the image related information in different memories according to the information proportion, and enabling the paired memories to mutually backup the image related information of the other party; when an image to be identified is acquired, reading image related information, performing position matching on the first image information and the second image information, and performing rotary matching on each piece of first circumference information and the second circumference information after the matching is completed until the complete matching is achieved, so as to obtain a standard original image after the matching is completed; and carrying out identity verification on the image to be identified and all standard original images, and judging the identity information of the image to be identified. The embodiment of the invention can improve the storage safety of the original image in the authentication process.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (5)
1. The network identity authentication method based on distributed storage and image processing is characterized by comprising the following steps of:
extracting a plurality of round images with equal size from an acquired original image, and taking the original image from which the round images are removed as a template image;
extracting image related information of the original image; the image related information comprises first image information and corresponding first circumference information of the circle image, and second image information and corresponding second circumference information of each round hole of the template image;
obtaining the information duty ratio of each memory according to the performance of the memory, and complementarily pairing the memories; storing the image related information in different memories according to the information proportion, and enabling paired memories to mutually backup the image related information of the other party;
when an image to be identified is acquired, reading the image related information, performing position matching on the first image information and the second image information, and performing rotary matching on each piece of first circumference information and the second circumference information after matching is completed until complete matching is achieved, so as to obtain a standard original image after matching is completed;
carrying out identity verification on the image to be identified and all the standard original images, and judging the identity information of the image to be identified;
the step of acquiring the image related information includes:
performing lossless compression on the circle image and the template image to obtain compressed first image information and second image information;
respectively acquiring the first circumference information and the second circumference information according to pixel values on circumferences of the circle image and the template image;
the method for acquiring the first circumference information and the second circumference information comprises the following steps:
sequentially recording pixel values on the circumference in a clockwise direction or a counterclockwise direction by taking any pixel point on the circumference corresponding to the circle image and the template image as a starting point to obtain the first circumference information and the second circumference information;
the step of matching the positions comprises the following steps:
forming a first information sequence of the circular image by the first image information, the first circumference information, the serial numbers of the original images corresponding to the circular image and the serial numbers of the circular image;
forming a second information sequence of the template image by the second image information, the second circumference information, the number corresponding to the second circumference information and the number of the original image corresponding to the template image;
matching the first information sequence with the second information sequence to finish the position matching of each circle image and the corresponding template image;
the rotation matching method comprises the following steps:
embedding the round image into a round hole which is correspondingly matched with the template image, taking the circumference of the round image as an inner ring, taking the round hole as an outer ring, obtaining a rotation angle according to the number of pixel points of the inner ring, rotating the round image by the rotation angle each time, and judging whether the round image is matched with the round hole.
2. The method according to claim 1, wherein the circle image extraction method is as follows:
and generating a plurality of non-overlapping circles with the total area accounting for the original image and the proportion of the non-overlapping circles being larger than a preset threshold value by taking any position in the original image as a circle center and taking any length in a preset range as a radius, and dividing and extracting the connected domains corresponding to each circle to obtain a plurality of circle images.
3. The method according to claim 1, wherein the information duty cycle obtaining method is as follows:
taking the probability that the storage and the reading of the storage are not damaged in the using process as the performance index of the storage; taking the duty ratio of the performance index in the sum of all the memory performance indexes as the information duty ratio of each memory.
4. A method according to claim 3, wherein the complementary pairing is performed by:
sorting the memories according to the size of the performance index, and when the number of the memories is even, sequentially pairing the sorted memories end to end;
when the number of the memories is odd, the two memories with the minimum performance index are shared and matched with the memory with the maximum performance index, and the rest memories are paired in sequence from head to tail.
5. The method of claim 1, wherein the step of completely matching comprises:
taking the pixel points on the inner ring and the pixel points on the outer ring with the pixel values identical to each other as identical pixel points;
calculating the distribution concentration degree of the consistent pixel points under each rotation angle;
and selecting the optimal rotation angle with the greatest distribution concentration degree, so that the round image rotates by the optimal rotation angle to achieve complete matching.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110958553.8A CN113742421B (en) | 2021-08-20 | 2021-08-20 | Network identity authentication method based on distributed storage and image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110958553.8A CN113742421B (en) | 2021-08-20 | 2021-08-20 | Network identity authentication method based on distributed storage and image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113742421A CN113742421A (en) | 2021-12-03 |
| CN113742421B true CN113742421B (en) | 2023-09-12 |
Family
ID=78731950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110958553.8A Active CN113742421B (en) | 2021-08-20 | 2021-08-20 | Network identity authentication method based on distributed storage and image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113742421B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08279021A (en) * | 1995-04-05 | 1996-10-22 | Ricoh Co Ltd | Method for detecting angle of rotation and recognizing image |
| CN105550671A (en) * | 2016-01-28 | 2016-05-04 | 北京麦芯科技有限公司 | Face recognition method and device |
| CN105740868A (en) * | 2016-01-26 | 2016-07-06 | 北京工商大学 | Circular operator based image edge extraction method and apparatus |
| WO2017047862A1 (en) * | 2015-09-18 | 2017-03-23 | 민운기 | Image key authentication method and system, which use color histogram and texture information of images |
| CN107103323A (en) * | 2017-03-09 | 2017-08-29 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | A kind of target identification method based on image outline feature |
| CN108090908A (en) * | 2017-12-07 | 2018-05-29 | 深圳云天励飞技术有限公司 | Image partition method, device, terminal and storage medium |
| CN109064178A (en) * | 2018-06-29 | 2018-12-21 | 北京金山安全软件有限公司 | Payment method, payment device, server and computer-readable storage medium |
| CN109711384A (en) * | 2019-01-09 | 2019-05-03 | 江苏星云网格信息技术有限公司 | A kind of face identification method based on depth convolutional neural networks |
| CN112200864A (en) * | 2019-07-08 | 2021-01-08 | 深圳中科飞测科技有限公司 | Image processing method, positioning method, device, equipment and storage medium |
-
2021
- 2021-08-20 CN CN202110958553.8A patent/CN113742421B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08279021A (en) * | 1995-04-05 | 1996-10-22 | Ricoh Co Ltd | Method for detecting angle of rotation and recognizing image |
| WO2017047862A1 (en) * | 2015-09-18 | 2017-03-23 | 민운기 | Image key authentication method and system, which use color histogram and texture information of images |
| CN105740868A (en) * | 2016-01-26 | 2016-07-06 | 北京工商大学 | Circular operator based image edge extraction method and apparatus |
| CN105550671A (en) * | 2016-01-28 | 2016-05-04 | 北京麦芯科技有限公司 | Face recognition method and device |
| CN107103323A (en) * | 2017-03-09 | 2017-08-29 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | A kind of target identification method based on image outline feature |
| CN108090908A (en) * | 2017-12-07 | 2018-05-29 | 深圳云天励飞技术有限公司 | Image partition method, device, terminal and storage medium |
| CN109064178A (en) * | 2018-06-29 | 2018-12-21 | 北京金山安全软件有限公司 | Payment method, payment device, server and computer-readable storage medium |
| CN109711384A (en) * | 2019-01-09 | 2019-05-03 | 江苏星云网格信息技术有限公司 | A kind of face identification method based on depth convolutional neural networks |
| CN112200864A (en) * | 2019-07-08 | 2021-01-08 | 深圳中科飞测科技有限公司 | Image processing method, positioning method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 一种新的高速圆形匹配算法;黄廉真;吴晓军;康文雄;;哈尔滨工业大学学报(07);92-96 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113742421A (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107332659B (en) | Identity authentication method, storage medium and system based on biological characteristics | |
| WO2017215540A1 (en) | Offline identity authentication method and apparatus | |
| CN108596126B (en) | Finger vein image identification method based on improved LGS weighted coding | |
| CN105553657B (en) | A kind of fingerprint fuzzy vault implementation method of feature-based fusion | |
| Chen et al. | Multi-bits biometric string generation based on the likelihood ratio | |
| CN109635576B (en) | Method and system for hiding data in image | |
| Yan et al. | Multi-scale difference map fusion for tamper localization using binary ranking hashing | |
| CN112668519A (en) | Abnormal face recognition living body detection method and system based on MCCAE network and Deep SVDD network | |
| CN110430337A (en) | Method, equipment and the storage medium that image camouflage and image restore | |
| CN113742421B (en) | Network identity authentication method based on distributed storage and image processing | |
| Wu et al. | Fingerprint bio‐key generation based on a deep neural network | |
| Rao et al. | Fingerprint based authentication application using visual cryptography methods (improved id card) | |
| Qin et al. | Research on face image encryption based on deep learning | |
| Kekre et al. | New clustering algorithm for vector quantization using walsh sequence | |
| Bravo-Solorio et al. | Watermarking with lowembedding distortion and self-propagating restoration capabilities | |
| CN114697671B (en) | Building engineering quality management system | |
| CN112989086B (en) | Intelligent recognition and classification system and method for city management images | |
| CN110956468A (en) | Fingerprint payment system | |
| CN112288617B (en) | Information hiding and recovering method, equipment and medium based on mosaic jigsaw | |
| Bendib et al. | A new cancelable deep biometric feature using chaotic maps | |
| CN115049715A (en) | Image steganography based on texture fusion feature block matching and large embedding rate product code | |
| Singh et al. | Cancelable multibiometrics template security using deep binarization and secure hashing | |
| Verma et al. | Biometric based key-generation system for multimedia data security | |
| Wu et al. | Image reversible visual transformation based on MSB replacement and histogram bin mapping | |
| CN110909335A (en) | Binary biological characteristic identification method for privacy protection |
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 |