CN115470503A - Color image encryption method, system and equipment based on chaotic neural network - Google Patents
Color image encryption method, system and equipment based on chaotic neural network Download PDFInfo
- Publication number
- CN115470503A CN115470503A CN202211110201.8A CN202211110201A CN115470503A CN 115470503 A CN115470503 A CN 115470503A CN 202211110201 A CN202211110201 A CN 202211110201A CN 115470503 A CN115470503 A CN 115470503A
- Authority
- CN
- China
- Prior art keywords
- component
- key
- color image
- scrambling
- diffusion
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- G06F21/602—Providing cryptographic facilities or services
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/08—Computing arrangements based on specific mathematical models using chaos models or non-linear system models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2211/00—Indexing scheme relating to details of data-processing equipment not covered by groups G06F3/00 - G06F13/00
- G06F2211/007—Encryption, En-/decode, En-/decipher, En-/decypher, Scramble, (De-)compress
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/21—Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/2107—File encryption
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Computational Mathematics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Nonlinear Science (AREA)
- Algebra (AREA)
- Molecular Biology (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Bioethics (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a color image encryption method, a system and equipment based on a chaotic neural network, which comprises the steps of extracting an R component, a G component and a B component of a color image, respectively generating an R component scrambling transformation key based on a three-dimensional chaotic neural network, scrambling the transformation key by the G component and a B component scrambling transformation key, randomly scrambling the color image in a row and a column according to the scrambling transformation key to obtain a scrambled image, dividing the scrambled image into a plurality of parts according to the row, respectively generating diffusion keys based on the three-dimensional chaotic neural network, diffusing all parts of the segmented image according to all parts of the diffusion keys to obtain all parts of the diffused image, scrambling and splicing all parts of the diffused image by using an array splicing function to obtain a spliced image, synthesizing the spliced image components to obtain an encrypted image of the color image, enhancing the randomness, enhancing the anti-attack capability and improving the safety.
Description
Technical Field
The invention relates to the technical field of image encryption, in particular to a color image encryption method, system and device based on a chaotic neural network.
Background
With the rapid development of digital technology and network technology, more and more multimedia data are generated and transmitted and stored in platforms such as a cloud server through a network. Wherein the digital image contains a large amount of information, for example, not only its size and number, but also its approximate position can be obtained by a military oil depot picture; a picture of a human face may not only reveal his or her long stature, but also give an approximate age and physical condition. Therefore, securing image data has attracted a wide range of attention in medical image systems, military image systems, and video conferencing.
At present, a color image encryption method based on a chaotic neural network mainly has two problems: firstly, the method has low correlation with the plaintext and poor attack resistance; another is that some methods do not take into account the correlation between R, G and B components, and the proposed method is easy to crack by statistical analysis.
Disclosure of Invention
The present invention is directed to at least solving the problems of the prior art. Therefore, the invention provides a color image encryption method, system and device based on a chaotic neural network, which can improve the randomness and enhance the anti-attack capability.
The invention provides a color image encryption method based on a chaotic neural network, which comprises the following steps:
extracting an R component, a G component and a B component of the color image;
respectively generating an R component scrambling transformation key, a G component scrambling transformation key and a B component scrambling transformation key based on a three-dimensional chaotic neural network, performing row-column random scrambling on the R component of the color image according to the R component scrambling transformation key to obtain a scrambled R component, performing row-column random scrambling on the G component of the color image according to the G component scrambling transformation key to obtain a scrambled G component, and performing row-column random scrambling on the B component of the color image according to the B component scrambling transformation key to obtain a scrambled B component;
dividing the scrambled R component, the scrambled G component and the scrambled B component into a plurality of parts according to columns;
respectively generating an R component diffusion key, a G component diffusion key and a B component diffusion key based on the three-dimensional chaotic neural network, diffusing all parts of the divided R component according to the R component diffusion key to obtain all parts of the diffused R component, diffusing all parts of the divided G component according to the G component diffusion key to obtain all parts of the diffused G component, and diffusing all parts of the divided B component according to the B component diffusion key to obtain all parts of the diffused B component;
scrambling and splicing all parts of the diffused R component by using an array splicing function to obtain a spliced R component, scrambling and splicing all parts of the diffused G component by using the array splicing function to obtain a spliced G component, scrambling and splicing all parts of the diffused B component by using the array splicing function to obtain a spliced B component;
and synthesizing the spliced R component, the spliced G component and the spliced B component to obtain the encrypted image of the color image.
According to the embodiment of the invention, at least the following technical effects are achieved:
the method comprises the steps of extracting an R component, a G component and a B component of a color image, respectively generating an R component scrambling transformation key based on a three-dimensional chaotic neural network, respectively generating a G component scrambling transformation key and a B component scrambling transformation key, performing line random scrambling on the R component of the color image according to the R component scrambling transformation key to obtain a scrambled R component, performing line random scrambling on the G component of the color image according to the G component scrambling transformation key to obtain a scrambled G component, performing line random scrambling on the B component of the color image according to the B component scrambling transformation key to obtain a scrambled B component, respectively dividing the scrambled R component, the scrambled G component and the scrambled B component into a plurality of parts in line, respectively generating R component diffusion keys based on the three-dimensional chaotic neural network, respectively generating R component diffusion keys, obtaining the G component diffusion keys and the B component diffusion keys, respectively dividing all parts of the R component divided according to the R component diffusion keys, obtaining all parts of the G component diffusion keys and the B component diffusion keys after the R component diffusion keys, and enhancing all three-dimensional diffusion keys of the color image, and using all three-channel diffusion keys to enhance the safety of all parts of the B component diffusion keys after diffusion keys; scrambling and splicing all parts of the diffused R component by using an array splicing function to obtain a spliced R component, scrambling and splicing all parts of the diffused G component by using the array splicing function to obtain a spliced G component, scrambling and splicing all parts of the diffused B component by using the array splicing function to obtain a spliced B component; and synthesizing the spliced R component, the spliced G component and the spliced B component to obtain an encrypted image of the color image, and scrambling the encrypted image by an array splicing function to enhance the anti-attack capability so that the encryption is safer.
According to some embodiments of the invention, the extracting of the R component, the G component, and the B component of the color image comprises:
separating and extracting an R component, a G component and a B component of the color image by using an array of matlab, wherein the R component, the G component and the B component of the color image have the calculation formulas;
where P is a color image, PR is an R component of the color image, PG is a G component of the color image, and PB is a B component of the color image.
According to some embodiments of the present invention, the generating an R component scrambling transformation key based on a three-dimensional chaotic neural network, and performing line random scrambling on the R component of the color image according to the R component scrambling transformation key to obtain a scrambled R component includes:
acquiring an M multiplied by N two-dimensional matrix of an R component of the color image, wherein M is the number of rows of R component pixel points of the color image, and N is the number of columns of R component pixel points of the color image;
obtaining two groups of chaotic sequences y through a three-dimensional chaotic neural network according to the two-dimensional matrix 1 (z),y 2 (z) generating a scrambling transformation key according to the chaotic sequence, wherein the scrambling transformation key is a random non-repetitive sequence, and the calculation formula for generating the scrambling transformation key according to the chaotic sequence is as follows:
wherein randM (i) is a scrambling transformation key of the ith row of the R component, randN (j) is a scrambling transformation key of the jth column of the R component, and floor () is a down-rounding function;
and constructing a key pair according to the scrambling transformation key and the incremental sequence, wherein a calculation formula of constructing the key pair according to the scrambling transformation key and the incremental sequence is as follows:
wherein, mchange is a 2 xM two-dimensional array key pair, and Nchange is a 2 xN two-dimensional array key pair;
and performing row-column random scrambling on the R component of the color image according to the key pair to obtain a scrambled R component, wherein a calculation formula for performing row-column random scrambling on the R component of the color image according to the key pair is as follows:
according to some embodiments of the invention, the dividing the scrambled R component, the scrambled G component and the scrambled B component into a plurality of parts by columns, respectively, comprises:
dividing the scrambled R component into three parts according to columns to obtain a first part of the R component, a second part of the R component and a third part of the R component, wherein the first part of the R component is the left third of the R component, the second part of the R component is the middle third of the R component, and the third part of the R component is the right third of the R component;
dividing the scrambled G component into three parts according to columns to obtain a first part of the G component, a second part of the G component and a third part of the G component, wherein the first part of the G component is the left third of the G component, the second part of the G component is the middle third of the G component, and the third part of the G component is the right third of the G component;
and dividing the scrambled B component into three parts according to columns to obtain a first part of the B component, a second part of the B component and a third part of the B component, wherein the first part of the B component is the left third of the B component, the second part of the B component is the middle third of the B component, and the third part of the B component is the right third of the B component.
According to some embodiments of the present invention, generating an R component diffusion key based on a three-dimensional chaotic neural network, and diffusing all parts of the segmented R component using the R component diffusion key to obtain all parts of the diffused R component, includes:
obtaining a two-dimensional array of the first portion of the R component, the second portion of the R component, and the third portion of the R component, wherein the calculation formula of obtaining the two-dimensional array of the first portion of the R component, the second portion of the R component, and the third portion of the R component is as follows:
wherein LP is a two-dimensional array of a first part of the R component, CP is a two-dimensional array of a second part of the R component, and RP is a two-dimensional array of a third part of the R component;
three different chaotic sequences y are generated through a three-dimensional chaotic neural network 1 ,y 2 ,y 3 And obtaining an R component diffusion key by the chaotic sequence calculation, wherein the R component diffusion key obtained by the chaotic sequence calculation has a calculation formula as follows:
wherein, k (n) 1 ) A diffusion key, k (n), being a first part of said R component 2 ) A diffusion key, k (n), being a second part of said R component 3 ) A diffusion key that is a third portion of the R component;
exclusive-or encrypting the first part of the R component with the two-dimensional array of the first part of the R component and the diffusion key of the first part of the R component to obtain a diffused first part of the R component, exclusive-or encrypting the second part of the R component with the diffusion key of the second part of the R component to obtain a diffused second part of the R component, exclusive-or encrypting the third part of the R component with the two-dimensional array of the third part of the R component and the diffusion key of the third part of the R component to obtain a diffused third part of the R component, wherein the exclusive-or encrypting the first part of the R component with the two-dimensional array of the first part of the R component and the diffusion key of the first part of the R component to obtain the diffused first part of the R component, exclusive-or encrypting the second part of the R component with the diffusion key of the second part of the R component and the diffusion key of the second part of the R component to obtain the diffused first part of the R component, exclusive-or encrypting the second part of the R component with the diffusion key of the second part of the R component to obtain the diffused third part of the R component, exclusive-or encrypting the second part of the R component with the diffusion key of the R component to obtain the diffused third part of the R component, and calculating the second diffused R component:
wherein CLR is a first part of the diffused R component, CCR is a second part of the diffused R component, CRR is a third part of the diffused R component, and bixor (P, k) is an exclusive-OR function.
According to some embodiments of the present invention, a calculation formula for scrambling and stitching all the parts of the diffused R component by using an array stitching function is as follows:
CR＝[CCR,CLR,CRR]
wherein CR is the spliced R component.
According to some embodiments of the invention, the calculation formula for synthesizing the spliced R component, the spliced G component and the spliced B component is:
C＝cat(3,CR,CG,CB)
wherein C is the encrypted image, CG is the spliced G component, CB is the spliced B component, and cat () is a splicing function.
According to some embodiments of the invention, the third order neural network is of the specific form:
wherein X (t), Y (t), and Z (t) respectively represent state variables of 3 neurons, and initial values of the state variables of the neurons are set to X (0), Y (0), and Z (0).
In a second aspect of the present invention, there is provided a chaotic neural network based color image encryption system, including:
the component extraction module is used for extracting an R component, a G component and a B component of the color image;
the component scrambling module is used for respectively generating an R component scrambling transformation key, a G component scrambling transformation key and a B component scrambling transformation key based on the three-dimensional chaotic neural network, performing line random scrambling on the R component of the color image according to the R component scrambling transformation key to obtain a scrambled R component, performing line random scrambling on the G component of the color image according to the G component scrambling transformation key to obtain a scrambled G component, and performing line random scrambling on the B component of the color image according to the B component scrambling transformation key to obtain a scrambled B component;
a component dividing module, configured to divide the scrambled R component, the scrambled G component, and the scrambled B component into a plurality of portions in a column, respectively;
the component diffusion module is used for respectively generating an R component diffusion key, a G component diffusion key and a B component diffusion key based on the three-dimensional chaotic neural network, diffusing all the divided R components according to the R component diffusion key to obtain all the diffused R components, diffusing all the divided G components according to the G component diffusion key to obtain all the diffused G components, and diffusing all the divided B components according to the B component diffusion key to obtain all the diffused B components;
the component splicing module is used for scrambling and splicing all the parts of the diffused R component by using an array splicing function to obtain a spliced R component, scrambling and splicing all the parts of the diffused G component by using the array splicing function to obtain a spliced G component, and scrambling and splicing all the parts of the diffused B component by using the array splicing function to obtain a spliced B component;
and the component synthesis module is used for synthesizing the spliced R component, the spliced G component and the spliced B component to obtain an encrypted image of the color image.
The system respectively generates R component scrambling transformation keys, G component scrambling transformation keys and B component scrambling transformation keys based on a three-dimensional chaotic neural network by extracting the R component, G component scrambling transformation keys and B component scrambling transformation keys, carries out line random scrambling on the R component of a color image according to the R component scrambling transformation keys to obtain the scrambled R component, carries out line random scrambling on the G component of the color image according to the G component scrambling transformation keys to obtain the scrambled G component, carries out line random scrambling on the B component of the color image according to the B component scrambling transformation keys to obtain the scrambled B component, respectively divides the scrambled R component, the scrambled G component and the scrambled B component into a plurality of parts in line, respectively generates R component diffusion keys based on the three-dimensional chaotic neural network, respectively generates the R component diffusion keys, the G component diffusion keys and the B component diffusion keys, disperses all the divided parts of the R component according to the R component diffusion keys to obtain all the dispersed R component, disperses all the divided parts of the G component according to the G component, obtains all the dispersed parts of the G component, and enhances the safety of the B component, and the three-channel diffusion keys of the color image are generated by using three-channel diffusion keys; scrambling and splicing all parts of the diffused R component by using an array splicing function to obtain a spliced R component, scrambling and splicing all parts of the diffused G component by using the array splicing function to obtain a spliced G component, scrambling and splicing all parts of the diffused B component by using the array splicing function to obtain a spliced B component; and synthesizing the spliced R component, the spliced G component and the spliced B component to obtain an encrypted image of the color image, and scrambling the encrypted image by an array splicing function to enhance the anti-attack capability so that the encryption is safer.
In a third aspect of the invention, a color image encryption electronic device based on a chaotic neural network is provided, which comprises at least one control processor and a memory which is in communication connection with the at least one control processor; the memory stores instructions executable by the at least one control processor to enable the at least one control processor to perform the chaotic neural network based color image encryption method described above.
In a fourth aspect of the present invention, a computer-readable storage medium is provided, which stores computer-executable instructions for causing a computer to execute the above-mentioned chaotic neural network-based color image encryption method.
It should be noted that the beneficial effects between the second to fourth aspects of the present invention and the prior art are the same as the beneficial effects between the above-mentioned color image encryption system based on the chaotic neural network and the prior art, and will not be described in detail here.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flowchart of a color image encryption method based on a chaotic neural network according to an embodiment of the present invention;
fig. 2 is an overall flowchart of a color image encryption method based on a chaotic neural network according to an embodiment of the present invention;
fig. 3 is a graph comparing an experiment of Lena image encryption and decryption in a color image encryption method based on a chaotic neural network according to an embodiment of the present invention;
fig. 4 is a graph of a Lena image histogram test result of a color image encryption method based on a chaotic neural network according to an embodiment of the present invention;
FIG. 5 is a graph of a Lena image correlation test result of a chaotic neural network-based color image encryption method according to an embodiment of the present invention;
FIG. 6 is a graph showing the result of a Lena image sensitivity test of a color image encryption method based on a chaotic neural network according to an embodiment of the present invention;
fig. 7 is a flowchart of a color image encryption system based on a chaotic neural network according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention and are not to be construed as limiting the present invention.
In the description of the present invention, if there are first, second, etc. described, it is only for the purpose of distinguishing technical features, and it is not understood that relative importance is indicated or implied or the number of indicated technical features is implicitly indicated or the precedence of the indicated technical features is implicitly indicated.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to, for example, the upper, lower, etc., is indicated based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, but does not indicate or imply that the device or element referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present invention.
In the description of the present invention, it should be noted that unless otherwise explicitly defined, terms such as setup, installation, connection, etc. should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention by combining the detailed contents of the technical solutions.
At present, a color image encryption method based on a chaotic neural network mainly has two problems: firstly, the method has low correlation with the plaintext and poor attack resistance; another is that some methods do not take into account the correlation between R, G and B components, and the proposed method is easy to crack by statistical analysis.
In order to solve the technical defects, referring to fig. 1 and 2, the invention further provides a color image encryption method based on the chaotic neural network, which includes:
step S101, extracting an R component, a G component, and a B component of the color image.
Step S102, respectively generating an R component scrambling transformation key, a G component scrambling transformation key and a B component scrambling transformation key based on the three-dimensional chaotic neural network, performing row-column random scrambling on the R component of the color image according to the R component scrambling transformation key to obtain a scrambled R component, performing row-column random scrambling on the G component of the color image according to the G component scrambling transformation key to obtain a scrambled G component, and performing row-column random scrambling on the B component of the color image according to the B component scrambling transformation key to obtain a scrambled B component.
Step S103 divides the scrambled R component, the scrambled G component, and the scrambled B component into a plurality of parts in a row.
And step S104, respectively generating an R component diffusion key, a G component diffusion key and a B component diffusion key based on the three-dimensional chaotic neural network, diffusing all parts of the divided R component according to the R component diffusion key to obtain all parts of the diffused R component, diffusing all parts of the divided G component according to the G component diffusion key to obtain all parts of the diffused G component, and diffusing all parts of the divided B component according to the B component diffusion key to obtain all parts of the diffused B component.
And S105, scrambling and splicing all the parts of the diffused R component by using an array splicing function to obtain a spliced R component, scrambling and splicing all the parts of the diffused G component by using the array splicing function to obtain a spliced G component, and scrambling and splicing all the parts of the diffused B component by using the array splicing function to obtain a spliced B component.
And S106, synthesizing the spliced R component, the spliced G component and the spliced B component to obtain an encrypted image of the color image.
The method comprises the steps of extracting an R component, a G component and a B component of a color image, respectively generating an R component scrambling transformation key based on a three-dimensional chaotic neural network, respectively generating a G component scrambling transformation key and a B component scrambling transformation key, performing line random scrambling on the R component of the color image according to the R component scrambling transformation key to obtain a scrambled R component, performing line random scrambling on the G component of the color image according to the G component scrambling transformation key to obtain a scrambled G component, performing line random scrambling on the B component of the color image according to the B component scrambling transformation key to obtain a scrambled B component, respectively dividing the scrambled R component, the scrambled G component and the scrambled B component into a plurality of parts in line, respectively generating R component diffusion keys based on the three-dimensional chaotic neural network, respectively generating R component diffusion keys, obtaining the G component diffusion keys and the B component diffusion keys, respectively dividing all parts of the R component divided according to the R component diffusion keys, obtaining all parts of the G component diffusion keys and the B component diffusion keys after the R component diffusion keys, and enhancing all three-dimensional diffusion keys of the color image, and using all three-channel diffusion keys to enhance the safety of all parts of the B component diffusion keys after diffusion keys; scrambling and splicing all parts of the diffused R component by using an array splicing function to obtain a spliced R component, scrambling and splicing all parts of the diffused G component by using the array splicing function to obtain a spliced G component, scrambling and splicing all parts of the diffused B component by using the array splicing function to obtain a spliced B component; and synthesizing the spliced R component, the spliced G component and the spliced B component to obtain an encrypted image of the color image, and scrambling the encrypted image by an array splicing function to enhance the anti-attack capability so that the encryption is safer.
In some embodiments, step S101 may include, but is not limited to including, step S201:
step S201, separating and extracting an R component, a G component and a B component of the color image by using an array of matlab, wherein the calculation formulas of the R component, the G component and the B component of the color image are as follows;
where P is a color image, PR is an R component of the color image, PG is a G component of the color image, and PB is a B component of the color image.
In some embodiments, step S102 may include, but is not limited to including, step S301 to step S304:
step S301, obtaining an M multiplied by N two-dimensional matrix of the R component of the color image, wherein M is the number of rows of the R component pixel points of the color image, and N is the number of columns of the R component pixel points of the color image.
Step S302, two groups of chaotic sequences y are obtained through a three-dimensional chaotic neural network according to a two-dimensional matrix 1 (z),y 2 (z) generating a scrambling transformation key according to the chaotic sequence, wherein the scrambling transformation key is a random non-repetitive sequence, and a calculation formula for generating the scrambling transformation key according to the chaotic sequence is as follows:
the random M (i) is a scrambling transformation key of the ith row of the R component, the random N (j) is a scrambling transformation key of the jth column of the R component, and the floor () is a rounding-down function.
Step S303, a key pair is constructed according to the scrambling transformation key and the incremental sequence, wherein a calculation formula for constructing the key pair according to the scrambling transformation key and the incremental sequence is:
where, mchange is a 2 × M two-dimensional array key pair, and Nchange is a 2 × N two-dimensional array key pair.
Step S304, performing line-row random scrambling on the R component of the color image according to the key pair to obtain a scrambled R component, wherein a calculation formula for performing line-row random scrambling on the R component of the color image according to the key pair is as follows:
in some embodiments, step S102 may include, but is not limited to including, step S401 to step S404:
step S401, an M multiplied by N two-dimensional matrix of the G component of the color image is obtained, wherein M is the number of rows of the G component pixel points of the color image, and N is the number of columns of the G component pixel points of the color image.
S402, obtaining two groups of chaotic sequences y through a three-dimensional chaotic neural network according to a two-dimensional matrix 3 (z),y 4 (z) generating a scrambling transformation key according to the chaotic sequence, wherein the scrambling transformation key is a random non-repetitive sequence, and a calculation formula for generating the scrambling transformation key according to the chaotic sequence is as follows:
where RandM (i) is the scrambling transform key of the ith row of the G component, randN (j) is the scrambling transform key of the jth column of the G component, and floor () is a floor function.
Step S403, constructing a key pair according to the scrambling transformation key and the incremental sequence, wherein a calculation formula for constructing the key pair according to the scrambling transformation key and the incremental sequence is as follows:
where, mchange is a 2 × M two-dimensional array key pair, and Nchange is a 2 × N two-dimensional array key pair.
Step S404, performing line-column random scrambling on the G component of the color image according to the key pair to obtain a scrambled G component, wherein a calculation formula for performing line-column random scrambling on the G component of the color image according to the key pair is as follows:
the scrambled B component can be obtained in the same way.
In some embodiments, step S103 may include, but is not limited to including, step S501 through step S503:
step S501, dividing the scrambled R component into three parts according to columns, and obtaining a first part of the R component, a second part of the R component, and a third part of the R component, where the first part of the R component is the left third of the R component, the second part of the R component is the middle third of the R component, and the third part of the R component is the right third of the R component.
Step S502, dividing the scrambled G component into three parts according to columns to obtain a first part of the G component, a second part of the G component and a third part of the G component, wherein the first part of the G component is the left third of the G component, the second part of the G component is the middle third of the G component, and the third part of the G component is the right third of the G component.
Step S503, dividing the scrambled B component into three parts according to columns to obtain a first part of the B component, a second part of the B component, and a third part of the B component, wherein the first part of the B component is the left third of the B component, the second part of the B component is the middle third of the B component, and the third part of the B component is the right third of the B component.
In some embodiments, step S104 may include, but is not limited to including, step S601 through step S603:
step S601, obtaining a two-dimensional array of a first part of the R component, a second part of the R component, and a third part of the R component, wherein a calculation formula of obtaining the two-dimensional array of the first part of the R component, the second part of the R component, and the third part of the R component is:
wherein LP is a two-dimensional array of a first portion of the R component, CP is a two-dimensional array of a second portion of the R component, and RP is a two-dimensional array of a third portion of the R component.
Step S602, three different chaotic sequences y are generated through a three-dimensional chaotic neural network 1 ,y 2 ,y 3 And obtaining an R component diffusion key through chaotic sequence calculation, wherein the calculation formula of the R component diffusion key obtained through chaotic sequence calculation is as follows:
wherein, k (n) 1 ) Diffusion key, k (n), being the first part of the R component 2 ) Diffusion key, k (n), which is the second part of the R component 3 ) The diffusion key that is the third part of the R component.
Step S603, xor-encrypting the first part of the R component with the two-dimensional array of the first part of the R component and the diffusion key of the first part of the R component to obtain the first part of the R component after diffusion, xor-encrypting the second part of the R component with the two-dimensional array of the second part of the R component and the diffusion key of the second part of the R component to obtain the second part of the R component after diffusion, xor-encrypting the third part of the R component with the two-dimensional array of the third part of the R component and the diffusion key of the third part of the R component to obtain the third part of the R component after diffusion, wherein xor-encrypting the first part of the R component with the diffusion key of the first part of the R component to obtain the first part of the R component after diffusion, xor-encrypting the second part of the R component with the two-dimensional array of the second part of the R component and the diffusion key of the second part of the R component to obtain the second part of the R component after diffusion, xor-encrypting the third part of the R component with the diffusion key of the second part of the R component to obtain the diffusion key of the R component, and the diffusion key of the third part of the R component after diffusion key of the R component to obtain the diffusion formula:
wherein CLR is a first part of the diffused R component, CCR is a second part of the diffused R component, CRR is a third part of the diffused R component, and bixor (P, k) is an exclusive-OR function.
In some embodiments, step S104 may include, but is not limited to, steps S701 to S703:
step S701, acquiring a two-dimensional array of a first part of a G component, a second part of the G component, and a third part of the G component, wherein a calculation formula of acquiring the two-dimensional array of the first part of the G component, the second part of the G component, and the third part of the G component is:
wherein, LP is the two-dimensional array of the first part of the G component, CP is the two-dimensional array of the second part of the G component, and RP is the two-dimensional array of the third part of the G component.
Step S702, three different chaotic sequences y are generated through a three-dimensional chaotic neural network 4 ,y 5 ,y 6 And calculating a G component diffusion key through the chaotic sequence, wherein a calculation formula of the G component diffusion key obtained through the chaotic sequence is as follows:
wherein, k (n) 4 ) Diffusion key, k (n), being the first part of the G component 5 ) Diffusion key, k (n), being the second part of the G component 6 ) The diffusion key for the third portion of the G component.
Step S703, performing exclusive-or encryption on the first portion of the G component by using the two-dimensional array of the first portion of the G component and the diffusion key of the first portion of the G component to obtain a diffused first portion of the G component, performing exclusive-or encryption on the second portion of the G component by using the two-dimensional array of the second portion of the G component and the diffusion key of the second portion of the G component to obtain a diffused second portion of the G component, performing exclusive-or encryption on the third portion of the G component by using the two-dimensional array of the third portion of the G component and the diffusion key of the third portion of the G component to obtain a diffused third portion of the G component, performing exclusive-or encryption on the first portion of the G component by using the two-dimensional array of the first portion of the G component and the diffusion key of the first portion of the G component to obtain a diffused first portion of the G component, performing exclusive-or encryption on the second portion of the G component by using the two-dimensional array of the second portion of the G component and the diffusion key of the second portion of the G component to obtain a diffused third portion of the G component, and calculating a diffused third portion of the diffusion key of the G component as a diffusion formula:
wherein CLG is the first part of the diffused G component, CCG is the second part of the diffused G component, CRG is the third part of the diffused G component, and bixor (P, k) is an exclusive-or function.
The diffused B component can be obtained in the same way.
In some embodiments, step S105 may include, but is not limited to including, step S801:
step S801, scrambling and stitching all the parts of the diffused R component by using an array stitching function, wherein a calculation formula of the scrambling and the stitching is as follows:
CR＝[CCR,CLR,CRR]
wherein, CR is the R component after splicing.
In some embodiments, step S105 may include, but is not limited to including, step S901:
step S901, performing scrambling and stitching on all the diffused G components by using an array stitching function, wherein a calculation formula of the scrambling and stitching is as follows:
CG＝[CCG,CLG,CRG]
wherein, CG is the spliced G component.
And in the same way, a calculation formula for scrambling and splicing all the parts of the diffused B component by using an array splicing function can be obtained.
In some embodiments, the formula for synthesizing the spliced R component, the spliced G component, and the spliced B component is as follows:
C＝cat(3,CR,CG,CB)
where C is the encrypted image, CG is the spliced G component, CB is the spliced B component, and cat () is the splicing function.
In some embodiments, the third order neural network is embodied in the form of:
wherein X (t), Y (t), and Z (t) respectively represent state variables of 3 neurons, and initial values of the state variables of the neurons are set to X (0), Y (0), and Z (0).
To facilitate understanding by those skilled in the art, a set of experimental data is provided below:
referring to fig. 3, it can be seen that the contour of the ciphertext image cannot be seen completely, and the pixel points are distributed uniformly, so that image information can hardly be obtained from the contour; and the decrypted image and the plaintext image are completely consistent, and the encryption and decryption effects are good.
Referring to fig. 4 and fig. 4, which are graphs showing the results of histogram analysis of Lena, a high-security image encryption system should flatten the histogram of the encrypted ciphertext image as much as possible, and present a peak-like pattern, with the number distribution of each pixel value being extremely uneven, and a cross-sectional phenomenon at both ends, as viewed from the histograms of the plaintext images R, G, and B, thereby being able to obtain most of the information of the image from the plaintext histogram. And the R, G, and B histograms of the ciphertext image are extremely flat, without slices and without any bumps. The encrypted image information is more secret and has certain safety. Therefore, the encryption scheme of the present invention has the ability to resist statistical analysis.
The results of the correlation coefficients in different directions are shown in table 1, and it can be seen that the correlation coefficient of the Lena plaintext image is almost close to 1, which indicates that the correlation of the original text image is extremely strong; and the ciphertext image is almost close to 0, which shows that adjacent pixel points of the ciphertext image have almost no correlation. The plaintext image encrypted by the image encryption system provided by the invention basically has no correlation in four directions, namely horizontal direction, vertical direction, positive angle and negative angle, and is a color image encryption system based on the chaotic neural network with better performance.
TABLE 1
Referring to fig. 5, the Lena plaintext image is seen to be in positive correlation distribution in four directions, namely horizontal, vertical, positive angle and negative angle; however, lena ciphertext images are randomly distributed in four directions, and the pixel value of the adjacent pixel point of each pixel point can be any value. In the plaintext image, the pixel values of the adjacent pixels of each pixel are close to each other, and almost exist or are close to u i ＝v i On this line, the correlation is high.
The information entropy represents the degree of misordering of the state. The larger the entropy value is, the higher the chaos degree is, the higher the image information uncertainty is, and the more irregular the image can be found. The calculation formula is as follows.
Where P (i) represents the probability of occurrence when the pixel value is i. The ideal color image R, G, and B components entropy is 8. The method selects Lena plaintext images to obtain ciphertext images through a chaotic neural network image encryption system, and analyzes the R, G and B component entropies of the ciphertext images. From table 2, it can be seen that the information entropies of the three channels of the ciphertext image obtained by the encryption algorithm provided by this meal are all very close to the theoretical value 8, and it can be seen that the encryption algorithm has good security.
TABLE 2
PSNR, i.e., peak signal-to-noise ratio, is an index for measuring the degree of distortion between a plaintext image and a ciphertext image. The lower the PSNR value, the greater the difference between the plaintext image and the ciphertext image, and the better the encryption algorithm is used.
The full name of the MSE is Mean squared error, which is used to calculate the cumulative squared error between the plaintext image and the ciphertext image. The larger the MSE, the better the encryption effect. PSNR and MSE are defined as follows:
from the PSNR and MSE test results in table 3, PSNR =8.6315 and MSE =8911.0, which indicates that the encryption algorithm proposed by the present invention has very good performance.
TABLE 3
Referring to fig. 6, the sensitivity analysis is to decrypt the ciphertext image with an initial value slightly different from the initial value of the original key to see whether the plaintext image can be recovered. The Lena plaintext image is encrypted by using the initial key value provided herein, and the ciphertext image is decrypted by using three groups of slightly different initial key values Y1, Y2 and Y3 as shown in the following figure 6, so that the plaintext image cannot be correctly recovered. Therefore, the encryption system provided by the invention meets the requirement of key sensitivity.
An ideal image encryption method should have a key space greater than 2 100 The security of the encryption algorithm can be guaranteed. Suppose that the calculation accuracy of the computer is 10 -15 Precision of compressibility CR of 10 -2 . The total secret key space calculation result of the chaotic neural network encryption system in the invention is as follows:
10 2 ×10 15 ×10 14 ×10 14 ×10 14 ×10 14 ×10 14 ×10 14 ×10 14 ＞＞2 100
the encryption method has a key space which is large enough to resist exhaustive attack.
In addition, referring to fig. 7, an embodiment of the present invention provides a color image encryption system based on a chaotic neural network, including a component extraction module 1100, a component scrambling module 1200, a component segmentation module 1300, a component diffusion module 1400, a component splicing module 1500, and a component synthesis module 1600, where:
the component extraction module 1100 is used to extract an R component, a G component, and a B component of a color image.
The component scrambling module 1200 is configured to generate an R component scrambling transformation key, a G component scrambling transformation key, and a B component scrambling transformation key based on the three-dimensional chaotic neural network, perform random row-column scrambling on the R component of the color image according to the R component scrambling transformation key to obtain a scrambled R component, perform random row-column scrambling on the G component of the color image according to the G component scrambling transformation key to obtain a scrambled G component, and perform random row-column scrambling on the B component of the color image according to the B component scrambling transformation key to obtain a scrambled B component.
The component dividing module 1300 is configured to divide the scrambled R component, the scrambled G component, and the scrambled B component into a plurality of portions according to columns.
The component diffusion module 1400 is configured to generate an R component diffusion key, a G component diffusion key, and a B component diffusion key based on the three-dimensional chaotic neural network, diffuse all the parts of the divided R component according to the R component diffusion key to obtain all the parts of the diffused R component, diffuse all the parts of the divided G component according to the G component diffusion key to obtain all the parts of the diffused G component, and diffuse all the parts of the divided B component according to the B component diffusion key to obtain all the parts of the diffused B component.
The component splicing module 1500 is configured to scramble and splice all the parts of the diffused R component with an array splicing function to obtain a spliced R component, scramble and splice all the parts of the diffused G component with an array splicing function to obtain a spliced G component, scramble and splice all the parts of the diffused B component with an array splicing function to obtain a spliced B component.
The component synthesis module 1600 is configured to synthesize the spliced R component, the spliced G component, and the spliced B component to obtain an encrypted image of the color image.
The system respectively generates R component scrambling transformation keys, G component scrambling transformation keys and B component scrambling transformation keys based on a three-dimensional chaotic neural network by extracting the R component, G component scrambling transformation keys and B component scrambling transformation keys, carries out line random scrambling on the R component of a color image according to the R component scrambling transformation keys to obtain the scrambled R component, carries out line random scrambling on the G component of the color image according to the G component scrambling transformation keys to obtain the scrambled G component, carries out line random scrambling on the B component of the color image according to the B component scrambling transformation keys to obtain the scrambled B component, respectively divides the scrambled R component, the scrambled G component and the scrambled B component into a plurality of parts in line, respectively generates R component diffusion keys based on the three-dimensional chaotic neural network, respectively generates the R component diffusion keys, the G component diffusion keys and the B component diffusion keys, disperses all the divided parts of the R component according to the R component diffusion keys to obtain all the dispersed R component, disperses all the divided parts of the G component according to the G component, obtains all the dispersed parts of the G component, and enhances the safety of the B component, and the three-channel diffusion keys of the color image are generated by using three-channel diffusion keys; scrambling and splicing all parts of the diffused R component by using an array splicing function to obtain a spliced R component, scrambling and splicing all parts of the diffused G component by using the array splicing function to obtain a spliced G component, scrambling and splicing all parts of the diffused B component by using the array splicing function to obtain a spliced B component; and synthesizing the spliced R component, the spliced G component and the spliced B component to obtain an encrypted image of the color image, and scrambling the encrypted image by using an array splicing function to enhance the anti-attack capability so that the encryption is safer.
It should be noted that the embodiment of the present system and the embodiment of the system described above are based on the same inventive concept, and therefore, the related contents of the embodiment of the method described above are also applicable to the embodiment of the present system, and are not described herein again.
The present application also provides a color image encryption electronic device based on the chaotic neural network, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor when executing the computer program implementing: the color image encryption method based on the chaotic neural network is disclosed.
The processor and memory may be connected by a bus or other means.
The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and these remote memories may be connected to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The non-transitory software programs and instructions required to implement the chaotic neural network based color image encryption method of the above-described embodiments are stored in the memory, and when executed by the processor, perform the chaotic neural network based color image encryption method of the above-described embodiments, for example, perform the above-described method steps S101 to S106 in fig. 1.
The present application further provides a computer-readable storage medium storing computer-executable instructions for performing: the color image encryption method based on the chaotic neural network is disclosed.
The computer-readable storage medium stores computer-executable instructions, which are executed by a processor or controller, for example, by a processor in the above-mentioned embodiment of the electronic device, and can make the above-mentioned processor execute the color image encryption method based on the chaotic neural network in the above-mentioned embodiment, for example, execute the above-mentioned method steps S101 to S106 in fig. 1.
It will be understood by those of ordinary skill in the art that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, or suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program elements or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program elements, or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as is well known to those of ordinary skill in the art.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (10)
1. A color image encryption method based on a chaotic neural network is characterized by comprising the following steps:
extracting an R component, a G component and a B component of a color image;
respectively generating an R component scrambling transformation key, a G component scrambling transformation key and a B component scrambling transformation key based on a three-dimensional chaotic neural network, performing line random scrambling on the R component of the color image according to the R component scrambling transformation key to obtain a scrambled R component, performing line random scrambling on the G component of the color image according to the G component scrambling transformation key to obtain a scrambled G component, and performing line random scrambling on the B component of the color image according to the B component scrambling transformation key to obtain a scrambled B component;
dividing the scrambled R component, the scrambled G component and the scrambled B component into a plurality of parts according to a column;
respectively generating an R component diffusion key, a G component diffusion key and a B component diffusion key based on the three-dimensional chaotic neural network, diffusing all parts of the divided R component according to the R component diffusion key to obtain all parts of the diffused R component, diffusing all parts of the divided G component according to the G component diffusion key to obtain all parts of the diffused G component, and diffusing all parts of the divided B component according to the B component diffusion key to obtain all parts of the diffused B component;
scrambling and splicing all parts of the diffused R component by using an array splicing function to obtain a spliced R component, scrambling and splicing all parts of the diffused G component by using the array splicing function to obtain a spliced G component, scrambling and splicing all parts of the diffused B component by using the array splicing function to obtain a spliced B component;
and synthesizing the spliced R component, the spliced G component and the spliced B component to obtain the encrypted image of the color image.
2. The chaotic neural network-based color image encryption method according to claim 1, wherein the extracting of the R component, the G component, and the B component of the color image comprises:
separating and extracting an R component, a G component and a B component of the color image by using an array of matlab, wherein the R component, the G component and the B component of the color image have the calculation formulas;
where P is a color image, PR is an R component of the color image, PG is a G component of the color image, and PB is a B component of the color image.
3. The method for encrypting the color image based on the chaotic neural network according to claim 2, wherein the method for encrypting the color image based on the chaotic neural network comprises the steps of generating an R component scrambling transformation key based on the three-dimensional chaotic neural network, and randomly scrambling the R component of the color image according to the R component scrambling transformation key to obtain a scrambled R component, wherein the method comprises the following steps:
acquiring an M multiplied by N two-dimensional matrix of an R component of the color image, wherein M is the number of rows of R component pixel points of the color image, and N is the number of columns of R component pixel points of the color image;
obtaining two groups of chaotic sequences y through a three-dimensional chaotic neural network according to the two-dimensional matrix 1 (z),y 2 (z) generating a scrambling transformation key according to the chaotic sequence, wherein the scrambling transformation key is a random non-repetitive sequence, and the scrambling transformation is generated according to the chaotic sequenceThe calculation formula of the key exchange is as follows:
the random M (i) is a scrambling transformation key of the ith row of the R component, the random N (j) is a scrambling transformation key of the jth column of the R component, and the floor () is a down-rounding function;
and constructing a key pair according to the scrambling transformation key and the incremental sequence, wherein a calculation formula for constructing the key pair according to the scrambling transformation key and the incremental sequence is as follows:
wherein, mchange is a 2 xM two-dimensional array key pair, and Nchange is a 2 xN two-dimensional array key pair;
and performing row-column random scrambling on the R component of the color image according to the key pair to obtain a scrambled R component, wherein a calculation formula for performing row-column random scrambling on the R component of the color image according to the key pair is as follows:
4. the method for encrypting the color image based on the chaotic neural network according to claim 3, wherein the dividing the scrambled R component, the scrambled G component and the scrambled B component into a plurality of parts according to columns comprises:
dividing the scrambled R component into three parts according to columns to obtain a first part of the R component, a second part of the R component and a third part of the R component, wherein the first part of the R component is the left third of the R component, the second part of the R component is the middle third of the R component, and the third part of the R component is the right third of the R component;
dividing the scrambled G component into three parts according to columns to obtain a first part of the G component, a second part of the G component and a third part of the G component, wherein the first part of the G component is one third of the left side of the G component, the second part of the G component is one third of the middle side of the G component, and the third part of the G component is one third of the right side of the G component;
and dividing the scrambled B component into three parts according to columns to obtain a first part of the B component, a second part of the B component and a third part of the B component, wherein the first part of the B component is the left third of the B component, the second part of the B component is the middle third of the B component, and the third part of the B component is the right third of the B component.
5. The method for encrypting the color image based on the chaotic neural network according to claim 4, wherein an R component diffusion key is generated based on a three-dimensional chaotic neural network, and all parts of the segmented R component are diffused by using the R component diffusion key to obtain all parts of the diffused R component, and the method comprises the following steps:
obtaining a two-dimensional array of the first portion of the R component, the second portion of the R component, and the third portion of the R component, wherein the calculation formula of obtaining the two-dimensional array of the first portion of the R component, the second portion of the R component, and the third portion of the R component is as follows:
wherein LP is a two-dimensional array of a first part of the R component, CP is a two-dimensional array of a second part of the R component, and RP is a two-dimensional array of a third part of the R component;
three different chaotic sequences y are generated through a three-dimensional chaotic neural network 1 ,y 2 ,y 3 Calculating to obtain R component diffusion through the chaos sequenceAnd the key, wherein the calculation formula of the R component diffusion key obtained by the chaos sequence calculation is as follows:
wherein, k (n) 1 ) A diffusion key, k (n), being a first part of said R component 2 ) A diffusion key, k (n), being a second part of said R component 3 ) A diffusion key that is a third portion of the R component;
exclusive-OR encrypting the first part of the R component by using a two-dimensional array of the first part of the R component and a diffusion key of the first part of the R component to obtain a diffused first part of the R component, exclusive-OR encrypting the second part of the R component by using a two-dimensional array of the second part of the R component and a diffusion key of the second part of the R component to obtain a diffused second part of the R component, exclusive-OR encrypting the third part of the R component by using a two-dimensional array of the third part of the R component and a diffusion key of the third part of the R component to obtain a diffused third part of the R component, wherein exclusive-OR encrypting the first part of the R component by using a diffusion key of the first part of the R component and the diffusion key of the first part of the R component to obtain the diffused first part of the R component, exclusive-OR encrypting the second part of the R component by using a two-dimensional array of the second part of the R component and a diffusion key of the second part of the R component to obtain a diffused second part of the R component, exclusive-OR encrypting the second part of the R component by using a diffusion key of the second part of the R component to obtain a diffusion key of the diffused R component, and the diffused second part of the R component, and the R component, calculating the diffusion key of the R component:
wherein CLR is a first part of the diffused R component, CCR is a second part of the diffused R component, CRR is a third part of the diffused R component, and bixor (P, k) is an exclusive-OR function.
6. The method for encrypting the color image based on the chaotic neural network according to claim 5, wherein a calculation formula for scrambling and splicing all the diffused R components by using an array splicing function is as follows:
CR＝[CCR,CLR,CRR]
wherein CR is the spliced R component.
7. The method for encrypting the color image based on the chaotic neural network according to claim 6, wherein a calculation formula for synthesizing the spliced R component, the spliced G component and the spliced B component is as follows:
C＝cat(3,CR,CG,CB)
wherein C is the encrypted image, CG is the spliced G component, CB is the spliced B component, and cat () is a splicing function.
8. The color image encryption method based on the chaotic neural network as claimed in claim 7, wherein the third-order neural network is in a specific form:
wherein X (t), Y (t) and Z (t) respectively represent state variables of 3 neurons, and initial values of the state variables of the neurons are set to X (0), Y (0) and Z (0).
9. A color image encryption system based on a chaotic neural network is characterized by comprising:
the component extraction module is used for extracting an R component, a G component and a B component of the color image;
the component scrambling module is used for respectively generating an R component scrambling transformation key, a G component scrambling transformation key and a B component scrambling transformation key based on the three-dimensional chaotic neural network, performing line random scrambling on the R component of the color image according to the R component scrambling transformation key to obtain a scrambled R component, performing line random scrambling on the G component of the color image according to the G component scrambling transformation key to obtain a scrambled G component, and performing line random scrambling on the B component of the color image according to the B component scrambling transformation key to obtain a scrambled B component;
a component dividing module for dividing the scrambled R component, the scrambled G component and the scrambled B component into a plurality of parts in a row;
the component diffusion module is used for respectively generating an R component diffusion key, a G component diffusion key and a B component diffusion key based on the three-dimensional chaotic neural network, diffusing all the divided R components according to the R component diffusion key to obtain all the diffused R components, diffusing all the divided G components according to the G component diffusion key to obtain all the diffused G components, and diffusing all the divided B components according to the B component diffusion key to obtain all the diffused B components;
the component splicing module is used for scrambling and splicing all the parts of the diffused R component by using an array splicing function to obtain a spliced R component, scrambling and splicing all the parts of the diffused G component by using the array splicing function to obtain a spliced G component, and scrambling and splicing all the parts of the diffused B component by using the array splicing function to obtain a spliced B component;
and the component synthesis module is used for synthesizing the spliced R component, the spliced G component and the spliced B component to obtain an encrypted image of the color image.
10. The color image encryption equipment based on the chaotic neural network is characterized by comprising at least one control processor and a memory which is in communication connection with the at least one control processor; the memory stores instructions executable by the at least one control processor to enable the at least one control processor to perform the chaotic neural network based color image encryption method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211110201.8A CN115470503A (en) | 2022-09-13 | 2022-09-13 | Color image encryption method, system and equipment based on chaotic neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211110201.8A CN115470503A (en) | 2022-09-13 | 2022-09-13 | Color image encryption method, system and equipment based on chaotic neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115470503A true CN115470503A (en) | 2022-12-13 |
Family
ID=84333636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211110201.8A Pending CN115470503A (en) | 2022-09-13 | 2022-09-13 | Color image encryption method, system and equipment based on chaotic neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115470503A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117951754A (en) * | 2024-03-27 | 2024-04-30 | 国网山东省电力公司济南供电公司 | Electronic seal encryption and decryption method, device and medium based on deep learning |
-
2022
- 2022-09-13 CN CN202211110201.8A patent/CN115470503A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117951754A (en) * | 2024-03-27 | 2024-04-30 | 国网山东省电力公司济南供电公司 | Electronic seal encryption and decryption method, device and medium based on deep learning |
| CN117951754B (en) * | 2024-03-27 | 2024-06-07 | 国网山东省电力公司济南供电公司 | Electronic seal encryption and decryption method, device and medium based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhan et al. | Cross-utilizing hyperchaotic and DNA sequences for image encryption | |
| Zhang et al. | Image encryption based on three-dimensional bit matrix permutation | |
| KR100699703B1 (en) | How to verify the integrity of an image transferred with loss | |
| CN109102452B (en) | Image encryption method based on Latin square array scrambling and bidirectional diffusion | |
| CN109104544B (en) | Chaotic image encryption method based on complex network synchronization | |
| CN112272262B (en) | Image encryption and decryption method and device | |
| CN103530571A (en) | Image encryption method based on sine mapping and Logistic chaos sequence | |
| CN106709854A (en) | Cat mapping and chaos based image information fusion and encryption method | |
| Arshad et al. | A novel image encryption scheme based on Walsh compressed quantum spinning chaotic Lorenz system | |
| Lee et al. | Selective scalable secret image sharing with verification | |
| Islam et al. | Application of homomorphism to secure image sharing | |
| CN115470503A (en) | Color image encryption method, system and equipment based on chaotic neural network | |
| Ganesan et al. | Image encryption using eight dimensional chaotic cat map | |
| Yang et al. | MTVSS:(M) isalignment (T) olerant (V) isual (S) ecret (S) haring on resolving alignment difficulty | |
| Dey et al. | Linear‐feedback shift register‐based multi‐ant cellular automation and chaotic map‐based image encryption | |
| Zhang et al. | A digital image encryption scheme based on the hybrid of cellular neural network and logistic map | |
| CN116208394A (en) | Image processing method, system, image capturing apparatus, server, and storage medium | |
| Yakubu et al. | A chaos based image encryption algorithm using ShimizuMorioka system | |
| Ramakrishna et al. | A Novel Image Encryption using 3D Logistic Map and Improved Chirikov Map | |
| Rajput et al. | Cloud based image color transfer and storage in encrypted domain | |
| Singh et al. | Stealth steganography in visual cryptography for half tone images | |
| CN114612280B (en) | Color image encryption method and system based on three-dimensional Boolean convolutional neural network | |
| Chen et al. | Cheating prevention in visual cryptography | |
| Yang et al. | New region incrementing visual cryptography scheme | |
| Ntalianis et al. | Chaotic video objects encryption based on mixed feedback, multiresolution decomposition and time-variant S-boxes |
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 |