CN115102683A - Method, system and equipment for encrypting and decrypting face image based on target detection technology - Google Patents

Method, system and equipment for encrypting and decrypting face image based on target detection technology Download PDF

Info

Publication number
CN115102683A
CN115102683A CN202210490733.2A CN202210490733A CN115102683A CN 115102683 A CN115102683 A CN 115102683A CN 202210490733 A CN202210490733 A CN 202210490733A CN 115102683 A CN115102683 A CN 115102683A
Authority
CN
China
Prior art keywords
image
face
group
face image
sequences
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
Application number
CN202210490733.2A
Other languages
Chinese (zh)
Inventor
谢巍
余锦伟
杨启帆
魏金湖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
South China University of Technology SCUT
Original Assignee
South China University of Technology SCUT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by South China University of Technology SCUT filed Critical South China University of Technology SCUT
Priority to CN202210490733.2A priority Critical patent/CN115102683A/en
Publication of CN115102683A publication Critical patent/CN115102683A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/001—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols using chaotic signals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/235—Processing of additional data, e.g. scrambling of additional data or processing content descriptors
    • H04N21/2351—Processing of additional data, e.g. scrambling of additional data or processing content descriptors involving encryption of additional data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
    • H04N21/4405—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving video stream decryption
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate

Abstract

The invention relates to the field of face privacy protection, and discloses a face image encryption and decryption method, system and device based on a target detection technology. The method comprises the following steps: acquiring a face region in an image, generating a plaintext associated key based on the acquired face image, performing pixel scrambling, pixel diffusion and row-column scrambling on the face region image by using an integer random sequence to obtain an encrypted face image, and fusing the encrypted face image with the non-face region to obtain a ciphertext image. The face area in the image is detected and extracted by combining a target detection technology, and the face area in the image is locally encrypted by combining a hyperchaotic Chen system, so that the face privacy protection function is realized, the calculation amount in the encryption process is reduced, and the efficiency of an encryption algorithm is improved.

Description

Method, system and equipment for encrypting and decrypting face image based on target detection technology
Technical Field
The invention relates to the field of face privacy protection, in particular to a face image encryption and decryption method, system and device based on a target detection technology.
Background
In recent years, biometric identification technology has been widely applied to various fields with its uniqueness and stability. The biological characteristics comprise the inherent characteristics of each person such as fingerprints, irises and faces, wherein the face information is widely applied to daily scenes such as mobile payment and intelligent access control due to the unique convenience of the face information.
With the wide application of biometric technology, the security of biometric information has received great attention. If the face information is leaked, the encryption system bound with the face is cracked permanently. With the development of internet and multimedia technology, people have become accustomed to transmitting photos on social networks, which increases the risk of facial image leakage. In order to solve the security problem of face privacy leakage, the technical research on the encryption protection of the face image is very important.
Disclosure of Invention
The invention provides a face image encryption and decryption method and system based on a target detection technology, and aims to realize the face privacy protection function, reduce the calculation amount in the encryption process and improve the efficiency of an encryption algorithm by combining the target detection technology to detect and extract the face area in the image and combining a hyperchaotic Chen system to perform local encryption on the face area in the image.
The invention aims to provide a face image encryption and decryption method based on an object detection technology.
The second purpose of the invention is to provide a face image encryption and decryption system based on the target detection technology.
It is a third object of the invention to provide a computer apparatus.
The first purpose of the invention can be achieved by adopting the following technical scheme:
a face image encryption and decryption method based on a target detection technology comprises the following steps:
s1, detecting the input plaintext image by using an MTCNN model, acquiring a face region image and face position coordinates, and calculating an average gray value of the face image;
s2, setting an initial key, calculating a first group of initial values of the hyperchaotic Chen system according to the initial key and the average gray value of the face image, and iterating the hyperchaotic Chen system to generate a first group of chaotic sequences;
s3, calculating by using the average gray value of the face image and the first group of chaotic sequences, updating and acquiring a second group of initial values of the hyperchaotic Chen system, and iterating the hyperchaotic Chen system to generate a second group of chaotic sequences;
s4, preprocessing the first group of chaotic sequences and the second group of chaotic sequences, converting the first group of chaotic sequences and the second group of chaotic sequences into integer random sequences and integer index sequences with preset lengths, and performing pixel scrambling, pixel diffusion and row-column scrambling on the face region image by using the integer random sequences to obtain an encrypted face image;
s5, fusing the encrypted face image and the non-face area in the plaintext image into an image, carrying out XOR encryption on the face position coordinates, and embedding the encrypted face position coordinates into the fused image to obtain a final ciphertext image.
The second purpose of the invention can be achieved by adopting the following technical scheme:
the face image encryption and decryption system based on the target detection technology comprises:
the detection module is used for detecting the input plaintext image by using the MTCNN model, acquiring a face region image and face position coordinates, and calculating an average gray value of the face image;
the first generation module is used for setting an initial key, calculating a first group of initial values of the hyperchaotic Chen system according to the average gray value of the face image, and iterating the hyperchaotic Chen system to generate a first group of chaotic sequences;
the second generation module is used for calculating by using the average gray value of the face image and the first group of chaotic sequences, updating and acquiring a second group of initial values of the hyperchaotic Chen system, and iterating the hyperchaotic Chen system to generate a second group of chaotic sequences;
the encryption module is used for preprocessing the first group of chaotic sequences and the second group of chaotic sequences, converting the first group of chaotic sequences and the second group of chaotic sequences into integer random sequences and integer index sequences with preset lengths, and performing pixel scrambling, pixel diffusion and row-column scrambling on the face region image by using the integer random sequences to obtain an encrypted face image;
and the fusion output module is used for fusing the encrypted face image and the non-face area in the plaintext image into an image, carrying out XOR encryption on the face position coordinates, and embedding the encrypted face position coordinates into the fused image to obtain a final ciphertext image.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. according to the invention, by adopting a local area encryption mode, the face area in the image is detected by using the target detection algorithm, and then the face area is encrypted, so that the calculated amount in the encryption process is reduced, the efficiency of the encryption algorithm is improved, the face area in the image is encrypted, and the risk of face data leakage is effectively reduced.
2. The invention can be applied to practical scenes such as access control systems, airport identity authentication, safe payment and the like, can effectively protect personal privacy, prevents face data from being revealed, and has higher practical application value.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
Fig. 1 is a flowchart of implementing face image encryption based on a target detection technology in embodiment 1 of the present invention;
fig. 2 is a basic flowchart for implementing two-stage plaintext associated key generation in embodiment 1 of the present invention;
fig. 3 is a schematic diagram of an overall architecture of a face image encryption algorithm in embodiment 1 of the present invention;
fig. 4 is a schematic diagram of an encryption effect of the face image encryption method in embodiment 1 of the present invention.
Detailed Description
The technical solutions of the present invention will be described in further detail with reference to the accompanying drawings and examples, and it is obvious that the described examples are some, but not all, examples of the present invention, and the embodiments of the present invention are not limited thereto. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
as shown in fig. 1, the face image encryption and decryption algorithm based on the target detection technology of the present invention includes the following steps:
the method comprises the following steps: and detecting the input plaintext image by using the MTCNN model, acquiring a face region image and face position coordinates, and calculating the average gray value of the face image.
Specifically, a plaintext image is input into a MTCNN face detection model trained by a high-performance GPU, and model operation is carried out to obtain the position coordinates (x) of a face area 1 ,y 1 )、(x 2 ,y 2 ) The position coordinates of the face area comprise the coordinates of the upper left corner of the face area and the coordinates of the lower right corner of the face area; wherein (x) 1 ,y 1 ) Coordinates of the upper left corner representing the face region, (x) 2 ,y 2 ) The coordinates of the lower right corner representing the face region; cutting the original image according to the obtained face position coordinates to obtain a face image P with the size of M multiplied by N, and calculating the average gray value P of the face image ave 。
The face area in the image is detected by using the target detection algorithm, and then the face area is encrypted, so that the calculated amount in the encryption process is reduced, and the efficiency of the encryption algorithm is improved.
Step two: setting an initial key, calculating a first group of initial values of the hyperchaotic Chen system according to the initial key and the average gray value of the face image, and iterating the hyperchaotic Chen system to generate a first group of chaotic sequences.
In this embodiment, the initial key is set to x 0 ,y 0 ,z 0 ,h 0 And calculating the variation of the four initial values according to the average gray value of the face image. Average gray value P of human face image ave The value of each decimal digit is represented as C i (i ═ 1,2, L,16), the amounts of change in the four initial values Δ α, Δ β, Δ θ, Δ γ were calculated:
Figure BDA0003631679240000041
initial key x 0 ,y 0 ,z 0 ,h 0 Operating with the variation of the four initial values of delta alpha, delta beta, delta theta and delta gamma to generate a first set of initial values x associated with the plaintext 01 ,y 01 ,z 01 ,h 01 . The specific operation is as follows:
Figure BDA0003631679240000042
wherein x is 0 ,y 0 ,z 0 ,h 0 As initial key, initial values x of delta alpha, delta beta, delta theta and delta gamma 01 ,y 01 ,z 01 ,h 01 The amount of change in (c).
An initial value is substituted into a hyperchaotic Chen system and a first group of chaotic sequences X with the length of 2MN +1 are generated in an iterative way 1 、Y 1 、Z 1 And H 1 . The hyperchaotic Chen system comprises an iterative equation:
Figure BDA0003631679240000043
wherein m, q, p, n, r are parameters of the system; 0,1,2, 3.; x, y, z, h are state variables that produce a chaotic sequence.
Step three: and calculating by using the average gray value of the face image and the first group of chaotic sequences, updating to obtain a second group of initial values of the hyperchaotic Chen system, and iterating the hyperchaotic Chen system again to generate a second group of chaotic sequences.
In this embodiment, a chaotic sequence X is used 1 、Y 1 、Z 1 And H 1 Element X of (2) 1 (2MN +1), element Y 1 (2MN +1), element Z 1 (2MN +1) and element H 1 (2MN +1) and the four variable quantities obtained in the second step are calculated, and a second group of initial values x are obtained through updating 02 ,y 02 ,z 02 ,h 02 ：
Figure BDA0003631679240000044
Setting a second set of initial values x 02 ,y 02 ,z 02 ,h 02 The hyperchaotic Chen system is replaced, and the hyperchaotic Chen system is iterated for the second time to generate four chaotic sequences X with the length of 2MN 2 、Y 2 、Z 2 And H 2 。
As shown in fig. 2, a basic flow chart of two-stage plaintext associated key generation first calculates an average gray value of a face image, and sets an initial key of a hyper-chaotic Chen system. The initial values of the first group of hyperchaotic Chen systems are obtained through calculation and updating of the average gray value of the face image, and the hyperchaotic Chen systems are iterated to generate chaotic sequences. And (4) recalculating the chaos sequence and the average gray value of the face image to obtain a second set of initial values, and iterating the hyperchaotic Chen system again to generate a second set of chaos sequence. And finally, preprocessing the two groups of chaotic sequences to obtain eight integer random sequences.
Step four: preprocessing the first group of chaotic sequences and the second group of chaotic sequences, converting the first group of chaotic sequences and the second group of chaotic sequences into integer random sequences and integer index sequences with preset lengths, and performing pixel scrambling, pixel diffusion and row-column scrambling on the face region image by using the integer random sequences to obtain an encrypted face image.
In this embodiment, the first group of chaotic sequences and the second group of chaotic sequences are preprocessed and converted into integer random sequences and integer index sequences of preset lengths, where S 1 -S 3 、S 5 -S 7 Is an integerRandom sequence, S 4 And S 8 Is a chaotic sequence in which S 4 For generating integer index sequences Ind S4 ，S 8 For generating the integer index sequence Ind M Integer index sequence Ind N And a random sequence S of integers pos The method comprises the following steps:
Figure BDA0003631679240000051
Figure BDA0003631679240000052
where round (x) is a function that rounds x to zero to the nearest integer; mod (a, b) represents the modulo operation of a on b.
To S 4 Sorting to obtain integer index sequence Ind S4 ：
Ind S4 ＝sort(S 4 )
Wherein Sort (S) is a function for obtaining the sorting index of the elements in S in a descending order.
By S 8 Obtaining an integer index sequence Ind M 、Ind N And an integer random sequence S pos ：
Figure BDA0003631679240000061
In which Ind M For scrambling lines, Ind, of images N For scrambling image columns, S pos Used for encrypting the face position coordinates.
Preferably, the pixel scrambling, the pixel diffusing and the row-column scrambling are performed on the face region image by using an integer random sequence and an integer index sequence, and the obtaining of the encrypted face image includes:
and (2) carrying out pixel scrambling on the face image, decomposing the face image P into three channel images PR, PG and PB, and remolding the PR, PG and PB into one-dimensional vectors VR, VG and VB of 1 multiplied by MN.
Will threeAll pixels in the one-dimensional vectors VR, VG and VB are indexed according to the integer index sequence Ind S4 Element universities in (1) reordering:
Figure BDA0003631679240000062
wherein i is 1,2, L, N, M; temp is a temporary variable.
And remolding VR, VG and VB into three matrixes with the size of M multiplied by N to obtain scrambled channel images SR, SG and SB.
Performing pixel diffusion on the face image, wherein the process of pixel cyclic diffusion is divided into two rounds, and the first round uses an integer random sequence S 1 -S 3 Respectively diffusing three channel images of the face image, wherein the pixels of each channel are in the sequence of S from left to right and from top to bottom 1 -S 3 After the elements in the sequence are subjected to XOR encryption, the elements are subjected to XOR operation with the pixels at the previous position. The first round of diffusion is specifically that the first pixel is subjected to exclusive-or encryption by the following formula:
Figure BDA0003631679240000063
wherein
Figure BDA0003631679240000064
Representing a bitwise xor operation. The remaining pixels are iteratively diffused by the following formula:
Figure BDA0003631679240000065
wherein i is 1,2, L, M; j is 1,2, L, N; n is 1 ＝2,3,L,MN；last i And last j Determined by the following equation:
Figure BDA0003631679240000066
second round of diffusionIn (1), using a chaotic sequence S 5 -S 7 And respectively diffusing the three channel images of the face image. And carrying out XOR encryption on the pixels of each channel image and the chaotic random number in the sequence from bottom to top and from right to left, and then carrying out XOR operation on the pixels at the next position. The second round of diffusion algorithm specifically iterates the following formula to perform diffusion encryption on the pixels:
Figure BDA0003631679240000071
wherein i ═ M, M-1, L, 1; j is N, N-1, L, 1; n is 2 ＝2,3,L,MN；last i And last j Determined by the following equation:
Figure BDA0003631679240000072
and values of the matrix SR, SG and SB elements are assigned to the images DR, DG and DB.
Performing row-column scrambling on the face image, firstly using an integer index sequence Ind M Scrambling the image, specifically:
Figure BDA0003631679240000073
wherein i is 1,2, L, M; DR (i,: indicates the ith row of DR.
Followed by the use of the integer index sequence Ind N And (3) performing row scrambling on the image:
Figure BDA0003631679240000074
wherein j is 1,2, L, N; DR (: j) denotes the j-th column of DR.
And finally, fusing the three scrambled channel images to obtain a color encrypted face image.
As shown in fig. 3, the overall architecture of the face image encryption algorithm is schematically illustrated, and a plain text image is processed by a face detection algorithm to obtain a face image, face position coordinates and a non-face region image, wherein the face image is encrypted by pixel scrambling, pixel diffusion and row-column scrambling to obtain an encrypted face image, and the face position coordinates are encrypted by exclusive or to obtain encrypted face position coordinates. And fusing the encrypted face image with the non-face area in the plaintext image, and embedding the position coordinates of the encrypted face into the fused image to obtain a ciphertext image.
Step five: fusing the encrypted face image and the non-face area in the plaintext image into an image, carrying out XOR encryption on the face position coordinates, and embedding the encrypted face position coordinates into the fused image to obtain a final ciphertext image.
Using an integer random sequence S pos And carrying out XOR encryption on the face position to obtain an encrypted face position coordinate, thus obtaining the encrypted watermark. Specifically, the exclusive or encryption is performed by the following formula:
Figure BDA0003631679240000081
fusing the encrypted face image with a non-face area in a plaintext image, and replacing the original non-encrypted face area with the encrypted face area, so as to combine the encrypted face area and the non-face area into an image; and embedding the encrypted face position coordinates into the first four pixels in the R channel of the fusion image, hiding face position information and obtaining a final ciphertext image. As shown in fig. 4, a schematic diagram of an encryption effect of a face image is shown, a face area in a picture is encrypted, and a non-face area retains original information.
Example 2:
the embodiment provides a face image encryption and decryption system based on a target detection technology, which comprises a detection module, a first generation module, a second generation module, an encryption module and a fusion output module, wherein the specific functions of the modules are as follows:
the detection module is used for detecting the input plaintext image by using an MTCNN model, acquiring a face region image and face position coordinates, and calculating an average gray value of the face image;
the first generation module is used for setting an initial key, calculating a first group of initial values of the hyperchaotic Chen system according to the average gray value of the face image, and iterating the hyperchaotic Chen system to generate a first group of chaotic sequences;
the second generation module is used for calculating by using the average gray value of the face image and the first group of chaotic sequences, updating and acquiring a second group of initial values of the hyperchaotic Chen system, and iterating the hyperchaotic Chen system to generate a second group of chaotic sequences;
the encryption module is used for preprocessing the first group of chaotic sequences and the second group of chaotic sequences, converting the first group of chaotic sequences and the second group of chaotic sequences into integer random sequences and integer index sequences with preset lengths, and performing pixel scrambling, pixel diffusion and row-column scrambling on the face region image by using the integer random sequences to obtain an encrypted face image;
and the fusion output module is used for fusing the encrypted face image and the non-face area in the plaintext image into an image, carrying out XOR encryption on the face position coordinates, and embedding the encrypted face position coordinates into the fused image to obtain a final ciphertext image.
Example 3:
the present embodiment provides a computer device, which may be a server, a computer, or the like, and includes a processor, a memory, an input device, a display, and a network interface connected by a system bus, where the processor is configured to provide computing and control capabilities, the memory includes a nonvolatile storage medium and an internal memory, the nonvolatile storage medium stores an operating system, a computer program, and a database, the internal memory provides an environment for the operating system and the computer program in the nonvolatile storage medium to run, and when the processor executes the computer program stored in the memory, the method for encrypting and decrypting a face image based on an object detection technology in embodiment 1 is implemented as follows:
detecting an input plaintext image by using an MTCNN model, acquiring a face region image and face position coordinates, and calculating an average gray value of the face image;
setting an initial key, calculating a first group of initial values of the hyperchaotic Chen system according to the average gray value of the face image, and iterating the hyperchaotic Chen system to generate a first group of chaotic sequences;
calculating by using the average gray value of the face image and the first group of chaotic sequences, updating to obtain a second group of initial values of the hyperchaotic Chen system, and iterating the hyperchaotic Chen system to generate a second group of chaotic sequences;
preprocessing the first group of chaotic sequences and the second group of chaotic sequences, converting the first group of chaotic sequences and the second group of chaotic sequences into integer random sequences and integer index sequences with preset lengths, and performing pixel scrambling, pixel diffusion and row-column scrambling on the face region image by using the integer random sequences to obtain an encrypted face image;
and fusing the encrypted face image and the non-face region in the plaintext image into an image, carrying out XOR encryption on the face position coordinates, and embedding the encrypted face position coordinates into the fused image to obtain a final ciphertext image.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.

Claims (10)

1. The face image encryption and decryption method based on the target detection technology is characterized by comprising the following steps:
s1, detecting the input plaintext image by using an MTCNN model, acquiring a face region image and face position coordinates, and calculating an average gray value of the face image;
s2, setting an initial key, calculating a first group of initial values of the hyperchaotic Chen system according to the initial key and the average gray value of the face image, and iterating the hyperchaotic Chen system to generate a first group of chaotic sequences;
s3, calculating by using the average gray value of the face image and the first group of chaotic sequences, updating and acquiring a second group of initial values of the hyperchaotic Chen system, and iterating the hyperchaotic Chen system to generate a second group of chaotic sequences;
s4, preprocessing the first group of chaotic sequences and the second group of chaotic sequences, converting the first group of chaotic sequences and the second group of chaotic sequences into integer random sequences and integer index sequences with preset lengths, and performing pixel scrambling, pixel diffusion and row-column scrambling on the face region image by using the integer random sequences to obtain an encrypted face image;
and S5, fusing the encrypted face image and the non-face region in the plaintext image into an image, carrying out XOR encryption on the face position coordinates, and embedding the encrypted face position coordinates into the fused image to obtain a final ciphertext image.
2. The method for encrypting and decrypting the face image based on the target detection technology as claimed in claim 1, characterized in that: the MTCNN model is an MTCNN face detection model trained by a GPU, a plaintext image is input into the MTCNN face detection model to obtain position coordinates of a face area, an original plaintext image is cut according to the obtained position coordinates of the face area to obtain a face image with the size of M multiplied by N, and the average gray value of the face image is calculated;
the face region position coordinates comprise the coordinates of the upper left corner of the face region and the coordinates of the lower right corner of the face region.
3. The target detection technology-based face image encryption and decryption method of claim 1, wherein: the step S2 includes: setting an initial key, and calculating the variation of the four initial values according to the average gray value of the face image; calculating the initial key and the variation of the four initial values to generate a first group of initial values related to the plaintext; and (3) substituting the first group of initial values into the hyperchaotic Chen system, and iterating the hyperchaotic Chen system to obtain four chaotic sequences.
4. The method for encrypting and decrypting the face image based on the target detection technology as claimed in claim 3, characterized in that:
the operation formula of the first group of initial values is as follows:
Figure FDA0003631679230000011
wherein x is 01 ,y 01 ,z 01 ,h 01 Is a first set of initial values, x 0 ,y 0 ,z 0 ,h 0 As initial keys, delta alpha, delta beta, delta theta and delta gamma are initial values x respectively 01 ,y 01 ,z 01 ,h 01 The amount of change in (c);
the iteration equation of the hyperchaotic Chen system is as follows:
Figure FDA0003631679230000021
where m, q, p, n, r are parameters of the system, i is 0,1,2,3, x, y, z, h are state variables that generate the chaotic sequence.
5. The target detection technology-based face image encryption and decryption method of claim 4, wherein: the step S3 includes: calculating by using the elements of the 4 chaotic sequences and the variable quantity of the first group of initial values, and updating to obtain a second group of initial values; and substituting a second group of initial values into the hyperchaotic Chen system, and performing second iteration on the hyperchaotic Chen system to obtain four chaotic sequences.
6. The target detection technology-based face image encryption and decryption method of claim 5, wherein: the operation formula of the second group of initial values is as follows:
Figure FDA0003631679230000022
wherein x is 02 ,y 02 ,z 02 ,h 02 Is a second set of initial values, X 1 (2MN+1)、Y 1 (2MN+1)、Z 1 (2MN+1)、H 1 (2MN +1) is an element of the chaotic sequence, and delta alpha, delta beta, delta theta and delta gamma are respectivelyInitial value x 01 ,y 01 ,z 01 ,h 01 The amount of change in (c).
7. The method for encrypting and decrypting the face image based on the target detection technology as claimed in claim 1, characterized in that: the step S4 includes:
performing pixel scrambling on a face image, decomposing the face image into 3 channel images, then remolding the 3 channel images into 3 one-dimensional vectors, reordering all pixels in the 3 one-dimensional vectors according to element universities in an integer index sequence, remolding the 3 one-dimensional vectors into 3 matrixes with the size of M multiplied by N, and obtaining 3 scrambled channel images;
performing pixel diffusion on the face image, performing first round diffusion on three channel images of the face image by using an integer random sequence, performing XOR encryption on the pixels of each channel image and elements in the integer random sequence from left to right and from top to bottom, and performing XOR operation on the pixels of the previous position; performing second round diffusion on three channel images of the face image by using the chaotic sequence, and performing XOR operation on pixels of each channel image and pixels at the next position after performing XOR encryption on the pixels of each channel image and the chaotic random number in sequence from bottom to top and from right to left;
and performing row-column scrambling on the face image, firstly performing row scrambling on the face image by using an integer index sequence, performing row-column scrambling on the face image by using the integer index sequence, and fusing the three scrambled channel images to obtain a color encrypted face image.
8. The target detection technology-based face image encryption and decryption method of claim 1, wherein: the step S5 includes: fusing the encrypted face image with a non-face area in a plaintext image, replacing the original non-encrypted face area with the encrypted face area, and combining the encrypted face area and the non-face area into a fused image; and carrying out XOR encryption on the face position by using an integer random sequence to obtain an encrypted face position coordinate, embedding the encrypted face position coordinate into the first four pixels in the R channel of the fusion image, and hiding the face position information to obtain a final ciphertext image.
9. A face image encryption and decryption system based on a target detection technology is characterized by comprising:
the detection module is used for detecting the input plaintext image by using the MTCNN model, acquiring a face region image and face position coordinates, and calculating an average gray value of the face image;
the first generation module is used for setting an initial key, calculating a first group of initial values of the hyperchaotic Chen system according to the initial key and the average gray value of the face image, and iterating the hyperchaotic Chen system to generate a first group of chaotic sequences;
the second generation module is used for calculating by using the average gray value of the face image and the first group of chaotic sequences, updating and acquiring a second group of initial values of the hyperchaotic Chen system, and iterating the hyperchaotic Chen system to generate a second group of chaotic sequences;
the encryption module is used for preprocessing the first group of chaotic sequences and the second group of chaotic sequences, converting the first group of chaotic sequences and the second group of chaotic sequences into integer random sequences and integer index sequences with preset lengths, and performing pixel scrambling, pixel diffusion and row-column scrambling on the face region image by using the integer random sequences to obtain an encrypted face image;
and the fusion output module is used for fusing the encrypted face image and the non-face area in the plaintext image into an image, carrying out XOR encryption on the face position coordinates, and embedding the encrypted face position coordinates into the fused image to obtain a final ciphertext image.
10. Computer device comprising a processor and a memory for storing a program executable by the processor, wherein the processor, when executing the program stored in the memory, implements the method for encrypting and decrypting a face image based on an object detection technique according to any one of claims 1 to 8.
CN202210490733.2A 2022-05-07 2022-05-07 Method, system and equipment for encrypting and decrypting face image based on target detection technology Pending CN115102683A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210490733.2A CN115102683A (en) 2022-05-07 2022-05-07 Method, system and equipment for encrypting and decrypting face image based on target detection technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210490733.2A CN115102683A (en) 2022-05-07 2022-05-07 Method, system and equipment for encrypting and decrypting face image based on target detection technology

Publications (1)

Publication Number Publication Date
CN115102683A true CN115102683A (en) 2022-09-23

Family

ID=83287549

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210490733.2A Pending CN115102683A (en) 2022-05-07 2022-05-07 Method, system and equipment for encrypting and decrypting face image based on target detection technology

Country Status (1)

Country Link
CN (1) CN115102683A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115278181A (en) * 2022-09-27 2022-11-01 中科金勃信(山东)科技有限公司 Image processing method for intelligent security monitoring system
CN116467730A (en) * 2023-06-16 2023-07-21 北京东联世纪科技股份有限公司 Intelligent park digital operation and maintenance management system based on CIM architecture
CN117319569A (en) * 2023-10-23 2023-12-29 长讯通信服务有限公司 Face encryption method based on hyperchaotic system and DNA encryption

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115278181A (en) * 2022-09-27 2022-11-01 中科金勃信(山东)科技有限公司 Image processing method for intelligent security monitoring system
CN115278181B (en) * 2022-09-27 2022-12-20 中科金勃信(山东)科技有限公司 Image processing method for intelligent security monitoring system
CN116467730A (en) * 2023-06-16 2023-07-21 北京东联世纪科技股份有限公司 Intelligent park digital operation and maintenance management system based on CIM architecture
CN116467730B (en) * 2023-06-16 2023-08-15 北京东联世纪科技股份有限公司 Intelligent park digital operation and maintenance management system based on CIM architecture
CN117319569A (en) * 2023-10-23 2023-12-29 长讯通信服务有限公司 Face encryption method based on hyperchaotic system and DNA encryption

Similar Documents

Publication Publication Date Title
Dhawan et al. Analysis of various data security techniques of steganography: A survey
CN115102683A (en) Method, system and equipment for encrypting and decrypting face image based on target detection technology
CN113538203B (en) Image encryption method and device based on novel two-dimensional composite chaotic mapping and SHA-256
CN109800585B (en) Image interpolation space completely reversible separable ciphertext domain information hiding algorithm
Gao et al. EFR-CSTP: Encryption for face recognition based on the chaos and semi-tensor product theory
CN110430036B (en) RGB (Red, Green and blue) color image encryption method based on inverse difference chaotic mapping
CN103226802B (en) Based on the medical image share method of chaos encryption
CN107094072B (en) Mixed chaotic encryption method based on generalized Henon mapping
CN108199828B (en) Method and device for encrypting color picture
Ye et al. PRA-TPE: Perfectly recoverable approximate thumbnail-preserving image encryption
CN111131657B (en) Chaos medical image tamper-proof encryption method based on self-verification matrix
CN108924379B (en) Digital image encryption method
CN115103080B (en) Image encryption method and system based on DNA triploid variation
CN111597568A (en) Image encryption method of high-dimensional fractional order complex system based on distributed time lag
CN116827509A (en) Image encryption method based on five-dimensional conserved hyperchaotic system and bit plane segmentation diffusion
CN116192362A (en) Lyapunov exponent adjustable chaotic system and image encryption and decryption method
Abiega-L’Eglisse et al. A New Fuzzy Vault based Biometric System robust to Brute-Force Attack
CN116055024A (en) Multi-image multi-region-of-interest encryption method based on DNA sequence and chaotic system
CN115408665A (en) Image encryption technology based on chaos theory
Yu et al. A two-stage chaotic encryption algorithm for color face image based on circular diffusion
Al-Laham et al. Digital Image Slicing to Strengthen the Security of LSB Technique of Encrypting Text Messages
CN111756518B (en) Color image encryption method based on memristor hyperchaotic system
Hu et al. Research on encrypted face recognition algorithm based on new combined chaotic map and neural network
CN113992811A (en) Image encryption method based on novel three-dimensional fractional order discrete chaotic mapping
Yan et al. Secret image sharing based on error-correcting codes

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