CN115378574A - Lightweight dynamic image data encryption method and system - Google Patents
Lightweight dynamic image data encryption method and system Download PDFInfo
- Publication number
- CN115378574A CN115378574A CN202210948717.3A CN202210948717A CN115378574A CN 115378574 A CN115378574 A CN 115378574A CN 202210948717 A CN202210948717 A CN 202210948717A CN 115378574 A CN115378574 A CN 115378574A
- Authority
- CN
- China
- Prior art keywords
- image
- chaotic
- sensitive
- target
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 230000000739 chaotic effect Effects 0.000 claims abstract description 119
- 238000012216 screening Methods 0.000 claims abstract description 45
- 230000035945 sensitivity Effects 0.000 claims abstract description 30
- 238000001514 detection method Methods 0.000 claims abstract description 24
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 238000013507 mapping Methods 0.000 claims abstract description 15
- 230000007246 mechanism Effects 0.000 claims abstract description 5
- 230000008569 process Effects 0.000 claims description 29
- 239000011159 matrix material Substances 0.000 claims description 24
- 238000001914 filtration Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 8
- 230000009467 reduction Effects 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000009792 diffusion process Methods 0.000 claims description 5
- 238000013145 classification model Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 239000000203 mixture Substances 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims 1
- 238000000354 decomposition reaction Methods 0.000 claims 1
- 230000008859 change Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
- G06V10/993—Evaluation of the quality of the acquired pattern
-
- 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
- H04L9/002—Countermeasures against attacks on cryptographic mechanisms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/32—Circuits or arrangements for control or supervision between transmitter and receiver or between image input and image output device, e.g. between a still-image camera and its memory or between a still-image camera and a printer device
- H04N1/32101—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title
- H04N1/32144—Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title embedded in the image data, i.e. enclosed or integrated in the image, e.g. watermark, super-imposed logo or stamp
- H04N1/32149—Methods relating to embedding, encoding, decoding, detection or retrieval operations
- H04N1/32267—Methods relating to embedding, encoding, decoding, detection or retrieval operations combined with processing of the image
- H04N1/32272—Encryption or ciphering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses a method and a system for encrypting lightweight dynamic image data, wherein an automatic identification image screening mechanism based on an image quality screening and feature extraction method is used for extracting structural features of an image, and similarity matching is carried out on the extracted features to realize image screening of specific contents; through image target detection and feature comparison, the screened images are subjected to sensitive region identification, the sensitivity level is calculated according to sensitive objects contained in the images, and relevant sensitive regions meeting conditions are segmented and extracted; and scrambling the specific sensitive area by using a pixel space scrambling method based on the chaotic sequence, and then constructing a new chaotic sequence by using dynamic chaotic mapping to diffuse the scrambled image to realize encryption. The method and the system for encrypting the lightweight dynamic image data have the advantages that the lightweight encryption is realized, the safety performance is good, and the covering attack, the differential attack and the statistical attack of the image data can be resisted.
Description
Technical Field
The invention belongs to the technical field of computer image encryption, and particularly relates to a lightweight dynamic image data encryption method and system.
Background
With the progress and development of internet technology, image data plays an increasingly important role in related fields, however, image data often contains some sensitive information contents, which may cause privacy information leakage in transmission and storage processes, especially in some special application scenarios such as medical treatment and finance. At present, image encryption processing is generally used for protecting image information, and sensitive information or customized private information is hidden in an original image so as to prevent the original image from being stolen or information leakage. However, it is generally difficult to securely and efficiently encrypt image data having a large data volume and a two-dimensional structure and high redundancy by an encryption algorithm designed for text data.
Furthermore, the ciphertext used to encrypt the images is only related to the key, and not the plaintext, so they are more vulnerable to select plaintext attacks or known plaintext attacks. The chaotic system has strong sensitivity to initial values and parameters, can generate excellent long-period random sequences, has unpredictability of long-term evolution, and accords with confusion and diffusion rules of password design, so that the chaotic system is often used for designing and using an image encryption algorithm. However, the multi-dimensional chaotic system has the defects of more parameters, complex algorithm structure, difficult realization, high time consumption and the like, and the application of the chaotic system in the rapid image encryption in real-time image processing is severely limited, so that the development of an enhanced chaotic system and a lightweight image encryption method with low computation complexity is very necessary.
Disclosure of Invention
The invention aims to provide a method and a system for encrypting lightweight dynamic image data, which solve the problem that a multi-dimensional chaotic system has the defects of more parameters, complex algorithm structure, difficult realization, high time consumption and the like, and seriously limit the rapid image encryption application of the chaotic system in real-time image processing.
In order to achieve the purpose, the invention provides the following technical scheme: a method and a system for encrypting lightweight dynamic image data comprise the following steps:
the method comprises the following steps: automatic screening of images: extracting structural features of the image based on an automatic image screening mechanism, and performing similarity matching on the extracted features to realize image screening of specific contents;
step two: sensitive object recognition: through image target model detection and feature comparison, image sensitive object identification is carried out on the screened image, sensitivity is calculated according to the sensitive object contained in the image, and relevant sensitive areas meeting conditions are extracted;
step three: dynamic chaotic encryption: scrambling a specific sensitive area by using an area pixel space scrambling method based on a chaotic sequence, then constructing a new chaotic sequence by using dynamic chaotic encryption mapping to spread a scrambled image to realize dynamic chaotic encryption of the image, splicing an encrypted part of the sensitive area and an unencrypted part of a background area, and obtaining an encrypted image for storage or transmission.
Preferably, the method for automatically screening the images specifically comprises the following processes:
(1.1) image quality screening: filtering and denoising the original image, calculating the edge gradient of pixel points, accumulating and summing the pixel points and normalizing the edge gradient to screen out a clear image;
(1.2) similarity matching: extracting structural features of the images meeting the quality requirements through a clustering and classifying algorithm, and screening out the images matched with a specific target from the structural feature vectors based on a multi-metric similarity matching algorithm;
the sensitive object identification specifically comprises the following processes:
(2.1) sensitive target detection: identifying, detecting and classifying specific target objects contained in the image;
(2.2) sensitivity calculation: correspondingly calculating the sensitive target object according to a preset sensitivity value;
(2.3) sensitive area extraction: performing regional image segmentation and extraction on the region of the target object meeting the sensitivity requirement;
the dynamic chaotic encryption comprises the following processes:
(3.1) regional pixel scrambling: and performing preset disorder processing on bytes of the initial image according to the initial chaotic system, and performing dimension reduction on the obtained array by copying the RGB value of each adjacent pixel to obtain a preset disorder bitmap.
(3.2) dynamic chaotic encryption: a new chaotic system is dynamically constructed, iterative diffusion is carried out on the bit image elements after the chaotic processing according to a chaotic mapping sequence, and a ciphertext matrix is obtained;
(3.3) image data stitching: and splicing and integrating the confusion encrypted region image ciphertext matrix and the unprocessed region of the original image to form complete data of the target encrypted image.
Preferably, the image quality screening process specifically includes:
(1.11) firstly, carrying out image filtering and denoising treatment, converting an original image into filtering and denoising treatment, filtering noise and smoothing the image, and removing irrelevant details in the image;
(1.12) then, calculating the edge gradient of the image, respectively calculating the edge gradient in the neighborhood of each pixel point, carrying out weighted summation on the edge gradient in the neighborhood of each pixel point, thereby calculating the edge gradient sum of each pixel point, accumulating the edge gradient sum of each pixel point, dividing by the number of the pixel points to obtain a normalized edge gradient, and screening out a clear image according to the edge gradient value obtained after normalization.
Preferably, the similarity matching includes feature clustering and feature classification,
the feature clustering specifically includes the following:
(1.201) extracting image features of an image to obtain sample image features, and extracting structural features of the image features by using a feature clustering model to obtain at least one image structural feature;
(1.202) clustering the image structural features based on the structural features to obtain at least one clustering result of the structural features;
(1.203) optimizing the preset feature clustering model according to the clustering result until the preset model is converged to obtain a feature clustering model and using the feature clustering model for screening structural features of the target image;
the feature classification specifically includes:
(1.204) selecting a plurality of image samples which can be randomly replaced from the image, marking a characteristic class label as a training sample, selecting the existing convolutional neural network model for parameter adjustment and optimization, wherein the convolutional neural network model and the network model for extracting the characteristics need to keep different model structures and training data;
(1.205) identifying the target image features by using a feature classification model to obtain a structural feature model and a class confidence coefficient thereof, and screening out the features as irrelevant samples if the confidence coefficient of a certain sample on the class is low;
the structural feature extraction comprises the following steps:
(1.21) first, defining structure information as attributes reflecting the structure of an object in a scene independent of brightness and contrast from the perspective of image composition, using a mean value as an estimate of brightness, a standard deviation as an estimate of contrast, and a covariance as a measure of the degree of similarity of the structure;
(1.22) secondly, partitioning the image into blocks by utilizing a sliding window, calculating each step based on pixels in the window, corresponding to the structural similarity of the blocks, and finally taking the average value as the structural similarity measurement of the two images.
Preferably, the specific content of the sensitive target detection is as follows:
according to a preset detection sensitive object list, automatically classifying and identifying target objects contained in image contents to acquire corresponding category information and position information;
extracting features according to sensitive object training images, and using the obtained feature vectors for feature library training of target image recognition to obtain a target detection model;
the sensitivity calculation method comprises the following steps:
according to the sensitive target detection identification information, calculating the sensitivity of the object in the current image, wherein the sensitivity depends on the application scene of the image, the target preset value and the semantic relationship among the objects in the image scene; the target preset value can be used for defining the initial sensitivity of a given target object in advance according to the general understanding of the image;
the process of extracting the sensitive area comprises the following steps:
and carrying out image region division based on a target detection model on the original image according to the identified sensitive object, and dividing the image into a plurality of mutually disjoint regions according to the characteristics of gray scale, color, spatial texture, geometric shape and the like, wherein the example division and the scene division are included so as to obtain the target sensitive object region image.
Preferably, the pixel spatial scrambling specifically includes: constructing chaotic mapping based on an initial chaotic system, generating a chaotic sequence of pseudo-random numbers, changing the spatial position of pixels in a target area by performing finite step length elementary matrix conversion on an image matrix, and changing an original area image into a disordered and invisible new area image;
the chaotic encryption comprises the following steps: reading in a sensitive area picture to be processed, entering a chaotic sequence through an encryption key, and designing an encryption algorithm by adopting a chaotic system to realize the encryption purpose; and generating a chaotic key sequence related to the characteristics of the plaintext image by adopting a chaotic system and a logic diagram, replacing the pixel value of the target area, realizing the purpose of disturbing the pixel position, and finally diffusing the image to obtain the encrypted image of the target area.
Preferably, the process of constructing the new dynamic chaotic encryption system is as follows: one chaotic map is used for controlling the parameters of the other chaotic system to form a new chaotic system, and the mathematical expression is as follows:
x n+1 ＝G(u n+1 ，x n )
u n+1 ＝H(y n+1 )
y n+1 ＝F(v，y n )
where F (x) represents the control chaotic map, G (x) represents the seed chaotic map, and H (x) represents the transfer relationship function used to map the output of F (x) into the parameter range of G (x).
Preferably, the image data stitching process includes:
the method comprises the steps of decomposing an encrypted area image in multiple channels to obtain an encrypted characteristic matrix of each channel of the encrypted area image, obtaining a characteristic vector of each channel of the encrypted area image, combining the characteristic vectors with an unencrypted area characteristic matrix to generate an image matrix with the same size as an original image, and generating a target encrypted image based on the combined encrypted matrix for storage or transmission.
The system used by the method comprises:
the automatic image screening and matching module is used for screening and matching the input images according to conditions;
the image sensitive object identification module is used for carrying out sensitive object identification on image contents;
and the image dynamic chaotic encryption module is used for encrypting the image sensitive area.
The invention has the technical effects and advantages that: an automatic identification image screening mechanism based on the image quality screening and feature extraction method extracts structural features of the image, and performs similarity matching on the extracted features to realize image screening of specific contents; through image target detection and feature comparison, the screened images are subjected to sensitive region identification, the sensitivity level is calculated according to sensitive objects contained in the images, and relevant sensitive regions meeting conditions are segmented and extracted; the method comprises the steps of scrambling a specific sensitive area by using a pixel space scrambling method based on a chaotic sequence, then constructing a new chaotic sequence by using dynamic chaotic mapping to diffuse a scrambled image to realize encryption, splicing an encrypted part of the sensitive area and an unencrypted part of a background area to obtain an encrypted image for storage or transmission, realizing light encryption, having good safety performance, and resisting covering attack, differential attack and statistical attack of image data.
Drawings
FIG. 1 is a schematic diagram of a system provided by the present invention;
FIG. 2 is a schematic diagram of an image screening process provided by the present invention;
FIG. 3 is a schematic diagram illustrating a process of identifying an image sensitive region according to the present invention;
FIG. 4 is a schematic diagram illustrating an encryption process for an image sensitive area according to the present invention;
FIG. 5 is a graph of a gray scale frequency contrast histogram of an image encrypted color channel provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
The invention provides a method and a system for encrypting lightweight dynamic image data as shown in figures 1-5, wherein the method and the system for encrypting the lightweight dynamic image data comprise the following steps:
the method comprises the following steps: automatic screening of images: performing structural feature extraction on the image based on an image automatic screening mechanism, and performing similarity matching on the extracted features to realize image screening of specific contents;
step two: sensitive object recognition: through image target model detection and feature comparison, image sensitive object identification is carried out on the screened images, sensitivity is calculated according to the sensitive objects contained in the images, and relevant sensitive areas meeting conditions are extracted;
step three: dynamic chaotic encryption: scrambling a specific sensitive area by using an area pixel space scrambling method based on a chaotic sequence, then constructing a new chaotic sequence by using dynamic chaotic encryption mapping to spread a scrambled image to realize dynamic chaotic encryption of the image, splicing an encrypted part of the sensitive area and an unencrypted part of a background area, and obtaining an encrypted image for storage or transmission.
Specifically, the method for automatically screening the image specifically comprises the following processes:
(1.1) image quality screening: filtering and denoising the original image, calculating the edge gradient of pixel points, accumulating and summing the pixel points, and normalizing the edge gradient to screen out a clear image;
(1.2) similarity matching: extracting structural features of the images meeting the quality requirements through a clustering and classifying algorithm, and screening out the images matched with the specific targets from the structural feature vectors based on a multi-metric similarity matching algorithm;
the sensitive object identification specifically comprises the following processes:
(2.1) sensitive target detection: identifying, detecting and classifying specific target objects contained in the image;
(2.2) sensitivity calculation: correspondingly calculating the sensitive target object according to a preset sensitivity value;
(2.3) sensitive area extraction: performing regional image segmentation and extraction on the region of the target object meeting the sensitivity requirement;
the dynamic chaotic encryption comprises the following processes:
(3.1) regional pixel scrambling: and performing preset disorder processing on bytes of the initial image according to the initial chaotic system, and performing dimension reduction on the obtained array by copying the RGB value of each adjacent pixel to obtain a preset disorder bitmap.
(3.2) dynamic chaotic encryption: a new chaotic system is dynamically constructed, iterative diffusion is carried out on the bit image elements after the chaotic processing according to a chaotic mapping sequence, and a ciphertext matrix is obtained;
(3.3) image data splicing: and splicing and integrating the confusion encrypted regional image ciphertext matrix and the unprocessed region of the original image to form complete data of the target encrypted image.
Specifically, the image quality screening process specifically includes:
(1.11) carrying out image filtering and denoising, converting an original image to carry out filtering and denoising, filtering noise and smoothing the image, and removing irrelevant details in the image;
(1.12) calculating the edge gradient of the image, respectively calculating the edge gradient in the neighborhood of each pixel point, weighting and summing the edge gradient in the neighborhood of each pixel point, thereby calculating the edge gradient sum of each pixel point, accumulating the edge gradient sum of each pixel point, dividing the edge gradient sum by the number of the pixel points to obtain a normalized edge gradient, and screening out a clear image according to the edge gradient value obtained after normalization.
Referring to fig. 2, the process of filtering and denoising the image specifically includes: the original image is converted to be subjected to filtering and noise reduction processing, space proximity and pixel value similarity of the image are combined based on nonlinear bilateral filtering, and space proximity information and color similarity information are considered at the same time, so that noise is filtered, the image is smoothed, edge storage is achieved, and irrelevant details in the image are removed. Optimizing each weight value calculated by the spatial proximity of each point to the central point, optimizing the weight value into the product of the weight value calculated by the spatial proximity and the weight value calculated by the pixel value similarity, and performing convolution operation on the optimized weight value and the image.
The process of image edge gradient is specifically as follows: the calculation process of the gradient value between the image edge pixel points is used for representing the edge information of the image, can reflect the speed of the change of the image pixels and can indicate the definition of the image to a certain degree; respectively calculating the edge gradient in the neighborhood of each pixel point for the pixel points of the image after the noise reduction treatment, accumulating the edge gradient sum of each pixel point, and dividing the edge gradient sum by the number of the pixel points to obtain a normalized edge gradient; and (4) screening out a clear image according to the edge gradient value obtained after normalization, wherein the gradient of the image f (x, y) at a certain point can be represented as follows:
wherein, G x And G y Represented as a gradient chaotic sequence at a certain point.
Specifically, the similarity matching includes feature clustering and feature classification,
the feature clustering specifically includes the following:
(1.201) extracting image features of the image to obtain sample image features, and extracting structural features of the image features by using a feature clustering model to obtain at least one image structural feature;
(1.202) clustering the image structural features based on the structural features to obtain at least one clustering result of the structural features;
(1.203) optimizing the preset feature clustering model according to the clustering result until the preset model is converged to obtain a feature clustering model and using the feature clustering model for structural feature screening of the target image;
the feature classification specifically includes:
(1.204) selecting a plurality of image samples which can be randomly replaced from the image, marking a characteristic class label as a training sample, selecting the existing convolutional neural network model for parameter adjustment and optimization, wherein the convolutional neural network model and the network model for extracting the characteristics need to keep different model structures and training data;
(1.205) identifying the target image features by using a feature classification model to obtain a structural feature model and a class confidence coefficient thereof, and screening out the features as irrelevant samples if the confidence coefficient of a certain sample on the class is low;
referring to fig. 1, structural feature extraction is performed on the image meeting the quality requirement through a clustering and classification algorithm. Firstly, extracting image features of the image to obtain sample image features, extracting structural features of the image features by using a feature clustering model, clustering the image structural features, adjusting parameters of a preset feature clustering model according to a clustering result until the preset model is converged to obtain the feature clustering model and using the feature clustering model for screening the structural features of the target image. The classification method comprises the steps of selecting a plurality of image samples from images which can be randomly replaced, marking feature class labels as training samples, selecting the existing convolutional neural network model for parameter adjustment and optimization, and identifying target image features by using a feature classification model to obtain a structural feature model and class confidence coefficients thereof.
The structural feature extraction comprises the following steps:
(1.21) defining structure information from the perspective of image composition as attributes reflecting the structure of objects in a scene independent of brightness and contrast, using a mean value as an estimate of brightness, a standard deviation as an estimate of contrast, and a covariance as a measure of the degree of similarity of the structure;
and (1.22) partitioning the image into blocks by using a sliding window, calculating each step based on pixels in the window, corresponding to the structural similarity of the blocks, and finally taking the average value as the structural similarity measurement of the two images.
Referring to fig. 1, an image matched with a specific target is screened out from the structural feature vector based on a multi-metric similarity matching algorithm. The structural similarity defines structural information as attributes which are independent of brightness and contrast and reflect the structure of an object in a scene from the angle of image composition, and the value range [0,1] represents that the image distortion is smaller when the value is larger. Modeling is a combination of three different factors of brightness, contrast and structure, with the mean as the brightness estimate, the standard deviation as the contrast estimate and the covariance as a measure of the structural similarity. The distortion condition of the image is changed in space, the image is partitioned by utilizing a sliding window, the total number of the partitions is N, and each step is calculated based on pixels in the window. Considering the influence of the window shape on the blocks, a Gaussian weighting function with the standard deviation of 1.5 is used as a weighting window, and the mean value, the variance and the covariance of each window are calculated by adopting Gaussian weighting; and then calculating the structural similarity of the corresponding blocks, and finally taking the average value as the structural similarity measurement of the two images.
Specifically, the specific content of the sensitive target detection is as follows:
according to a preset detection sensitive object list, automatically classifying and identifying target objects contained in image contents to acquire corresponding category information and position information;
extracting features according to sensitive object training images, and using the obtained feature vectors for feature library training of target image recognition to obtain a target detection model;
the sensitivity calculation method comprises the following steps:
according to the sensitive target detection identification information, calculating the sensitivity of the object in the current image, wherein the sensitivity depends on the application scene of the image, the target preset value and the semantic relation among all objects in the image scene; the target preset value can be used for defining the initial sensitivity of a given target object in advance according to the general understanding of the image;
the process of extracting the sensitive area comprises the following steps:
and carrying out image region division based on a target detection model on the original image according to the identified sensitive object, and dividing the image into a plurality of mutually disjoint regions according to the characteristics of gray scale, color, spatial texture, geometric shape and the like, wherein the example division and the scene division are included so as to obtain the target sensitive object region image.
Wherein, the target object sensitivity calculation gives a calculation formula of the image context sensitivity on the basis of experiment and analysis:
SD r ＝S r *W s +C r *W c +A r *W A +L r *W L ；
wherein, W s +W c +W A +W L =1, area profile feature of identified image content is S r The generic type is characterized by C r Area ratio of A r The position distance characteristic is L r The initial default weights corresponding to the terms are W S ，W C ，W A ，W L 。
Specifically, the pixel spatial scrambling specifically includes: constructing chaotic mapping based on an initial chaotic system, generating a chaotic sequence of pseudo-random numbers, changing the spatial position of pixels in a target area by performing finite step length elementary matrix conversion on an image matrix, and changing an original area image into a disordered and invisible new area image;
the chaotic encryption comprises the following steps: reading in a sensitive area picture to be processed, entering a chaotic sequence through an encryption key, and designing an encryption algorithm by adopting a chaotic system to realize the encryption purpose; and generating a chaotic key sequence related to the characteristics of the plaintext image by adopting a chaotic system and a logic diagram, replacing the pixel value of the target area, realizing the pixel position disorder, and finally diffusing the image to obtain the encrypted image of the target area.
Specifically, the process of constructing the new dynamic chaotic encryption system is as follows: one chaotic map is used for controlling the parameters of the other chaotic system to form a new chaotic system, and the mathematical expression is as follows:
x n+1 ＝G(u n+1 ，x n )
u n+1 ＝H(y n+1 )
y n+1 ＝F(v，y n )
where F (x) represents the control chaotic map, G (x) represents the seed chaotic map, and H (x) represents the transfer function, which is used to map the output of F (x) into the parameter range of G (x).
With reference to fig. 4:
regional pixel scrambling: and constructing chaotic mapping based on the initial chaotic system, generating a chaotic sequence of pseudo random numbers, and performing preset scrambling processing on bytes of the initial image. The order of odd rows and columns of the initial image is reversed, then the RGB values of the rows and columns are rotated, and the resulting 3-dimensional array is transformed into a 2-dimensional array by copying the R, G, and B values of each adjacent pixel, resulting in a preset bitmap of size M x 3N.
Dynamic chaotic encryption: reading in a sensitive area picture to be processed, dynamically constructing a new chaotic system, and performing iterative diffusion on bit image pixels subjected to chaotic processing according to a chaotic mapping sequence to achieve the aim of encryption. In the process of dynamically constructing the new chaotic system, the Chirikov chaotic mapping is used for controlling the parameters of the Tent chaotic system to form the new chaotic system, and the Chirikov chaotic system expression is as follows:
the equation of the Tent chaotic system is defined as:
calculating the sum of pixel values of the image and recording the sum as s by using the digital image which is pre-scrambled by M multiplied by 3N, and calculating the initial iteration number k of the chaotic system by using the following formula, namely:
k＝s mod 10 3 +10 3
iterating the Chirikov chaotic system M multiplied by 3N-1 times to obtain a pseudo-random number t1, and performing the following processing on the pseudo-random number t 1:
t＝mod((t 1 *10 3 )，2)+1
and according to the t obtained in the step, the t is used as a control parameter mu and an iteration number k of the Tent chaotic system, and the Tent chaotic system is iterated from k times to obtain a chaotic sequence with the length of M multiplied by 3N and is sequenced. And scrambling the pixels of the original image by using the index position sequence to obtain a scrambled image C'.
And inputting the secret keys G0 and H0 to iterate the chaotic mapping system, and intercepting chaotic sequences G and H with the length of M multiplied by 3N after iteration. A new chaotic sequence F is constructed by two chaotic sequences according to the following formula, so that the chaotic sequence F has better pseudo-randomness.
Generating a chaotic key sequence related to the characteristics of a plaintext image by adopting a chaotic system and a logic diagram, carrying out exclusive or operation on the obtained chaotic sequence F and a scrambled image C', replacing a pixel value of a target area, realizing the position of a scrambled pixel, and finally diffusing the image to obtain an encrypted image of the target area:
C＝F⊕C’。
specifically, the image data stitching process includes:
the method comprises the steps of decomposing an encrypted area image in multiple channels to obtain an encrypted feature matrix of each channel of the encrypted area image, obtaining a feature vector of each channel of the encrypted area image, combining the feature vector with an unencrypted area feature matrix to generate an image matrix with the same original image size, and generating a target encrypted image based on the combined encrypted matrix for storage or transmission.
The system used by the method comprises:
the automatic image screening and matching module is used for screening and matching the input images according to conditions;
the image sensitive object identification module is used for carrying out sensitive object identification on image contents;
and the image dynamic chaotic encryption module is used for encrypting the image sensitive area.
Referring to fig. 5, the Lena image is used as a sample image, the size of the original image is 256 × 256, and the histograms of the three channels (a), (B), and (c) in the original images are shown, so that the pixels of the gray histogram of the plaintext image are not uniformly distributed and have large fluctuation; in the graphs (d), (e) and (f), histograms of three channels of the encrypted image are obtained, the encryption areas of the three graphs are very close to each other, namely, the occurrence frequency of each gray value is basically the same, the histogram distribution of pixels is relatively consistent, the information is converged, the correlation among the pixels of the plaintext image is broken, and thus an attacker cannot obtain the related information of the image sensitive area. In addition, each channel of the encrypted picture has good randomness and can resist statistical attack, and the correlation of horizontal, vertical and diagonal adjacent elements of each channel of the encrypted picture is very close to 0, so that the correlation of adjacent pixels is greatly weakened.
The Mean Square Error (MSE) characterizes the difference between the original image and the encrypted image, and when the MSE is 0, it means that the two images are equal. Through analysis, the picture can be decrypted only when the value range of the key parameter enters a small interval, so that the encrypted picture can be effectively prevented from being decrypted by using the overlay attack. With the increase of randomness, the mean square error of the decrypted image is also increased all the time, and the increasing speed is in a slowing trend. Meanwhile, the peak signal-to-noise ratio of the decrypted image is also reduced all the time, and the reduction speed is in a slowing trend.
The pixel change rate indicates that when any pixel value in the plaintext image slightly changes or the key slightly changes, the information of the ciphertext image can be greatly changed, and the closer to an ideal value, the better the sensitivity of the ciphertext to the plaintext is; the normalized average change strength shows that the more the values of the two indexes are close to the ideal value, the more sensitive the fine change of the plaintext image is, and the stronger the anti-attack capability is. And a better pixel change rate and normalized average change intensity are obtained through calculation, and differential attack is better resisted.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.
Claims (9)
1. A method for encrypting lightweight dynamic image data, comprising:
the method comprises the following steps: automatic screening of images: performing structural feature extraction on the image based on an image automatic screening mechanism, and performing similarity matching on the extracted features to realize image screening of specific contents;
step two: sensitive object recognition: through image target model detection and feature comparison, image sensitive object identification is carried out on the screened images, sensitivity is calculated according to the sensitive objects contained in the images, and relevant sensitive areas meeting conditions are extracted;
step three: dynamic chaotic encryption: scrambling a specific sensitive area by using an area pixel space scrambling method based on a chaotic sequence, then constructing a new chaotic sequence by using dynamic chaotic encryption mapping to spread a scrambled image to realize dynamic chaotic encryption of the image, splicing an encrypted part of the sensitive area and an unencrypted part of a background area, and obtaining an encrypted image for storage or transmission.
2. The method for encrypting the lightweight dynamic image data according to claim 1, wherein the method for automatically screening the image specifically comprises the following processes:
(1.1) image quality screening: filtering and denoising the original image, calculating the edge gradient of pixel points, accumulating and summing the pixel points, and normalizing the edge gradient to screen out a clear image;
(1.2) similarity matching: extracting structural features of the images meeting the quality requirements through a clustering and classifying algorithm, and screening out the images matched with the specific targets from the structural feature vectors based on a multi-metric similarity matching algorithm;
the sensitive object identification specifically comprises the following processes:
(2.1) sensitive target detection: identifying, detecting and classifying specific target objects contained in the image;
(2.2) sensitivity calculation: correspondingly calculating the sensitive target object according to a preset sensitivity value;
(2.3) sensitive area extraction: performing regional image segmentation and extraction on the region of the target object meeting the sensitivity requirement;
the dynamic chaotic encryption comprises the following processes:
(3.1) regional pixel scrambling: and performing preset disorder processing on bytes of the initial image according to the initial chaotic system, and performing dimension reduction on the obtained array by copying the RGB value of each adjacent pixel to obtain a preset disorder bitmap.
(3.2) dynamic chaotic encryption: a new chaotic system is dynamically constructed, iterative diffusion is carried out on the bit image pixels after the chaotic processing according to a chaotic mapping sequence, and a ciphertext matrix is obtained;
(3.3) image data stitching: and splicing and integrating the confusion encrypted regional image ciphertext matrix and the unprocessed region of the original image to form complete data of the target encrypted image.
3. The method for encrypting the lightweight dynamic image data according to claim 1, wherein the image quality screening process specifically comprises:
(1.11) carrying out image filtering and noise reduction treatment, converting an original image into filtering and noise reduction treatment, filtering noise and smoothing the image, and removing irrelevant details in the image;
(1.12) calculating the edge gradient of the image, respectively calculating the edge gradient in the neighborhood of each pixel point, weighting and summing the edge gradient in the neighborhood of each pixel point, thereby calculating the edge gradient sum of each pixel point, accumulating the edge gradient sum of each pixel point, dividing the edge gradient sum by the number of the pixel points to obtain a normalized edge gradient, and screening out a clear image according to the edge gradient value obtained after normalization.
4. The method of claim 2, wherein the similarity matching includes feature clustering and feature classification,
the feature clustering specifically includes the following:
(1.201) extracting image features of an image to obtain sample image features, and extracting structural features of the image features by using a feature clustering model to obtain at least one image structural feature;
(1.202) clustering the image structural features based on the structural features to obtain at least one clustering result of the structural features;
(1.203) optimizing a preset feature clustering model according to a clustering result until the preset model is converged to obtain a feature clustering model and using the feature clustering model for screening structural features of the target image;
the feature classification specifically includes:
(1.204) selecting a plurality of image samples which can be randomly replaced from the image, marking a characteristic class label as a training sample, selecting the existing convolutional neural network model for parameter adjustment and optimization, wherein the convolutional neural network model and the network model for extracting the characteristics need to keep different model structures and training data;
(1.205) identifying the target image features by using a feature classification model to obtain a structural feature model and a class confidence coefficient thereof, and screening out the features as irrelevant samples if the confidence coefficient of a certain sample on the class is low;
the structural feature extraction comprises the following steps:
(1.21) defining structure information from the perspective of image composition as attributes reflecting the structure of objects in a scene independent of brightness and contrast, using a mean value as an estimate of brightness, a standard deviation as an estimate of contrast, and a covariance as a measure of the degree of similarity of the structure;
and (1.22) partitioning the image into blocks by using a sliding window, calculating each step based on pixels in the window, corresponding to the structural similarity of the blocks, and finally taking the average value as the structural similarity measurement of the two images.
5. The method for encrypting the lightweight dynamic image data according to claim 2, wherein the specific contents of the sensitive object detection are as follows:
according to a preset detection sensitive object list, automatically classifying and identifying target objects contained in image contents to acquire corresponding category information and position information;
extracting features according to sensitive object training images by target detection and identification, and using the obtained feature vectors for feature library training of target image identification to obtain a target detection model;
the sensitivity calculation method comprises the following steps:
according to the sensitive target detection identification information, calculating the sensitivity of the object in the current image, wherein the sensitivity depends on the application scene of the image, the target preset value and the semantic relationship among all objects in the image scene; the target preset value can be used for defining the initial sensitivity of a given target object in advance according to the general understanding of the image;
the process of the sensitive area extraction is as follows:
and carrying out image region division based on a target detection model on the original image according to the identified sensitive object, and dividing the image into a plurality of mutually disjoint regions according to the characteristics of gray scale, color, spatial texture, geometric shape and the like, wherein the example division and the scene division are included so as to obtain the target sensitive object region image.
6. The method according to claim 3, wherein the pixel space scrambling specifically comprises: constructing chaotic mapping based on an initial chaotic system, generating a chaotic sequence of pseudo-random numbers, changing the spatial position of pixels in a target area by performing finite step length elementary matrix conversion on an image matrix, and changing an original area image into a chaotic and disordered invisible new area image;
the chaotic encryption comprises the following steps: reading in a sensitive area picture to be processed, entering a chaotic sequence through an encryption key, and designing an encryption algorithm by adopting a chaotic system to realize the encryption purpose; and generating a chaotic key sequence related to the characteristics of the plaintext image by adopting a chaotic system and a logic diagram, replacing the pixel value of the target area, realizing the pixel position disorder, and finally diffusing the image to obtain the encrypted image of the target area.
7. The method for encrypting the lightweight dynamic image data according to claim 2, wherein the construction process of the dynamic chaotic encryption system is as follows: one chaotic map is used for controlling the parameters of the other chaotic system to form a new chaotic system, and the mathematical expression is as follows:
x n+1 ＝G(u n+1 ，x n )
u n+1 ＝H(y n+1 )
y n+1 ＝F(v，y n )；
where F (x) represents the control chaotic map, G (x) represents the seed chaotic map, and H (x) represents the transfer function, which is used to map the output of F (x) into the parameter range of G (x).
8. The method for encrypting the lightweight dynamic image data according to claim 2, wherein the image data splicing process comprises:
carrying out multi-channel decomposition on the encrypted area image to obtain an encrypted feature matrix of each channel of the encrypted area image, obtaining a feature vector of each channel of the encrypted area image, merging the feature vectors with the feature matrix of the unencrypted area to generate an image matrix with the same size as an original image, and generating a target encrypted image based on the merged encrypted matrix for storage or transmission.
9. A system for a lightweight dynamic image data encryption method according to any one of claims 1 to 8, comprising:
the automatic image screening and matching module is used for screening and matching the input images according to conditions;
the image sensitive object identification module is used for carrying out sensitive object identification on image contents;
and the image dynamic chaotic encryption module is used for encrypting the image sensitive area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210948717.3A CN115378574B (en) | 2022-08-09 | 2022-08-09 | Lightweight dynamic image data encryption method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210948717.3A CN115378574B (en) | 2022-08-09 | 2022-08-09 | Lightweight dynamic image data encryption method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115378574A true CN115378574A (en) | 2022-11-22 |
| CN115378574B CN115378574B (en) | 2023-12-19 |
Family
ID=84063568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210948717.3A Active CN115378574B (en) | 2022-08-09 | 2022-08-09 | Lightweight dynamic image data encryption method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115378574B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116226471A (en) * | 2023-05-10 | 2023-06-06 | 济宁蜗牛软件科技有限公司 | Data storage method for homeland resource planning |
| CN116431846A (en) * | 2023-06-14 | 2023-07-14 | 泰山学院 | Student sensitive information storage system and method |
| CN116451276A (en) * | 2023-06-15 | 2023-07-18 | 杭州海康威视数字技术股份有限公司 | Image processing method, device, equipment and system |
| CN116566585A (en) * | 2023-07-10 | 2023-08-08 | 中国科学院东北地理与农业生态研究所 | Informationized intelligent storage method |
| CN117278692A (en) * | 2023-11-16 | 2023-12-22 | 邦盛医疗装备（天津）股份有限公司 | Desensitization protection method for monitoring data of medical detection vehicle patients |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108650434A (en) * | 2018-05-08 | 2018-10-12 | 吉林大学 | A kind of method of image encryption |
| CN109977686A (en) * | 2019-04-01 | 2019-07-05 | 桂林电子科技大学 | A kind of image encryption method and image processing equipment based on Composite Chaotic System |
| CN111783116A (en) * | 2020-06-29 | 2020-10-16 | 南通职业大学 | Lightweight hyperchaotic rapid image encryption algorithm |
| WO2021227349A1 (en) * | 2020-05-11 | 2021-11-18 | 华南理工大学 | Front-end facial image encryption and recognition method for biometric privacy protection |
-
2022
- 2022-08-09 CN CN202210948717.3A patent/CN115378574B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108650434A (en) * | 2018-05-08 | 2018-10-12 | 吉林大学 | A kind of method of image encryption |
| CN109977686A (en) * | 2019-04-01 | 2019-07-05 | 桂林电子科技大学 | A kind of image encryption method and image processing equipment based on Composite Chaotic System |
| WO2021227349A1 (en) * | 2020-05-11 | 2021-11-18 | 华南理工大学 | Front-end facial image encryption and recognition method for biometric privacy protection |
| CN111783116A (en) * | 2020-06-29 | 2020-10-16 | 南通职业大学 | Lightweight hyperchaotic rapid image encryption algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 刘进;孙婧;徐正全;顾鑫;: "基于目标的图像轻量级加密", 华中科技大学学报(自然科学版), no. 06 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116226471A (en) * | 2023-05-10 | 2023-06-06 | 济宁蜗牛软件科技有限公司 | Data storage method for homeland resource planning |
| CN116431846A (en) * | 2023-06-14 | 2023-07-14 | 泰山学院 | Student sensitive information storage system and method |
| CN116431846B (en) * | 2023-06-14 | 2023-08-18 | 泰山学院 | Student sensitive information storage system and method |
| CN116451276A (en) * | 2023-06-15 | 2023-07-18 | 杭州海康威视数字技术股份有限公司 | Image processing method, device, equipment and system |
| CN116451276B (en) * | 2023-06-15 | 2023-09-26 | 杭州海康威视数字技术股份有限公司 | Image processing method, device, equipment and system |
| CN116566585A (en) * | 2023-07-10 | 2023-08-08 | 中国科学院东北地理与农业生态研究所 | Informationized intelligent storage method |
| CN116566585B (en) * | 2023-07-10 | 2023-09-05 | 中国科学院东北地理与农业生态研究所 | Informationized intelligent storage method |
| CN117278692A (en) * | 2023-11-16 | 2023-12-22 | 邦盛医疗装备（天津）股份有限公司 | Desensitization protection method for monitoring data of medical detection vehicle patients |
| CN117278692B (en) * | 2023-11-16 | 2024-02-13 | 邦盛医疗装备（天津）股份有限公司 | Desensitization protection method for monitoring data of medical detection vehicle patients |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115378574B (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Al-Dmour et al. | A steganography embedding method based on edge identification and XOR coding | |
| CN115378574B (en) | Lightweight dynamic image data encryption method and system | |
| Balasamy et al. | A fuzzy based ROI selection for encryption and watermarking in medical image using DWT and SVD | |
| Cheema et al. | A novel optimized semi-blind scheme for color image watermarking | |
| Laishram et al. | A novel minimal distortion-based edge adaptive image steganography scheme using local complexity: (BEASS) | |
| US7587063B2 (en) | Asymmetric subspace watermarking | |
| Théophile et al. | Fuzzy logic-based steganographic scheme for high payload capacity with high imperceptibility | |
| Xie et al. | A new cost function for spatial image steganography based on 2d-ssa and wmf | |
| Meenakshi et al. | A hybrid matrix factorization technique to free the watermarking scheme from false positive and negative problems | |
| Singh et al. | From classical to soft computing based watermarking techniques: A comprehensive review | |
| Zhang et al. | Exposing unseen GAN-generated image using unsupervised domain adaptation | |
| Liu et al. | Making DeepFakes more spurious: evading deep face forgery detection via trace removal attack | |
| Saeed et al. | An accurate texture complexity estimation for quality-enhanced and secure image steganography | |
| Mehrish et al. | Joint spatial and discrete cosine transform domain-based counter forensics for adaptive contrast enhancement | |
| CN114998080A (en) | Face tamper-proof watermark generation method, tamper detection method and attribute detection method | |
| Liu et al. | A robust approach of watermarking in contourlet domain based on probabilistic neural network | |
| Wagdarikar et al. | Design and development of a multiobjective cost function for robust video watermarking using wavelet transform | |
| Shankar et al. | Random embedded calibrated statistical blind steganalysis using cross validated support vector machine and support vector machine with particle swarm optimization | |
| Pichardo-Méndez et al. | LSB pseudorandom algorithm for image steganography using skew tent map | |
| Kumar et al. | Robust approach of video steganography using combined keypoints detection algorithm against geometrical and signal processing attacks | |
| Fadoua et al. | Medical video watermarking scheme for telemedicine applications | |
| Ouyang et al. | A semi-fragile reversible watermarking method based on qdft and tamper ranking | |
| Rezaei et al. | Low distortion and adaptive image steganography by enhancing DBSCAN, Sobel operator, and XOR coding | |
| Li et al. | Perceptual hashing for color images | |
| Wang | An efficient multiple-bit reversible data hiding scheme without shifting |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |