CN103632375A - Image scrambling evaluation method and image scrambling evaluation device - Google Patents
Image scrambling evaluation method and image scrambling evaluation device Download PDFInfo
- Publication number
- CN103632375A CN103632375A CN201310669497.1A CN201310669497A CN103632375A CN 103632375 A CN103632375 A CN 103632375A CN 201310669497 A CN201310669497 A CN 201310669497A CN 103632375 A CN103632375 A CN 103632375A
- Authority
- CN
- China
- Prior art keywords
- image
- scramble
- width
- original image
- bitmap images
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 30
- 238000003062 neural network model Methods 0.000 claims abstract description 43
- 238000000605 extraction Methods 0.000 claims abstract description 39
- 238000006243 chemical reaction Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 abstract description 2
- 230000001054 cortical effect Effects 0.000 abstract 2
- 238000000034 method Methods 0.000 description 19
- 230000008569 process Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 9
- 210000002569 neuron Anatomy 0.000 description 6
- 230000009466 transformation Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses an image scrambling evaluation method and an image scrambling evaluation device, and belongs to the field of digital image processing. The image scrambling evaluation method includes respectively performing bitwise layering to the original image and at least one scrambling image to acquire a bitmap image of the original image and a bitmap image of the scrambling image, performing feature extraction to the bitmap image of the original image and the bitmap image of the scrambling image respectively according to an intersecting cortical neural network model to acquire a structural feature sequence of the original image and a structural feature sequence of the scrambling image, and calculating according to the structural feature sequence of the original image and the structural feature sequence of the scrambling image so as to acquire the scrambling degree of the scrambling image. By the steps of performing the bitwise layering to the original image and the scrambling images and performing the feature extraction according to the intersecting cortical neural network model, the structural feature information of the images is extracted directly and the scrambling degree evaluation is implemented effectively.
Description
Technical field
The present invention relates to digital image processing field, particularly a kind of image scrambling evaluation method and device.
Background technology
Along with fast development and the widespread use of computer networking technology, by network, carry out data transmission and become very convenient and quick.Meanwhile, data security also receives increasing concern.Image scrambling is a kind of cryptographic means to view data, and information that can hidden image by this technology, to guarantee the security of view data in Internet Transmission.For scramble image, scramble degree is higher, and the cipher round results of view data is better, therefore, the effective evaluation of scramble degree is had to important theoretical and practical significance in information encryption.
In prior art, adopt Pulse-coupled Neural Network Model to evaluate scramble image, by Pulse-coupled Neural Network Model, extract the characteristic sequence of scramble image, compare with the characteristic sequence of the original image not converting through scramble, obtain the scramble degree of scramble image.
In realizing process of the present invention, inventor finds that prior art at least exists following problem:
In prior art, when Pulse-coupled Neural Network Model is evaluated scramble image, the half-tone information of the characteristic sequence extracting based on image, scramble conversion is the conversion to the structural information of image, the overall gray level information of image is constant, therefore, the characteristic sequence extracting by the Pulse-coupled Neural Network Model based on half-tone information, can not directly reflect the variation of scramble picture structure information.
Summary of the invention
In order to solve the problem of direct extraction scramble picture structure information, the embodiment of the present invention provides a kind of image scrambling evaluation method and device.Described technical scheme is as follows:
On the one hand, provide a kind of image scrambling evaluation method, described method comprises:
Original image and at least one width scramble image are carried out respectively to step-by-step layering, obtain the bitmap images of described original image and the bitmap images of described at least one width scramble image;
According to intersecting cortex neural network model, respectively the bitmap images of the bitmap images of described original image and described at least one width scramble image is carried out to feature extraction, obtain the architectural feature sequence of described original image and the architectural feature sequence of described at least one width scramble image;
According to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, calculate, obtain the scramble degree of described at least one width scramble image.
Preferably, original image and scramble image are carried out to step-by-step layering, before obtaining the bitmap images of described original image and the bitmap images of described at least one width scramble image, comprising:
According to Image Scrambling Algorithm, original image is carried out to scramble conversion, obtain at least one width scramble image.
Preferably, according to intersecting cortex neural network model, respectively the bitmap images of the bitmap images of described original image and described at least one width scramble image is carried out to feature extraction, obtains the architectural feature sequence of described original image and the architectural feature sequence of described at least one width scramble image, comprising:
According to intersecting cortex neural network model, respectively the bitmap images of the predetermined number of the bitmap images of the predetermined number of described original image and described at least one width scramble image is carried out respectively to feature extraction, obtain the characteristic sequence of bitmap images of predetermined number of described original image and the characteristic sequence of the bitmap images of the predetermined number of described at least one width scramble image;
The characteristic sequence of the bitmap images of the predetermined number of described original image is combined, when obtaining the architectural feature sequence of described original image, the characteristic sequence of the bitmap images of the predetermined number of described at least one width scramble image is combined, obtain the architectural feature sequence of described at least one width scramble image.
Preferably, according to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, calculate, obtain the scramble degree of described at least one width scramble image, comprising:
According to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, calculate single order absolute value distance, the scramble degree using described single order absolute value distance as described at least one width scramble image.
On the other hand, provide a kind of image scrambling evaluating apparatus, described device comprises:
Hierarchical block, for original image and at least one width scramble image are carried out respectively to step-by-step layering, obtains the bitmap images of described original image and the bitmap images of described at least one width scramble image;
Characteristic extracting module, be used for according to intersecting cortex neural network model, respectively the bitmap images of the bitmap images of described original image and described at least one width scramble image is carried out to feature extraction, obtain the architectural feature sequence of described original image and the architectural feature sequence of described at least one width scramble image;
Computing module, for calculating according to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, obtains the scramble degree of described at least one width scramble image.
Preferably, described device also comprises:
Scramble module, for original image being carried out to scramble conversion according to Image Scrambling Algorithm, obtains at least one width scramble image.
Preferably, described characteristic extracting module, comprising:
Feature extraction unit, be used for according to intersecting cortex neural network model, respectively the bitmap images of the predetermined number of the bitmap images of the predetermined number of described original image and described at least one width scramble image is carried out respectively to feature extraction, obtain the characteristic sequence of bitmap images of predetermined number of described original image and the characteristic sequence of the bitmap images of the predetermined number of described at least one width scramble image;
Assembled unit, for the characteristic sequence of the bitmap images of the predetermined number of described original image is combined, when obtaining the architectural feature sequence of described original image, the characteristic sequence of the bitmap images of the predetermined number of described at least one width scramble image is combined, obtain the architectural feature sequence of described at least one width scramble image.
Preferably, described computing module is for calculating single order absolute value distance, the scramble degree using described single order absolute value distance as described at least one width scramble image according to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image.
The beneficial effect that the technical scheme that the embodiment of the present invention provides is brought is:
The embodiment of the present invention provides a kind of image scrambling evaluation method and device, by original image and at least one width scramble image are carried out respectively to step-by-step layering, obtains the bitmap images of described original image and the bitmap images of described at least one width scramble image; According to intersecting cortex neural network model, respectively the bitmap images of the bitmap images of described original image and described at least one width scramble image is carried out to feature extraction, obtain the architectural feature sequence of described original image and the architectural feature sequence of described at least one width scramble image; According to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, calculate, obtain the scramble degree of described at least one width scramble image.The technical scheme that adopts the embodiment of the present invention to provide, by original image and at least one width scramble image being carried out to step-by-step layering and using, intersect cortex neural network model and carry out feature extraction, realize the structure feature information of direct extraction image, thereby can carry out better the evaluation of scramble degree.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, below the accompanying drawing of required use during embodiment is described is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skills, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is a kind of image scrambling evaluation method process flow diagram providing in the embodiment of the present invention;
Fig. 2 a is a kind of image scrambling evaluation method process flow diagram providing in the embodiment of the present invention;
Fig. 2 b is the scramble degree curve synoptic diagram of a kind of scramble image of providing in the embodiment of the present invention;
Fig. 3 is a kind of image scrambling evaluating apparatus structural representation providing in the embodiment of the present invention.
Embodiment
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing, embodiment of the present invention is described further in detail.
It should be noted that, the gray scale of digital picture can be represented by numerous types of data, as two-value data, integer, single precision, double precision etc., therefore, the number of bits that the image of different types of data is corresponding is not identical yet, preferably, in embodiments of the present invention, the data type of original image and scramble image is unsigned int, and data tonal range is 0-255, and this tonal range can represent with 8 bits.For the image of other value types, need to carry out value type conversion, making it tonal range is 0-255.The data type of original image and scramble image of take in embodiments of the present invention describes as unsigned int as example.
Fig. 1 is a kind of image scrambling evaluation method process flow diagram providing in the embodiment of the present invention, and referring to Fig. 1, the method comprises:
101: original image and at least one width scramble image are carried out respectively to step-by-step layering, obtain the bitmap images of described original image and the bitmap images of described at least one width scramble image;
Wherein, scramble image refers to the pixel position that changes image by scrambling algorithm, and does not change the image that pixel gray scale obtains, and compares with original image, and the structure of scramble image changes, and overall gray scale does not change.
This original image and at least one width scramble image are carried out respectively to step-by-step decomposition, respectively the gray-scale value of each pixel of this original image and at least one width scramble image is represented with 8 bits, the binary number of getting on the same position of each pixel forms bitmap images, obtains 8 width bitmap images of this original image and 8 width bitmap images of this at least one width scramble image.Because bitmap images is by binary number representation, bitmap images is bianry image, and the gray scale of this bianry image only has 0 and 1, black and white.
102: according to intersecting cortex neural network model, respectively the bitmap images of the bitmap images of described original image and described at least one width scramble image is carried out to feature extraction, obtain the architectural feature sequence of described original image and the architectural feature sequence of described at least one width scramble image;
Wherein, the cortex neural network model that intersects is the simplification of paired pulses coupled neural network model, and its mathematical formulae is as shown in (1)-(3):
F
ij[n+1]=fF
ij[n]+S
ij+W{Y[n]} (1)
θ
ij[n+1]=gθ
ij[n]+hY
ij[n+1] (2)
Wherein, formula (1) is feed-in unit, as the value of being fed forward Fij with the previous feed-in value of pixel ij, the brightness value Sij of pixel ij and surrounding pixel are put a front output valve Y[n] relevant, f is the attenuation coefficient (being less than 1) of feed-in unit, the connection weight that W is adjacent neurons.Formula (2) is threshold cell, the input of current threshold value θ ij is relevant with the output valve of pixel ij with the previous threshold value of pixel ij, g is the attenuation coefficient (being less than 1) of threshold cell, h is the coupling coefficient to pixel ij output valve, be used for suppressing same pixel continuous ignition, conventionally value is larger, as 100,200,300 etc., this embodiment of the present invention is not done to concrete restriction.Formula (3) is output unit, and the output Yij of pixel ij relatively produces by working as the value of being fed forward Fij and previous threshold value θ ij, when Fij is greater than θ ij, and pixel ij igniting, Yij is 1, on the contrary Yij is that 0, θ ij is initialized as 1.
Thereby the cortex neural network model that intersects has the characteristic of catching surrounding pixel point igniting generation auto-wave, this characteristic makes to intersect cortex neural network model and can extract the structure feature information of image.
Intersect and to produce and to excite when the neuron of cortex neural network model is subject to extraneous input stimulus and neighborhood neuron output coupling influence, other neuron that further impact is adjacent, produces the auto-wave of outwards propagating centered by or a group neuron.Automatically wave propagation can excite the adjacent neuron with similar state under close dynamic excitation simultaneously, produces a series of two-value pulse diagram pictures for presentation video feature.By calculating the number of pulse in the two-value pulse diagram picture of each iteration output, output pulse diagram is looked like to be transformed to the one-dimensional signal for token image pattern, i.e. architectural feature sequence.The pulse output number of each iteration is as follows as the computing formula of an eigenwert in architectural feature sequence:
N=∑Y
ij (4)
According to intersecting cortex neural network model, respectively the bitmap images of the bitmap images of this original image and at least one width scramble image is carried out to feature extraction, by the propagation characteristic of auto-wave, obtain the eigenwert of bitmap images, by this eigenwert, form characteristic sequence, obtain the architectural feature sequence of this original image and the architectural feature sequence of at least one width scramble image.
103: according to the architectural feature sequence of the architectural feature sequence of described original image and described scramble image, obtain the scramble degree of scramble image.
Wherein, scramble degree has reflected the Information hiding degree of scramble image, and scramble degree is higher, and the Information hiding degree of scramble image is higher, and scramble degree is lower, and the Information hiding degree of scramble image is lower.
By use, intersect cortex neural network model this original image and scramble image are carried out to feature extraction, obtain the architectural feature sequence of this original image and the architectural feature sequence of scramble image, difference between the architectural feature sequence of this original image and the architectural feature sequence of scramble image is weighed, obtained the scramble degree of scramble image.Difference between the architectural feature sequence of this original image and the architectural feature sequence of scramble image is larger, the scramble degree of scramble image is higher, difference between the architectural feature sequence of this original image and the architectural feature sequence of scramble image is less, and the scramble degree of scramble image is lower.
Between the architectural feature sequence of this original image and the architectural feature sequence of scramble image, the computing method of difference can be single order absolute value distance, information entropy, Euclidean distance and related coefficient etc., to this, the embodiment of the present invention is not done concrete restriction, preferably, adopts single order absolute value distance.
The embodiment of the present invention provides a kind of image scrambling evaluation method, by original image and at least one width scramble image are carried out respectively to step-by-step layering, obtains the bitmap images of described original image and the bitmap images of described at least one width scramble image; According to intersecting cortex neural network model, respectively the bitmap images of the bitmap images of described original image and described at least one width scramble image is carried out to feature extraction, obtain the architectural feature sequence of described original image and the architectural feature sequence of described at least one width scramble image; According to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, calculate, obtain the scramble degree of described at least one width scramble image.The technical scheme that adopts the embodiment of the present invention to provide, by original image and at least one width scramble image being carried out to step-by-step layering and using, intersect cortex neural network model and carry out feature extraction, realize the structure feature information of direct extraction image, thereby can carry out better the evaluation of scramble degree.
Fig. 2 a is a kind of image scrambling evaluation method process flow diagram providing in the embodiment of the present invention, the executive agent of this embodiment is the electronic equipment with image-capable, as personal computer, panel computer, picture pick-up device or server etc., referring to Fig. 2 a, the method comprises:
201: according to Image Scrambling Algorithm, original image is carried out to scramble conversion, obtain at least one width scramble image;
Wherein, Image Scrambling Algorithm can convert for Arnold, Fibonacci conversion, Magic Square Transformation, Hilbert conversion, affined transformation etc., and to this, the embodiment of the present invention is not done concrete restriction, preferably, adopts Arnold conversion.
Arnold conversion is a kind of conversion that mathematician Arnold proposes when research ergodic theory, supposes that original image size is for N * N, and location of pixels is (x, y), location of pixels after how much scrambles conversion be (x ', y '), and the disorder method that how much scrambles convert is described as:
Wherein,
A, b, c, d ∈ Z (Positive Integer Set), works as a=b=c=1, and during d=2, formula (5) is the canonical form of Arnold conversion.
Original image converts through an Arnold, by former give me a little (x, y) locate corresponding grey scale pixel value move to (x ', y '), obtain a width scramble image, will (x ', y ') as the input of Arnold conversion next time, convert continuously, can obtain a series of scramble images.The image of fixed size has fixedly Arnold transformation period, and, after the Arnold conversion of certain number of times, this image reverts to original image.Original image, after Arnold conversion, can obtain at least one width scramble image.
The image that the size of take in the embodiment of the present invention is 256*256 carries out the explanation of scramble degree evaluation as example, the data type of the gray scale of this image is unsigned int, by 8 bits, represented, be 192 the Arnold transformation period of this image, and this image can obtain 192 width scramble images after Arnold conversion.
202: original image and at least one width scramble image are carried out respectively to step-by-step layering, obtain the bitmap images of described original image and the bitmap images of described at least one width scramble image;
Original image and at least one width scramble image are carried out respectively to step-by-step layering, the image representing for 8 systems, original image and at least one width scramble image can obtain 8 layers of bitmap images after step-by-step layering, every layer of bitmap images is bianry image, and the quantity of information of every layer of bitmap images is different, it is many that the quantity of information of the bitmap images of high bit is wanted relatively, and less compared with the quantity of information of the bitmap images of low level.
Example based in step 201, after Arnold conversion, gets 192 width scramble images at the image that is 256*256 to size, and original image and 192 width scramble images are carried out respectively to step-by-step layering, and every width image is corresponding to 8 width bitmap images.
203: according to intersecting cortex neural network model, respectively the bitmap images of the predetermined number of the bitmap images of the predetermined number of described original image and described at least one width scramble image is carried out respectively to feature extraction, obtain the characteristic sequence of bitmap images of predetermined number of described original image and the characteristic sequence of the bitmap images of the predetermined number of described at least one width scramble image;
Wherein, predetermined number is the numerical value that is less than or equal to the bitmap images number of plies, and when bitmap images is 8, this predetermined number can be 3,4,5 etc., and to this, the embodiment of the present invention is not done concrete restriction.
The embodiment of the present invention only be take and is intersected cortex neural network model and the bitmap images of the predetermined number of this original image is carried out to feature extraction describe as example, and this process comprises following two steps:
(1) from the bitmap images of original image according to the order from a high position to low level, choose the bitmap images of predetermined number, as when predetermined number value is 5, choose the bitmap images of high 5;
(2) using the bitmap images of the predetermined number of choosing respectively as intersecting the input picture of cortex neural network model, according to default iterations, carry out iteration, obtain the characteristic sequence of bitmap images of the predetermined number of this original image.This default iterations can be 5,10,20 etc., and to this, the embodiment of the present invention is not done concrete restriction, in order to reduce calculated amount, improves arithmetic speed, and preferably, default iterations is 5 times.Particularly, every width bitmap images when intersecting the input of cortex neural network model, calculates each iteration characteristic of correspondence value according to formula (4), obtains the eigenwert number identical with default iterations quantity, forms the characteristic sequence of every width bitmap images.
The process that the cortex neural network model that intersects carries out feature extraction to the bitmap images of the predetermined number of this at least one width scramble image is similar with said process, specifically referring to above-mentioned intersection cortex neural network model, the bitmap images of the predetermined number of this original image is carried out to the step of feature extraction, do not repeat them here.
Example based in step 202 when predetermined number is 3, from 8 width bitmap images of original image, is chosen 3 width bitmap images according to the order from a high position to low level in this step; By intersection cortex neural network model, every width bitmap images is carried out to iteration, when iterations is 5, every width bitmap images obtains the characteristic sequence that 5 eigenwerts form.Simultaneously, from 8 width bitmap images of at least one width scramble image, according to the order from a high position to low level, choose 3 width bitmap images, by intersection cortex neural network model, every width bitmap images is carried out to iteration, when iterations is 5, at least one width bitmap images obtains the characteristic sequence that 5 eigenwerts form, and repeats this process, until obtain the characteristic sequence of the bitmap images of the predetermined number that 192 width scramble images are corresponding.
204: the characteristic sequence of the bitmap images of the predetermined number of described original image is combined, when obtaining the architectural feature sequence of described original image, the characteristic sequence of the bitmap images of the predetermined number of described at least one width scramble image is combined, obtain the architectural feature sequence of described at least one width scramble image;
The characteristic sequence of the bitmap images of the predetermined number of this original image is combined, can to the characteristic sequence of low level bitmap images, arrange according to the characteristic sequence from high-order bitmap images, also can to the characteristic sequence of high-order bitmap images, arrange according to the feature from low level bitmap images, to this, the embodiment of the present invention is not done concrete restriction, obtain the architectural feature sequence of this original image, this architectural feature sequence is by intersection cortex neural network, the bitmap images of two-value to be carried out to direct feature extraction to obtain, the architectural feature that has reflected preferably this original image.
, the characteristic sequence of the bitmap images of the predetermined number of this at least one width scramble image is combined meanwhile, obtain the architectural feature sequence of this at least one width scramble image, this process is similar to the above process, does not repeat them here.
Example based in step 203, the characteristic sequence of the bitmap images of the predetermined number of this original image is combined according to the order from high-order bitmap images to low level bitmap images, the architectural feature sequence of this original image obtaining comprises 15 eigenwerts, and 192 width scramble images are after combination, the architectural feature sequence of every width scramble image also comprises 15 eigenwerts.
This step 203-204 is according to intersecting cortex neural network model, respectively the bitmap images of the bitmap images of described original image and described at least one width scramble image is carried out to feature extraction, obtain the process of the architectural feature sequence of described original image and the architectural feature sequence of described at least one width scramble image.
205: according to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, calculate single order absolute value distance, the scramble degree using described single order absolute value distance as described at least one width scramble image.
Wherein, the calculating of single order absolute value distance is as shown in Equation (6):
Wherein, K represents the K time iteration in Arnold conversion, and n represents the total length of architectural feature sequence, i numerical value in i representation feature structure sequence, Y
o ifor the architectural feature sequence of original image, Y
k ibe the architectural feature sequence of K width scramble image, D
kit is the single order absolute value distance of K width scramble image.
According to the architectural feature sequence of the architectural feature sequence of this original image and this at least one width scramble image, according to formula (6), calculate the single order absolute value distance of this at least one width scramble image, the scramble degree using this single order absolute value distance as this at least one width scramble image.
Further, after obtaining the single order absolute value distance of scramble image, for the scramble degree of more different scramble images more clearly, single order absolute value distance is normalized, the span that makes scramble degree is [0,1], can think approx that the value of single order absolute value distance is at 1 o'clock, the scramble degree of scramble image is the highest.
Example based in step 204, this step is calculated according to the architectural feature sequence of the architectural feature sequence of every width scramble image, original image and formula (6), can obtain the scramble degree of every width scramble image, after obtaining the scramble degree of every width scramble image, the maximal value of the scramble degree acquiring, the scramble degree of every width image, divided by this maximal value, is realized to normalization.The validity that adopts scramble degree that the technical scheme of the embodiment of the present invention obtains to evaluate in order to further illustrate, Fig. 2 b is the scramble degree curve synoptic diagram of a kind of scramble image of providing in the embodiment of the present invention, referring to Fig. 2 b, scramble in the figure line of writing music is approximate symmetrical, several minimum point a, b, c, d, e, f and g in figure, have been provided, due to symmetry, only the several points of a, b, c and d are analyzed.Those skilled in the art are known, the pixel of each gray level of scramble image distributes more even, the scramble degree of this scramble image is higher, the scramble degree that a is ordered is 0.8722, the scramble degree that b is ordered is 0.8768, the scramble degree that c is ordered is that the scramble degree that 0.887, d is ordered is 0.8279, and the sequence of the scramble degree of these four somes size is d<a<b<c.From this angle, can find out, the image of correspondence and these four points, the block effect of d, a, b and c image is more and more less, and pixel distributes also more and more even, thereby the scramble degree evaluation of scramble image is herein rational.Therefore, the technical scheme adopting in the embodiment of the present invention, by directly extracting the structure feature information of image, can realize the evaluation of scramble degree preferably.
This step 205 is to calculate according to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, obtains the process of the scramble degree of described at least one width scramble image.
The embodiment of the present invention provides a kind of image scrambling evaluation method, by original image and at least one width scramble image are carried out respectively to step-by-step layering, obtains the bitmap images of described original image and the bitmap images of described at least one width scramble image; According to intersecting cortex neural network model, respectively the bitmap images of the bitmap images of described original image and described at least one width scramble image is carried out to feature extraction, obtain the architectural feature sequence of described original image and the architectural feature sequence of described at least one width scramble image; According to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, calculate, obtain the scramble degree of described at least one width scramble image.The technical scheme that adopts the embodiment of the present invention to provide, by original image and at least one width scramble image being carried out to step-by-step layering and using, intersect cortex neural network model and carry out feature extraction, realize the structure feature information of direct extraction image, thereby can carry out better the evaluation of scramble degree.
Fig. 3 is a kind of image scrambling evaluating apparatus structural representation providing in the embodiment of the present invention, and referring to Fig. 3, this device comprises:
Hierarchical block 301, for original image and at least one width scramble image are carried out respectively to step-by-step layering, obtains the bitmap images of described original image and the bitmap images of described at least one width scramble image;
Characteristic extracting module 302, be used for according to intersecting cortex neural network model, respectively the bitmap images of the bitmap images of described original image and described at least one width scramble image is carried out to feature extraction, obtain the architectural feature sequence of described original image and the architectural feature sequence of described at least one width scramble image;
Computing module 303, for calculating according to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, obtains the scramble degree of described at least one width scramble image.
Described device also comprises:
Scramble module, for original image being carried out to scramble conversion according to Image Scrambling Algorithm, obtains at least one width scramble image.
Described characteristic extracting module 302, comprising:
Feature extraction unit, be used for according to intersecting cortex neural network model, respectively the bitmap images of the predetermined number of the bitmap images of the predetermined number of described original image and described at least one width scramble image is carried out respectively to feature extraction, obtain the characteristic sequence of bitmap images of predetermined number of described original image and the characteristic sequence of the bitmap images of the predetermined number of described at least one width scramble image;
Assembled unit, for the characteristic sequence of the bitmap images of the predetermined number of described original image is combined, when obtaining the architectural feature sequence of described original image, the characteristic sequence of the bitmap images of the predetermined number of described at least one width scramble image is combined, obtain the architectural feature sequence of described at least one width scramble image.
Described computing module 303 is for calculating single order absolute value distance, the scramble degree using described single order absolute value distance as described at least one width scramble image according to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image.
The embodiment of the present invention provides a kind of image scrambling evaluating apparatus, by original image and at least one width scramble image are carried out respectively to step-by-step layering, obtains the bitmap images of described original image and the bitmap images of described at least one width scramble image; According to intersecting cortex neural network model, respectively the bitmap images of the bitmap images of described original image and described at least one width scramble image is carried out to feature extraction, obtain the architectural feature sequence of described original image and the architectural feature sequence of described at least one width scramble image; According to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, calculate, obtain the scramble degree of described at least one width scramble image.The technical scheme that adopts the embodiment of the present invention to provide, by original image and at least one width scramble image being carried out to step-by-step layering and using, intersect cortex neural network model and carry out feature extraction, realize the structure feature information of direct extraction image, thereby can carry out better the evaluation of scramble degree.
It should be noted that: the image scrambling evaluating apparatus that above-described embodiment provides is when image scrambling is evaluated, only the division with above-mentioned each functional module is illustrated, in practical application, can above-mentioned functions be distributed and by different functional modules, completed as required, the inner structure of the equipment of being about to is divided into different functional modules, to complete all or part of function described above.In addition, the image scrambling evaluating apparatus that above-described embodiment provides and image scrambling evaluation method embodiment belong to same design, and its specific implementation process refers to embodiment of the method, repeats no more here.
One of ordinary skill in the art will appreciate that all or part of step that realizes above-described embodiment can complete by hardware, also can come the hardware that instruction is relevant to complete by program, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium of mentioning can be ROM (read-only memory), disk or CD etc.
The foregoing is only preferred embodiment of the present invention, in order to limit the present invention, within the spirit and principles in the present invention not all, any modification of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (8)
1. an image scrambling evaluation method, is characterized in that, comprising:
Original image and at least one width scramble image are carried out respectively to step-by-step layering, obtain the bitmap images of described original image and the bitmap images of described at least one width scramble image;
According to intersecting cortex neural network model, respectively the bitmap images of the bitmap images of described original image and described at least one width scramble image is carried out to feature extraction, obtain the architectural feature sequence of described original image and the architectural feature sequence of described at least one width scramble image;
According to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, calculate, obtain the scramble degree of described at least one width scramble image.
2. a kind of image scrambling evaluation method according to claim 1, is characterized in that, original image and scramble image are carried out to step-by-step layering, before obtaining the bitmap images of described original image and the bitmap images of described at least one width scramble image, comprising:
According to Image Scrambling Algorithm, original image is carried out to scramble conversion, obtain at least one width scramble image.
3. a kind of image scrambling evaluation method according to claim 1, it is characterized in that, according to intersecting cortex neural network model, respectively the bitmap images of the bitmap images of described original image and described at least one width scramble image is carried out to feature extraction, obtain the architectural feature sequence of described original image and the architectural feature sequence of described at least one width scramble image, comprising:
According to intersecting cortex neural network model, respectively the bitmap images of the predetermined number of the bitmap images of the predetermined number of described original image and described at least one width scramble image is carried out respectively to feature extraction, obtain the characteristic sequence of bitmap images of predetermined number of described original image and the characteristic sequence of the bitmap images of the predetermined number of described at least one width scramble image;
The characteristic sequence of the bitmap images of the predetermined number of described original image is combined, when obtaining the architectural feature sequence of described original image, the characteristic sequence of the bitmap images of the predetermined number of described at least one width scramble image is combined, obtain the architectural feature sequence of described at least one width scramble image.
4. a kind of image scrambling evaluation method according to claim 1, it is characterized in that, according to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, calculate, obtain the scramble degree of described at least one width scramble image, comprising:
According to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, calculate single order absolute value distance, the scramble degree using described single order absolute value distance as described at least one width scramble image.
5. an image scrambling evaluating apparatus, is characterized in that, comprising:
Hierarchical block, for original image and at least one width scramble image are carried out respectively to step-by-step layering, obtains the bitmap images of described original image and the bitmap images of described at least one width scramble image;
Characteristic extracting module, be used for according to intersecting cortex neural network model, respectively the bitmap images of the bitmap images of described original image and described at least one width scramble image is carried out to feature extraction, obtain the architectural feature sequence of described original image and the architectural feature sequence of described at least one width scramble image;
Computing module, for calculating according to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image, obtains the scramble degree of described at least one width scramble image.
6. a kind of image scrambling evaluating apparatus according to claim 5, is characterized in that, comprising:
Scramble module, for original image being carried out to scramble conversion according to Image Scrambling Algorithm, obtains at least one width scramble image.
7. a kind of image scrambling evaluating apparatus according to claim 5, is characterized in that, described characteristic extracting module, comprising:
Feature extraction unit, be used for according to intersecting cortex neural network model, respectively the bitmap images of the predetermined number of the bitmap images of the predetermined number of described original image and described at least one width scramble image is carried out respectively to feature extraction, obtain the characteristic sequence of bitmap images of predetermined number of described original image and the characteristic sequence of the bitmap images of the predetermined number of described at least one width scramble image;
Assembled unit, for the characteristic sequence of the bitmap images of the predetermined number of described original image is combined, when obtaining the architectural feature sequence of described original image, the characteristic sequence of the bitmap images of the predetermined number of described at least one width scramble image is combined, obtain the architectural feature sequence of described at least one width scramble image.
8. a kind of image scrambling evaluating apparatus according to claim 5, it is characterized in that, described computing module is for calculating single order absolute value distance, the scramble degree using described single order absolute value distance as described at least one width scramble image according to the architectural feature sequence of the architectural feature sequence of described original image and described at least one width scramble image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310669497.1A CN103632375B (en) | 2013-12-10 | 2013-12-10 | A kind of image scrambling evaluation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310669497.1A CN103632375B (en) | 2013-12-10 | 2013-12-10 | A kind of image scrambling evaluation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103632375A true CN103632375A (en) | 2014-03-12 |
| CN103632375B CN103632375B (en) | 2016-09-21 |
Family
ID=50213392
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310669497.1A Active CN103632375B (en) | 2013-12-10 | 2013-12-10 | A kind of image scrambling evaluation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103632375B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107392971A (en) * | 2017-08-07 | 2017-11-24 | 长安大学 | Image encryption effect evaluation method based on gap test |
| CN112017099A (en) * | 2020-09-03 | 2020-12-01 | 山东省计算中心（国家超级计算济南中心） | Method and system for hiding and analyzing program code in image |
| CN116305224A (en) * | 2023-05-24 | 2023-06-23 | 青岛宜开美数字科技有限公司 | User order information storage system based on platform data |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107193509A (en) * | 2017-04-27 | 2017-09-22 | 天津市捷威动力工业有限公司 | A kind of method for realizing any Windows fonts Chinese character printing |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750699A (en) * | 2012-06-11 | 2012-10-24 | 华南理工大学 | Method for measuring image scrambling degree based on information entropies |
-
2013
- 2013-12-10 CN CN201310669497.1A patent/CN103632375B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750699A (en) * | 2012-06-11 | 2012-10-24 | 华南理工大学 | Method for measuring image scrambling degree based on information entropies |
Non-Patent Citations (2)
| Title |
|---|
| CHUNLIN LI ETC.: "Evaluation of Image Scrambling Degree with Intersecting Cortical Model Neural Network", 《INTERNATIONAL JOURNAL OF HYBRID INFORMATION TECHNOLOGY》 * |
| 谭永杰: "图像置乱及其效果评价方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107392971A (en) * | 2017-08-07 | 2017-11-24 | 长安大学 | Image encryption effect evaluation method based on gap test |
| CN107392971B (en) * | 2017-08-07 | 2021-01-26 | 长安大学 | Image encryption effect evaluation method based on gap detection |
| CN112017099A (en) * | 2020-09-03 | 2020-12-01 | 山东省计算中心（国家超级计算济南中心） | Method and system for hiding and analyzing program code in image |
| CN112017099B (en) * | 2020-09-03 | 2023-12-15 | 山东省计算中心（国家超级计算济南中心） | Method and system for hiding and analyzing program codes in image |
| CN116305224A (en) * | 2023-05-24 | 2023-06-23 | 青岛宜开美数字科技有限公司 | User order information storage system based on platform data |
| CN116305224B (en) * | 2023-05-24 | 2023-07-21 | 青岛宜开美数字科技有限公司 | User order information storage system based on platform data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103632375B (en) | 2016-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Man et al. | Double image encryption algorithm based on neural network and chaos | |
| Dhawan et al. | Analysis of various data security techniques of steganography: A survey | |
| Li et al. | Image encryption based on dynamic filtering and bit cuboid operations | |
| Ubhi et al. | Neural style transfer for image within images and conditional GANs for destylization | |
| Cheng et al. | Pasadena: Perceptually aware and stealthy adversarial denoise attack | |
| Xu et al. | Image fusion based on nonsubsampled contourlet transform and saliency‐motivated pulse coupled neural networks | |
| Yang et al. | Lossless image compression-encryption algorithm based on BP neural network and chaotic system | |
| Rajagopalan et al. | Chua's diode and strange attractor: a three‐layer hardware–software co‐design for medical image confidentiality | |
| An et al. | Image encryption algorithm based on adaptive wavelet chaos | |
| CN103632375A (en) | Image scrambling evaluation method and image scrambling evaluation device | |
| Avci et al. | A novel reversible data hiding algorithm based on probabilistic XOR secret sharing in wavelet transform domain | |
| Wang et al. | An image encryption scheme using bit-plane cross-diffusion and spatiotemporal chaos system with nonlinear perturbation | |
| Medykovskyy et al. | Methods of protection document formed from latent element located by fractals | |
| Ye et al. | A novel image encryption algorithm based on improved Arnold transform and chaotic pulse-coupled neural network | |
| Zhang et al. | NHNet: A non‐local hierarchical network for image denoising | |
| Zhang et al. | Infrared and visible image fusion based on non‐subsampled shearlet transform, regional energy, and co‐occurrence filtering | |
| Jana et al. | A new DCT based robust image watermarking scheme using cellular automata | |
| Jiang et al. | Image encryption algorithm based on 2D‐CLICM chaotic system | |
| Li et al. | Privacy protection method based on multidimensional feature fusion under 6G networks | |
| Shi et al. | Image encryption scheme based on multiscale block compressed sensing and Markov model | |
| Chen et al. | An image encryption algorithm based on the LSCMM chaotic map and bidirectional dynamic diffusion | |
| CN107483963A (en) | A kind of 1 bit image compression encryption method | |
| Khan et al. | Toward developing tangling noise removal and blind inpainting mechanism based on total variation in image processing | |
| Ding et al. | Signal-sensing dynamic S-box image encryption with 2D Griewank–sin map | |
| He et al. | A fast image encryption algorithm based on logistic mapping and hyperchaotic lorenz system for clear text correlation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231103 Address after: No. 57-5 Development Avenue, No. 6015, Yichang Area, China (Hubei) Free Trade Zone, Yichang City, Hubei Province, 443005 Patentee after: Hubei Jiugan Technology Co.,Ltd. Address before: 443002 No. 8, University Road, Yichang, Hubei Patentee before: CHINA THREE GORGES University |