CN115834792B - Video data processing method and system based on artificial intelligence - Google Patents
Video data processing method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN115834792B CN115834792B CN202310146591.2A CN202310146591A CN115834792B CN 115834792 B CN115834792 B CN 115834792B CN 202310146591 A CN202310146591 A CN 202310146591A CN 115834792 B CN115834792 B CN 115834792B
- Authority
- CN
- China
- Prior art keywords
- complementary
- gray
- gray value
- value
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 33
- 238000003672 processing method Methods 0.000 title claims abstract description 20
- 230000000295 complement effect Effects 0.000 claims abstract description 306
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000007796 conventional method Methods 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 3
- 238000005315 distribution function Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000003169 complementation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image encryption, in particular to a video data processing method and system based on artificial intelligence. The method comprises the following steps: acquiring an initial gray level histogram of an image to be processed, and acquiring a target gray level value corresponding to a gray level value with a frequency other than 0 according to the frequency corresponding to each gray level value in the initial gray level histogram and the maximum gray level value and the minimum gray level value of a pixel point in the image to be processed, so as to acquire a stretched gray level histogram; obtaining complementary parameters of each gray value according to the frequency corresponding to each gray value in the stretched gray histogram and the average frequency of all gray values; and obtaining each optimal gray value set based on the complementary parameters, and carrying out complementary operation on the frequencies corresponding to the gray values in each optimal gray value set according to the frequencies corresponding to the gray values in each optimal gray value set and the average frequencies of all gray values to obtain an encrypted image. The invention reduces the risk of leakage of video data.
Description
Technical Field
The invention relates to the technical field of image encryption, in particular to a video data processing method and system based on artificial intelligence.
Background
With the advent of the informatization age, various industries began to use artificial intelligence technology to store data in video data and conduct anomaly analysis, and the change and anomaly existing in the video are accurately identified through the strong computing capacity of artificial intelligence; however, these video data may be tampered with and stolen before being transmitted to the artificial intelligence terminal, so the encryption protection during the video data transmission process becomes a research hot spot. At present, more data transmission uses an entropy coding method, and aiming at the advantages of encryption of video data with gray values distributed between 0 and 255, better encryption efficiency can be obtained by using entropy coding, however, the entropy coding exposes the statistical characteristics of the data, and the possibility of deducing the original data through the inverse coding of the statistical characteristics exists, so how to unify the video data to ensure that the video data is not leaked is a problem to be solved.
Disclosure of Invention
In order to solve the problem that the prior method cannot break the statistical characteristics of data to cause the risk of leakage of the video data when the video data is encrypted and protected, the invention aims to provide an artificial intelligence-based video data processing method and system, and the adopted technical scheme is as follows:
In a first aspect, the present invention provides an artificial intelligence based video data processing method comprising the steps of:
acquiring video data to be processed, and marking any frame of gray level image in the video data as an image to be processed;
acquiring an initial gray level histogram corresponding to the image to be processed, acquiring a target gray level value corresponding to each gray level value which is not 0 in the initial gray level histogram according to the frequency corresponding to each gray level value in the initial gray level histogram, the maximum gray level value of the pixel point in the image to be processed and the minimum gray level value of the pixel point in the image to be processed, and acquiring a stretched gray level histogram based on the target gray level value; obtaining complementary parameters of each gray value in the stretched gray histogram according to the frequency corresponding to each gray value in the stretched gray histogram and the average frequency of all gray values;
and obtaining each optimal gray value set based on the complementary parameters, and carrying out complementary operation on the frequencies corresponding to the gray values in each optimal gray value set according to the frequencies corresponding to the gray values in each optimal gray value set and the average frequencies of all gray values to obtain an encrypted image.
In a second aspect, the present invention provides an artificial intelligence based video data processing system, comprising a memory and a processor, the processor executing a computer program stored in the memory to implement the above mentioned artificial intelligence based video data processing method.
Preferably, the obtaining the complementary parameter of each gray value in the stretched gray histogram according to the frequency corresponding to each gray value in the stretched gray histogram and the average frequency of all gray values includes:
respectively calculating the difference value between the frequency corresponding to each gray value and the average frequency of all gray values, and marking the difference value as a first difference value; and taking the ratio of the first difference value to the average frequency of all the gray values as the complementary parameter of each gray value.
Preferably, the obtaining each optimal gray value set based on the complementary parameters includes:
sequencing all complementary parameters in the sequence from big to small to generate a complementary parameter sequence;
selecting the 1 st complementary parameter and the last 1 complementary parameter in the complementary parameter sequence as initial values, calculating the sum of the two initial values to be used as complementary judgment values of the 1 st complementary parameter and the last 1 complementary parameter, if the absolute value of the complementary judgment values of the 1 st complementary parameter and the last 1 complementary parameter is smaller than a statistical characteristic threshold value and the complementary judgment values of the 1 st complementary parameter and the last 1 complementary parameter are smaller than 0, traversing downwards from the gray value 255, calculating the complementary judgment values of the 1 st complementary parameter and the complementary parameters of all gray values until the complementary judgment values of the 1 st complementary parameter and the complementary parameters of the previous gray value are smaller than the complementary judgment values of the 1 st complementary parameter and the complementary parameters of the next gray value, taking the gray value corresponding to the 1 st complementary parameter and the corresponding previous gray value as an optimal gray value set, and deleting the complementary parameters of all gray values in the optimal gray value set in the complementary parameter sequence; if the absolute value of the complementary judgment value of the 1 st complementary parameter and the last 1 complementary parameter is smaller than the statistical characteristic threshold value, and the complementary judgment value of the 1 st complementary parameter and the last 1 complementary parameter is larger than or equal to 0, traversing upwards from the gray value 0 until the complementary judgment value of the 1 st complementary parameter and the complementary judgment value of the complementary parameter of the previous gray value is smaller than the complementary judgment value of the 1 st complementary parameter and the complementary judgment value of the complementary parameter of the subsequent gray value, and taking the gray value corresponding to the 1 st complementary parameter and the corresponding previous gray value as an optimal gray value set; and by analogy, updating the initial value, traversing all complementary parameters in the complementary parameter sequence to obtain a plurality of optimal gray value sets, and deleting the complementary parameters of each gray value in the optimal gray value sets in the complementary parameter sequence.
Preferably, if complementary parameters in the complementary parameter sequence after the complementary parameter operation of each gray value in the optimal gray value set are deleted, the complementary parameters in the complementary parameter sequence are ordered according to the sequence from big to small, a parameter sequence to be matched is constructed, according to the complementary judgment value of the 1 st complementary parameter and other complementary parameters in the parameter sequence to be matched, an optimal gray value complementary to the gray value corresponding to the 1 st complementary parameter is obtained, the gray value corresponding to the 1 st complementary parameter and each optimal gray value complementary to the 1 st complementary parameter form an optimal gray value set, and the other complementary parameters sequentially traverse forwards from the last 1 complementary parameters in the parameter sequence to be matched; and similarly, traversing the gray values corresponding to all complementary parameters in the parameter sequence to be matched to obtain each optimal gray value set.
Preferably, obtaining an optimal gray value complementary to the gray value corresponding to the 1 st complementary parameter according to the complementary determination value of the 1 st complementary parameter and other complementary parameters in the parameter sequence to be matched, includes:
if it isThen calculateUntil it meetsLast in the parameter sequence to be matchedThe gray value corresponding to the complementary parameter is taken as the optimal gray value complementary to the gray value corresponding to the 1 st complementary parameter, wherein, In order to take the absolute value of the value,for the 1 st complementary parameter in the sequence of parameters to be matched,for the last 1 complementary parameter in the sequence of parameters to be matched,for the number of complementary parameters in the sequence of parameters to be matched,for the 2 nd complementary parameter in the sequence of parameters to be matched,for the 3 rd complementary parameters in the sequence of parameters to be matched,for the last but one in the parameter sequence to be matchedThe number of complementary parameters is chosen,for the 1 st complementary parameter in the parameter sequence to be matched and the last complementary parameter in the parameter sequence to be matchedThe complementary determination values of the respective complementary parameters,for the 1 st complementary parameter in the parameter sequence to be matched and the last complementary parameter in the parameter sequence to be matchedComplementary determination values of the respective complementary parameters;
if it isThen calculateObtaining an optimal gray value complementary to the gray value corresponding to the 1 st complementary parameter, wherein,for the front in the parameter sequence to be matchedThe complementary parameter and the first parameter in the parameter sequence to be matchedComplementary determination values of the respective complementary parameters.
Preferably, the obtaining the target gray value corresponding to each gray value of the initial gray histogram, which is not 0, according to the frequency corresponding to each gray value in the initial gray histogram, the maximum gray value of the pixel point in the image to be processed, and the minimum gray value of the pixel point in the image to be processed, includes:
Calculating a target gray value corresponding to the ith gray value with the frequency of non-0 in the initial gray histogram by adopting the following formula:
wherein ,for a target gray value corresponding to the i-th gray value of frequency non-0,an ith gray value of frequency non-0,for the maximum gray value of the pixel point in the image to be processed,for the minimum gray value of the pixel point in the image to be processed,is rounded downwards.
Preferably, the obtaining the stretched gray level histogram based on the target gray level value includes: and replacing each gray value with a target gray value corresponding to the gray value, which is not 0, in the image to be processed, reconstructing a gray histogram based on the gray values of the pixel points in the image to be processed after the replacement is completed, and marking the gray histogram as a stretched gray histogram.
Preferably, the performing a complementary operation on the frequencies corresponding to the gray values in the optimal gray value sets according to the frequencies corresponding to the gray values in the optimal gray value sets and the average frequency of all the gray values to obtain the encrypted image includes:
if the number of gray values in the optimal gray value set is equal to 2, marking one gray value in the optimal gray value set as a first gray value, and marking the other gray value in the optimal gray value set as a second gray value; calculating the sum of the frequency corresponding to the first gray value before complementation and the frequency corresponding to the second gray value before complementation, marking the sum as a frequency index, taking the difference value of the frequency index and the average frequency of all gray values as the frequency corresponding to the first gray value after complementation, and taking the average frequency of all gray values as the frequency corresponding to the second gray value after complementation;
If the number of gray values in the optimal gray value set is greater than 2, marking the gray value with the maximum number of the corresponding optimal complementary gray values in the optimal gray value set as a third gray value, marking all other gray values except the third gray value in the optimal gray value set as a fourth gray value, taking the average frequency of all the gray values as the frequency corresponding to the third gray value after complementation, calculating the product of the average frequency of all the gray values and the number of the fourth gray value, marking the product as a first product, and taking the difference value of the frequency corresponding to the third gray value before complementation and the first product as the frequency corresponding to the fourth gray value after complementation;
an encrypted image is obtained based on the frequency at which each gradation value corresponds after complementation.
The invention has at least the following beneficial effects:
1. according to the distribution condition of the initial gray histogram corresponding to the image to be processed, a plurality of optimal gray value sets are obtained, the frequency corresponding to each gray value in each optimal gray value set is subjected to complementary operation based on a frequency complementary method, the statistic characteristics of image data are eliminated to generate an encrypted image, the problem of subjectivity and computational complexity of the threshold value is solved by the conventional method for average distribution and elimination of the statistic characteristics, the frequency corresponding to each gray value is subjected to complementary operation only once, compared with the conventional method, the method reduces operation cost, avoids the influence of human subjective factors on image encryption results, achieves the purposes of eliminating the statistic characteristics of the image data and encrypting, and reduces the risk of leakage of video data.
2. The invention obtains the optimal gray value set to carry out complementary operation on the frequency corresponding to each gray value in the optimal gray value set so as to eliminate the statistical characteristic of image data, considers that the gray values of pixel points in an image to be processed are possibly more intensively distributed in a certain gray interval, and can lead the gray values of the image to be uniformly distributed between 0 and 255 only through histogram equalization, but the statistical characteristic cannot be weakened, and the information in the image cannot be better protected, thus obtaining the target gray value corresponding to each gray value with frequency other than 0 in the image to be processed according to the frequency corresponding to each gray value in the image to be processed, the maximum gray value and the minimum gray value of the pixel points, and further carrying out stretching operation on the initial gray histogram; when the frequency corresponding to the gray value of the pixel point in the image to be processed is similar to the average frequency of all the gray values, the statistical characteristic of the image data is lower, so that the complementary parameters of all the gray values are obtained according to the frequency corresponding to each gray value in the stretched gray histogram and the average frequency of all the gray values, and further an optimal gray value set is obtained based on the complementary parameters, the statistical characteristic of the image data can be broken, and the risks of tampering and leakage of the video data are effectively reduced.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of an artificial intelligence based video data processing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an initial gray level histogram;
fig. 3 is a schematic diagram of a gray level histogram after stretching.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description is given below of an artificial intelligence-based video data processing method according to the present invention with reference to the accompanying drawings and the preferred embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of an artificial intelligence-based video data processing method and system.
Video data processing method embodiment based on artificial intelligence:
the embodiment provides an artificial intelligence-based video data processing method, as shown in fig. 1, which includes the following steps:
step S1, obtaining video data to be processed, and marking any frame of gray level image in the video data as the image to be processed.
The specific scene aimed at by this embodiment is: in the video data transmission process, encryption processing is required to be carried out on the data, the statistical characteristics of the image data cannot be changed in the traditional entropy coding, so that important information can be intercepted in the video data transmission process, and therefore, a method capable of uniformly processing the video data to enable the video data not to have the statistical characteristics is required. According to the embodiment, channel images are uniformly mapped into gray distribution according to the statistical characteristics of each channel of the image data, and gray values of all pixel points are converted through functions according to the frequency number to eliminate the statistical characteristics of the channel images, so that the aim of encrypting the image data is fulfilled.
The video data is composed of successive multi-frame RGB images, and is transmitted by encoding each channel data of each frame RGB image, and converting the encoded data into a digital signal during the transmission of the video data. The RGB image is composed of three channels of images, the gray distribution frequency of different images has statistical characteristics in the gray histogram, and the statistical characteristics reflect image information, so that the statistical information of the frequency needs to be eliminated by an encryption method, and the aim of protecting data is achieved. Because the data contained in each image is different, the gray scale distribution of the image channel may have regionality, for example, the gray scale value of the pixel point in the gray scale image of a certain channel is in the range of 0-40, the number of the pixel point is almost 0, the information reflected in the dark place of the channel is very little, and the gray scale value of the image can be uniformly distributed between 0 and 255 only through histogram equalization, but the statistical characteristic cannot be weakened, and the information in the image cannot be well protected.
In this embodiment, the video data to be processed is obtained by the video data acquisition module, and because the video data to be processed is composed of multiple frames of RGB images, each frame of RGB image needs to be split, that is, an R channel image, a G channel image and a B channel image of each frame of image are respectively extracted. The present embodiment will next be described taking one frame of RGB image in video data to be processed as an image to be encrypted as an example. As other embodiments, each frame of gray-scale image in the video data to be detected may be directly obtained, and each frame of gray-scale image may be encrypted, that is, each frame of image may not be split.
Step S2, obtaining an initial gray level histogram corresponding to the image to be processed, obtaining a target gray level value corresponding to each gray level value with a frequency other than 0 in the initial gray level histogram according to the frequency corresponding to each gray level value in the initial gray level histogram, the maximum gray level value of the pixel point in the image to be processed and the minimum gray level value of the pixel point in the image to be processed, and obtaining a stretched gray level histogram based on the target gray level value; and obtaining complementary parameters of each gray value in the stretched gray histogram according to the frequency corresponding to each gray value in the stretched gray histogram and the average frequency of all gray values.
Conventional histogram equalization counts histogram distribution based on cumulative distribution function, but since the duty ratio of each gray value needs to be calculated, if the duty ratio of a certain gray value is extremely small, the cumulative distribution function is calculatedThere is a possibility that the data is merged, i.e., the image data is changed. For example, when the duty ratio of a certain gradation value is 0.0001, when the map is calculated by the cumulative distribution function,and (3) withThe difference between the calculated results is less than the gray value minimum unit 1, whereinRepresenting gray values, two gray levels are combined, namely original image data is lost, compared with the original image, the histogram equalization result only changes the gray distribution of the image and does not eliminate the statistical characteristic of the image, the purpose of the embodiment is to encrypt the image, although the gray distribution is changed to enable the image to have certain confidentiality, the image information is not changed, and therefore the embodiment achieves the purpose of eliminating the statistical characteristic by calculating the frequency distribution of each gray value and performing self-adaptive frequency conversion on different gray levels on the basis of equalization.
Any channel image corresponding to the image to be encrypted is recorded as an image to be processed, and the image to be processed will be taken as an example in the embodiment, and the encryption processing can be performed on other channel images corresponding to the image to be encrypted and each channel image corresponding to other RGB images by adopting the method provided by the embodiment; counting the gray value of each pixel point in the image to be processed, constructing a corresponding gray histogram based on the gray values of all the pixel points in the image to be processed, and marking the gray histogram as an initial gray histogram, as shown in fig. 2, wherein the horizontal axis is the gray value, the horizontal axis is 0-255, the vertical axis is the frequency corresponding to each gray value, but due to the randomness of the image, part of gray values do not appear frequently, so that the corresponding frequency is 0, and most of the gray values are extremely dark and extremely bright areas, the gray distribution of the pixel points in the image is generally not 0-255, the gray of the image is more concentrated, and the existence information of the highlight area and the extremely dark area is less; meanwhile, in order to increase the difference between the encrypted image and the original image, the contrast of the image can be increased by stretching, and the detail information of the image is embodied. Stretching the initial gray level histogram to ensure that gray levels are distributed in an image more uniformly, and constructing a formula to adjust each gray level value with the frequency of non-0 in the initial gray level histogram to obtain a target gray level value corresponding to each gray level value with the frequency of non-0; the target gray value corresponding to the ith gray value of frequency non-0 is:
wherein ,for a target gray value corresponding to the i-th gray value of frequency non-0,an ith gray value of frequency non-0,for the maximum gray value of the pixel point in the image to be processed,for the minimum gray value of the pixel point in the image to be processed,,is rounded downwards.
The formula constructed in this embodiment can distribute the target gray value overBy stretching the gray distribution, the contrast of the image is increased, and the image information is highlighted; by adopting the above formula, a target gray value corresponding to the ith gray value with a frequency other than 0 can be obtained, for example: if it isAt the point of 50 a,at the time of 40 a, the number of the components is,180, then18; if it isAt the point of time of 60 a,at the time of 40 a, the number of the components is,200, then31; if it isAt the point of 150 a,at the point of 50 a,180, then192; if it isAt the point of 180 a, the number of the components is,at the point of time of 30 a,200, then255. Replacing gray values with frequency other than 0 in the image to be processed with corresponding target gray values, marking the image with the replaced gray values as a stretched gray image, and reconstructing gray straight based on the gray values of all pixel points in the stretched gray imageThe gray level histogram constructed at this time is denoted as a stretched gray level histogram as shown in fig. 3. The gray values of the pixel points are changed through histogram stretching, but the gray values are the same as the frequency distribution of the original image, the information of the image is still reserved, complementary parameters are determined according to the frequency corresponding to each target gray value, and the target gray values with more frequency are supplemented to the target gray values with less frequency according to the complementary parameters, so that the statistical characteristics are purposefully eliminated under the condition of not changing the total gray distribution.
The conventional method for eliminating statistical characteristics is to set a frequency threshold value, if the frequency corresponding to a gray value is higher than the threshold value, uniformly distributing the number of pixels higher than the threshold value in the gray value to other gray values, and repeating the steps. Therefore, this embodiment proposes a targeted frequency complementation method, and the frequencies corresponding to different gray values are selected to be optimally complemented by analyzing the frequency distribution in the histogram, where the optimal judgment standard is as follows: both gray frequencies can eliminate statistical properties after complementation; when the gray distribution of each gray value is more similar to the average frequency of all gray values, the weaker the statistical characteristic is, namely, the smaller the information quantity of the image exists; thus calculating the average frequency of all gray values, i.e , wherein ,for the average frequency of all gray values,for the total number of rows of pixels in the image to be processed,the total column number of pixel points in the image to be processed.
When the frequency corresponding to each gray value is similar to the average frequency of all gray values, the statistical characteristic is reduced. For the j-th gray value: calculating the difference value between the frequency corresponding to the gray value and the average frequency of all the gray values, marking the difference value as a first difference value, and taking the ratio of the first difference value to the average frequency of all the gray values as a complementary parameter of the gray values; the calculation formula of the complementary parameter corresponding to the jth gray value is as follows:
wherein ,for the frequency corresponding to the jth gray value,for the average frequency of all gray values,is the complementary parameter of the jth gray value.
When the frequency corresponding to the jth gray value is greater than the average frequency of all gray values, the complementary parametersThe larger the frequency corresponding to the jth gray value is, the larger the value of the complementary parameter is; when the frequency corresponding to the jth gray value is smaller than or equal to the average frequency of all gray values, the complementary parametersAnd the smaller the frequency corresponding to the jth gray value, the more the value of the complementary parameter approaches to-1.
By adopting the method, the complementary parameter of each gray value in the stretched gray histogram can be obtained.
And step S3, obtaining each optimal gray value set based on the complementary parameters, and carrying out complementary operation on the frequencies corresponding to the gray values in each optimal gray value set according to the frequencies corresponding to the gray values in each optimal gray value set and the average frequencies of all gray values to obtain an encrypted image.
In this embodiment, in step S2, complementary parameters of each gray value in the stretched gray histogram are obtained, all complementary parameters are ordered in order from large to small, a complementary parameter sequence is generated, and the maximum value and the minimum value of all complementary parameters in the complementary parameter sequence are distributed at two ends of the sequence respectively.
The specific acquisition process of the complementary gray value pair is as follows: setting statistical characteristic thresholdIn the present embodimentThe value of (2) is 0.1, and in the specific application, the implementer can set according to specific conditions; selecting the 1 st complementary parameter in the complementary parameter sequenceAnd the last 1 complementary parameter in the complementary parameter sequenceAs an initial value, calculate,Is the complementary determination value of the 1 st complementary parameter and the kth complementary parameter in the complementary parameter sequence,is the total number of complementary parameters in the complementary parameter sequence; if it isThe frequency of the two gray values is complementary, and the optimal gray value set needs to be found when When the absolute value of the difference value representing the minimum frequency and the average frequency is larger than the absolute value of the difference value of the maximum frequency and the average frequency, the selection method of the optimal gray complementary pair comprises the following steps: from gray value 255, go down until calculated,Is the 1 st complementary parameter in the complementary parameter sequenceAnd a complementary determination value of a complementary parameter of the gradation value b,is the 1 st complementary parameter in the complementary parameter sequenceAnd a complementary determination value of a complementary parameter of the gradation value b-1,to take absolute value, the 1 st complementary parameter in the complementary parameter sequenceThe corresponding gray value and gray value b form an optimal gray value set, and the 1 st complementary parameter in the complementary parameter sequence is deletedAnd the complementary parameters of the gray value b, such as:then the 1 st complementary parameter in the complementary parameter sequenceThe corresponding gray values and gray values 238 form an optimal gray value set; when (when)And is also provided withWhen the absolute value of the difference value representing the minimum frequency and the average frequency is smaller than or equal to the absolute value of the difference value of the maximum frequency and the average frequency, the selection method of the optimal gray complementary pair comprises the following steps: traversing from gray value 0 upwards until calculated,Is the complementary determination value of the complementary parameter of the gray value a and the kth complementary parameter in the complementary parameter sequence, Is the complementary determination value of the complementary parameter of the gray value a and the kth complementary parameter in the complementary parameter sequence,in order to take the absolute value, the gray value a and the gray value corresponding to the kth complementary parameter in the complementary parameter sequence form an optimal gray value set, and the kth complementary parameter in the complementary parameter sequence and the complementary parameter of the gray value a are deleted, for example:the gray value corresponding to the kth complementary parameter in the sequence of complementary parameters and the gray value 15 form an optimal gray value set. By adopting the method, the gray values corresponding to all the complementary parameters in the complementary parameter sequence are traversed, and the optimal gray value set is searched to obtain a plurality of optimal gray value sets; if the number of gray values in the optimal gray value set is equal to 2, marking one gray value in the optimal gray value set as a first gray value, and marking the other gray value in the optimal gray value set as a second gray value; calculating the sum of the frequency corresponding to the first gray value before complementation and the frequency corresponding to the second gray value before complementation, and marking the sum as a frequency index, and taking the difference between the frequency index and the average frequency of all gray values as the first gray value And taking the average frequency of all the gray values as the frequency corresponding to the second gray value after complementation. For the p-th optimal gray value set, the two gray values in the optimal gray value set are respectively gray valuesAnd gray valueGray value ofAnd gray valueThe corresponding frequencies after complementation are respectively:
wherein ,is a gray valueAfter the complementation the corresponding frequency is given,is a gray valueAfter the complementation the corresponding frequency is given,is a gray valueThe corresponding frequency before the complementation,is a gray valueThe corresponding frequency before the complementation,is the average frequency of all gray values.
Since the gray distribution of the pixels in the image has randomness, gray values with larger difference from the average frequency may exist, so thatIs not constant, i.eIs equal to or greater thanIf the complementary parameters corresponding to the optimal gray value set are deleted, the complementary parameters in the complementary parameter sequence do not exist, and then the subsequent processing is not carried out; if the complementary parameters corresponding to the optimal gray value set are deleted and partial complementary parameters exist in the complementary parameter sequence after the complementary parameter operation, the remaining complementary parameters in the complementary parameter sequence are ordered from big to small, a to-be-matched parameter sequence is constructed, the data in the to-be-matched parameter sequence is the remaining complementary parameters in the complementary parameter sequence, and the 1 st complementary parameter in the to-be-matched parameter sequence is selected And the last 1 complementary parameters, wherein For the total number of complementary parameters in the sequence of parameters to be matched, ifCalculation ofUntil it meets, wherein ,for the number of complementary parameters in the sequence of parameters to be matched,for the 2 nd complementary parameter in the sequence of parameters to be matched,for the 3 rd complementary parameters in the sequence of parameters to be matched,for the penultimate in the parameter sequence to be matchedThe number of complementary parameters is chosen,for the 1 st complementary parameter in the parameter sequence to be matched and the last complementary parameter in the parameter sequence to be matchedThe complementary determination values of the respective complementary parameters,for the 1 st complementary parameter in the parameter sequence to be matched and the last complementary parameter in the parameter sequence to be matchedComplementary determination values of the complementary parameters, wherein the gray value corresponding to the 1 st complementary parameter in the parameter sequence to be matched and the last complementary parameter in the parameter sequence to be matchedGray value formation corresponding to complementary parametersThe optimal gray value set, i.e. the one-to-many relationship. If the number of gray values in the optimal gray value set is greater than 2, marking the gray value with the maximum number of the corresponding optimal complementary gray values in the optimal gray value set as a third gray value, marking all other gray values except the third gray value in the optimal gray value set as a fourth gray value, taking the average frequency of all the gray values as the frequency corresponding to the third gray value after complementation, calculating the product of the average frequency of all the gray values and the number of the fourth gray value, marking the product as a first product, and taking the difference value between the frequency corresponding to the third gray value before complementation and the first product as the frequency corresponding to the fourth gray value after complementation. For the optimal gray value set, the corresponding frequency after the gray values of the 1 st complementary parameter in the parameter sequence to be matched are complementary is , wherein ,for the corresponding frequency after the gray value of the 1 st complementary parameter in the parameter sequence to be matched is complementary, the last parameter in the parameter sequence to be matchedThe corresponding frequencies after the gray values of the complementary parameters are complementary are equal and are the average frequency of all the gray valuesThe method comprises the steps of carrying out a first treatment on the surface of the If it isCalculation of,For the front in the parameter sequence to be matchedThe complementary parameter and the first parameter in the parameter sequence to be matchedAnd repeating the method to determine the optimal gray value set, and obtaining the corresponding frequency after each gray value in the optimal gray value set is complemented.
Since the average frequency of all gray values is a constant valueAfter complementation, the frequency is necessarily within the distribution range of the frequency with weak statistical characteristics, so that all gray values can find the optimal gray value complementary with the gray values, and the frequency corresponding to the complementary gray values is obtained. By adopting the method, the frequency distribution range of the two gray values in each optimal gray value set is made to be the same by complementing the frequency of each optimal gray value setI.e. the statistical properties of the gray values of the pixels in the image are eliminated.
So far, the corresponding frequency after all gray values are complemented is obtained, and the original image is processed according to the corresponding frequency after each gray value is complemented, wherein the specific processing process is as follows: if the number of gray values in the optimal gray value set is 2, for any one of the optimal gray value sets, calculating the absolute value of the difference value between the frequency corresponding to each gray value before complementation and the frequency corresponding to each gray value after complementation, taking the absolute value as the complementation number of each gray value, randomly selecting the complementation pixel points with the number equal to the complementation number, and enabling the gray values of the selected complementation pixel points to be equal to the optimal complementation gray value. For any one "one-to-many" optimal gray value set, i.e., the number of gray values in the optimal gray value set is greater than 2, divided by The number of the other pixel points except the gray value is the average frequency. In this embodiment, by performing statistical characteristic analysis on the frequency of each gray value, an optimal gray value set is found so that all gray values are obtainedThe values can find the gray value which is the optimal complement to the value, and compared with the existing method for eliminating the statistical characteristics, the method provided by the embodiment avoids repeated threshold distribution calculation, only performs one transformation operation on each gray value, and reduces the calculated amount and the calculated cost.
The method provided by the embodiment can obtain the encrypted image of each channel of the image to be encrypted by encrypting the image data by extracting the statistical characteristics.
The encrypted image is generated uniquely according to the original image, has uniqueness, and changes the original image to cause the frequency corresponding to the gray value to change, so that a new image constructed through frequency analysis changes, namely the method provided by the embodiment has sensitivity to the image; the generated encrypted image eliminates the statistical characteristic through frequency complementation, so that the possibility of being cracked is greatly reduced, and the encrypted image obtained by the embodiment has a good encryption effect.
The original image of each channel of the image to be encrypted is respectively 、、The encrypted image of each channel of the image to be encrypted is respectively、、Three-channel original image passing through original image、、And corresponding encrypted image、、Exclusive-or operation is performed to generate a key, namely:
wherein ,an encrypted image for the R channel of the image to be encrypted,an encrypted image for the G channel of the image to be encrypted,for the B-channel encrypted image of the image to be encrypted,is an exclusive or operator.
Since the exclusive-or operation is reversible, and the image is encrypted、、Has uniqueness, so the embodiment performs exclusive OR operation on the original image and the encrypted image to obtain a corresponding secret key、、. In the embodiment, the ciphertext image is obtained by splitting the image and analyzing the frequency and encrypting the image、、And a key、、And transmitting the secret key and the ciphertext, storing the ciphertext and the secret key, decrypting the ciphertext by using the secret key and performing anomaly detection by using artificial intelligence.
After the image is encrypted to generate the secret key and the ciphertext, the image is integrated into video to be transmitted and stored in the server, when the artificial intelligence needs to perform anomaly analysis on the video, a data downloading request is sent to the server, after the server receives the downloading request, the encrypted video and the secret key are transmitted to an anomaly analysis system, the analysis system splits the video into images according to frames after receiving the encrypted video, and decrypts the image, and for the image to be encrypted, the decryption process is as follows: ,,Obtaining an original image of each channel of an image to be encrypted、、Original image of three channels、、Combining to obtain an original RGB image; by adopting the method, all original RGB images can be obtained, all the original RGB images are combined to obtain the original video data, and the original video data is sent to an artificial intelligent anomaly analysis module for anomaly analysis.
According to the method, a plurality of optimal gray value sets are obtained according to the distribution condition of an initial gray histogram corresponding to an image to be processed, the frequency corresponding to each gray value in each optimal gray value set is subjected to complementary operation based on a frequency complementary method, the statistical characteristics of image data are eliminated to generate an encrypted image, the existing threshold average distribution statistical characteristic elimination method has the problems of threshold subjectivity and computational complexity, the frequency corresponding to each gray value is subjected to complementary operation only once, compared with the existing method, the operation cost is reduced, the influence of human subjective factors on an image encryption result is avoided, the purposes of eliminating the statistical characteristics of the image data and encrypting are achieved, and the risk of leakage of video data is reduced. The method comprises the steps that an optimal gray value set is obtained, so that the frequency corresponding to each gray value in the optimal gray value set is subjected to complementary operation, the statistical characteristics of image data are eliminated, the gray values of pixel points in an image to be processed are possibly more intensively distributed in a certain gray interval, the statistical characteristics cannot be weakened and information in the image cannot be well protected only by histogram equalization although the gray values of the image can be uniformly distributed between 0 and 255, and therefore, a target histogram gray value corresponding to each gray value, which is not 0, in the image to be processed is obtained according to the frequency corresponding to each gray value in the image to be processed, the maximum gray value and the minimum gray value of the pixel points, and then the initial gray is subjected to stretching operation; when the frequency corresponding to the gray value of the pixel point in the image to be processed is similar to the average frequency of all the gray values, the statistical characteristic of the image data is low, so that the complementary parameters of all the gray values are obtained according to the frequency corresponding to each gray value in the stretched gray histogram and the average frequency of all the gray values, and further an optimal gray value set is obtained based on the complementary parameters, the statistical characteristic of the image data can be broken, and the risks of tampering and leakage of the video data are effectively reduced.
Video data processing system embodiments based on artificial intelligence:
the video data processing system based on artificial intelligence of the embodiment comprises a memory and a processor, wherein the processor executes a computer program stored in the memory to realize the video data processing method based on artificial intelligence.
Since the video data processing method based on the artificial intelligence has been described in the embodiment of the video data processing method based on the artificial intelligence, the embodiment does not describe the video data processing method based on the artificial intelligence again.
Claims (8)
1. A method for processing video data based on artificial intelligence, the method comprising the steps of:
acquiring video data to be processed, and marking any frame of gray level image in the video data as an image to be processed;
acquiring an initial gray level histogram corresponding to the image to be processed, acquiring a target gray level value corresponding to each gray level value which is not 0 in the initial gray level histogram according to the frequency corresponding to each gray level value in the initial gray level histogram, the maximum gray level value of the pixel point in the image to be processed and the minimum gray level value of the pixel point in the image to be processed, and acquiring a stretched gray level histogram based on the target gray level value; obtaining complementary parameters of each gray value in the stretched gray histogram according to the frequency corresponding to each gray value in the stretched gray histogram and the average frequency of all gray values;
Obtaining each optimal gray value set based on the complementary parameters, and carrying out complementary operation on the frequencies corresponding to the gray values in each optimal gray value set according to the frequencies corresponding to the gray values in each optimal gray value set and the average frequencies of all gray values to obtain an encrypted image;
and obtaining complementary parameters of each gray value in the stretched gray histogram according to the frequency corresponding to each gray value in the stretched gray histogram and the average frequency of all gray values, wherein the complementary parameters comprise:
respectively calculating the difference value between the frequency corresponding to each gray value and the average frequency of all gray values, and marking the difference value as a first difference value; and taking the ratio of the first difference value to the average frequency of all the gray values as the complementary parameter of each gray value.
2. The artificial intelligence based video data processing method of claim 1, wherein the obtaining each optimal gray value set based on the complementary parameters comprises:
sequencing all complementary parameters in the sequence from big to small to generate a complementary parameter sequence;
selecting the 1 st complementary parameter and the last 1 complementary parameter in the complementary parameter sequence as initial values, calculating the sum of the two initial values to be used as complementary judgment values of the 1 st complementary parameter and the last 1 complementary parameter, if the absolute value of the complementary judgment values of the 1 st complementary parameter and the last 1 complementary parameter is smaller than a statistical characteristic threshold value and the complementary judgment values of the 1 st complementary parameter and the last 1 complementary parameter are smaller than 0, traversing downwards from the gray value 255, calculating the complementary judgment values of the 1 st complementary parameter and the complementary parameters of all gray values until the complementary judgment values of the 1 st complementary parameter and the complementary parameters of the previous gray value are smaller than the complementary judgment values of the 1 st complementary parameter and the complementary parameters of the next gray value, taking the gray value corresponding to the 1 st complementary parameter and the corresponding previous gray value as an optimal gray value set, and deleting the complementary parameters of all gray values in the optimal gray value set in the complementary parameter sequence; if the absolute value of the complementary judgment value of the 1 st complementary parameter and the last 1 complementary parameter is smaller than the statistical characteristic threshold value, and the complementary judgment value of the 1 st complementary parameter and the last 1 complementary parameter is larger than or equal to 0, traversing upwards from the gray value 0 until the complementary judgment value of the 1 st complementary parameter and the complementary judgment value of the complementary parameter of the previous gray value is smaller than the complementary judgment value of the 1 st complementary parameter and the complementary judgment value of the complementary parameter of the subsequent gray value, and taking the gray value corresponding to the 1 st complementary parameter and the corresponding previous gray value as an optimal gray value set; and by analogy, updating the initial value, traversing all complementary parameters in the complementary parameter sequence to obtain a plurality of optimal gray value sets, and deleting the complementary parameters of each gray value in the optimal gray value sets in the complementary parameter sequence.
3. The method for processing video data based on artificial intelligence according to claim 2, wherein if complementary parameters remain in the complementary parameter sequence after the complementary parameter operation of each gray value in the optimal gray value set is deleted, the complementary parameters remaining in the complementary parameter sequence are ordered in the order from big to small, a parameter sequence to be matched is constructed, an optimal gray value complementary to the gray value corresponding to the 1 st complementary parameter is obtained according to the complementary judgment value of the 1 st complementary parameter and other complementary parameters in the parameter sequence to be matched, the gray value corresponding to the 1 st complementary parameter and each optimal gray value complementary to the 1 st complementary parameter form an optimal gray value set, and the other complementary parameters sequentially traverse forward from the last 1 complementary parameters in the parameter sequence to be matched; and similarly, traversing the gray values corresponding to all complementary parameters in the parameter sequence to be matched to obtain each optimal gray value set.
4. A video data processing method based on artificial intelligence according to claim 3, wherein obtaining an optimal gray value complementary to the gray value corresponding to the 1 st complementary parameter according to the complementary determination value of the 1 st complementary parameter and other complementary parameters in the parameter sequence to be matched, comprises:
If it isThen calculateUntil it meetsLast +.>The gray value corresponding to the complementary parameter is used as the optimal gray value complementary to the gray value corresponding to the 1 st complementary parameter, wherein +.>To take absolute value, +.>For the 1 st complementary parameter in the sequence of parameters to be matched,/->For the last 1 complementary parameters in the sequence of parameters to be matched, < > in->For the number of complementary parameters in the sequence of parameters to be matched, < +.>For the 2 nd complementary parameter in the sequence of parameters to be matched,>for the 3 rd complementary parameter of the sequence of parameters to be matched,>for the last but one in the parameter sequence to be matchedComplementary parameters (a)>For the 1 st complementary parameter in the parameter sequence to be matched and the last +.>Complementary determination value of the respective complementary parameter, +.>For the 1 st complementary parameter in the parameter sequence to be matched and the last +.>Complementary determination values of the respective complementary parameters;
if it isCalculate +.>Obtaining an optimal gray value complementary to the gray value corresponding to the 1 st complementary parameter, wherein +_>For the first +.>The complementary parameters are the first of the sequence of parameters to be matched>Complementary determination values of the respective complementary parameters.
5. The method for processing video data based on artificial intelligence according to claim 1, wherein the obtaining the target gray value corresponding to each gray value with a frequency other than 0 in the initial gray histogram according to the frequency corresponding to each gray value in the initial gray histogram, the maximum gray value of the pixel point in the image to be processed, and the minimum gray value of the pixel point in the image to be processed comprises:
Calculating a target gray value corresponding to the ith gray value with the frequency of non-0 in the initial gray histogram by adopting the following formula:
wherein ,for the target gray value corresponding to the ith gray value of frequency non-0,/th gray value>An ith gray value of frequency non-0,for the maximum gray value of the pixel point in the image to be processed,/for>The minimum gray value of the pixel point in the image to be processed is ⌊ ⌋, which is rounded downwards.
6. The artificial intelligence based video data processing method of claim 1, wherein the obtaining a stretched gray level histogram based on the target gray level value comprises: and replacing each gray value with a target gray value corresponding to the gray value, which is not 0, in the image to be processed, reconstructing a gray histogram based on the gray values of the pixel points in the image to be processed after the replacement is completed, and marking the gray histogram as a stretched gray histogram.
7. The method for processing video data based on artificial intelligence according to claim 1, wherein the performing complementary operation on the frequencies corresponding to the gray values in the optimal gray value sets to obtain the encrypted image according to the frequencies corresponding to the gray values in the optimal gray value sets and the average frequency of all the gray values comprises:
If the number of gray values in the optimal gray value set is equal to 2, marking one gray value in the optimal gray value set as a first gray value, and marking the other gray value in the optimal gray value set as a second gray value; calculating the sum of the frequency corresponding to the first gray value before complementation and the frequency corresponding to the second gray value before complementation, marking the sum as a frequency index, taking the difference value of the frequency index and the average frequency of all gray values as the frequency corresponding to the first gray value after complementation, and taking the average frequency of all gray values as the frequency corresponding to the second gray value after complementation;
if the number of gray values in the optimal gray value set is greater than 2, marking the gray value with the maximum number of the corresponding optimal complementary gray values in the optimal gray value set as a third gray value, marking all other gray values except the third gray value in the optimal gray value set as a fourth gray value, taking the average frequency of all the gray values as the frequency corresponding to the third gray value after complementation, calculating the product of the average frequency of all the gray values and the number of the fourth gray value, marking the product as a first product, and taking the difference value of the frequency corresponding to the third gray value before complementation and the first product as the frequency corresponding to the fourth gray value after complementation;
And processing the original image based on the frequency after the complementation of each gray value, taking the frequency difference value of the complementation and the complementation gray value as the complementation frequency number, randomly selecting the complementation gray value of the complementation frequency number, and enabling the gray value of the selected complementation pixel point to be equal to the optimal complementation gray value, thereby obtaining the encrypted image.
8. An artificial intelligence based video data processing system comprising a memory and a processor, wherein the processor executes a computer program stored in the memory to implement the artificial intelligence based video data processing method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310146591.2A CN115834792B (en) | 2023-02-22 | 2023-02-22 | Video data processing method and system based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310146591.2A CN115834792B (en) | 2023-02-22 | 2023-02-22 | Video data processing method and system based on artificial intelligence |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115834792A CN115834792A (en) | 2023-03-21 |
CN115834792B true CN115834792B (en) | 2023-05-12 |
Family
ID=85522025
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310146591.2A Active CN115834792B (en) | 2023-02-22 | 2023-02-22 | Video data processing method and system based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115834792B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116033088B (en) * | 2023-03-27 | 2023-06-16 | 山东爱特云翔计算机有限公司 | Safe transmission method and system for video big data |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101586956A (en) * | 2009-06-18 | 2009-11-25 | 上海交通大学 | River water level monitoring method based on monocular camera |
CN101751564A (en) * | 2010-02-04 | 2010-06-23 | 华南理工大学 | Intravenous grain extraction method based on maximal intra-neighbor difference vector diagram |
CN102306375A (en) * | 2011-08-31 | 2012-01-04 | 北京航空航天大学 | Segmentation method for synthetic aperture radar (SAR) and visible light pixel-level fused image |
WO2021093648A1 (en) * | 2019-11-11 | 2021-05-20 | 阿里巴巴集团控股有限公司 | Watermark information embedding method and apparatus |
CN114943848A (en) * | 2022-07-25 | 2022-08-26 | 南通德晋昌光电科技有限公司 | Crack identification method in nickel screen laser cladding process |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7532755B2 (en) * | 2004-01-22 | 2009-05-12 | Lexmark International, Inc. | Image classification using concentration ratio |
CA2571666A1 (en) * | 2006-12-12 | 2008-06-12 | Diversinet Corp. | Secure identity and personal information storage and transfer |
-
2023
- 2023-02-22 CN CN202310146591.2A patent/CN115834792B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101586956A (en) * | 2009-06-18 | 2009-11-25 | 上海交通大学 | River water level monitoring method based on monocular camera |
CN101751564A (en) * | 2010-02-04 | 2010-06-23 | 华南理工大学 | Intravenous grain extraction method based on maximal intra-neighbor difference vector diagram |
CN102306375A (en) * | 2011-08-31 | 2012-01-04 | 北京航空航天大学 | Segmentation method for synthetic aperture radar (SAR) and visible light pixel-level fused image |
WO2021093648A1 (en) * | 2019-11-11 | 2021-05-20 | 阿里巴巴集团控股有限公司 | Watermark information embedding method and apparatus |
CN114943848A (en) * | 2022-07-25 | 2022-08-26 | 南通德晋昌光电科技有限公司 | Crack identification method in nickel screen laser cladding process |
Also Published As
Publication number | Publication date |
---|---|
CN115834792A (en) | 2023-03-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Chai et al. | An image encryption algorithm based on chaotic system and compressive sensing | |
Adam et al. | A 3des double–layer based message security scheme | |
CN115242475B (en) | Big data safety transmission method and system | |
CN115297363B (en) | Video data encryption transmission method based on Huffman coding | |
Ping et al. | Generating visually secure encrypted images by partial block pairing-substitution and semi-tensor product compressed sensing | |
CN115834792B (en) | Video data processing method and system based on artificial intelligence | |
Ren et al. | Reversible data hiding in encrypted binary images by pixel prediction | |
Guan et al. | An efficient high-capacity reversible data hiding scheme for encrypted images | |
Su et al. | Visualized multiple image selection encryption based on log chaos system and multilayer cellular automata saliency detection | |
Wang et al. | TPE-ISE: approximate thumbnail preserving encryption based on multilevel DWT information self-embedding | |
Ratan et al. | Security Analysis of Bit-plane Level Image Encryption Schemes. | |
CN113382128B (en) | Bit plane compressed encrypted image reversible information hiding method | |
Islam et al. | Denoising and error correction in noisy AES-encrypted images using statistical measures | |
CN116996628B (en) | Network data transmission protection method | |
CN115225771B (en) | Method and device for hiding reversible information of encrypted image and computer equipment | |
CN114969796A (en) | Image steganography method and system combining QR (quick response) code and S-box chaotic scrambling | |
Zhang et al. | Color Image Encryption Based on LSS-Type Coupled Mapped Lattice | |
Mostafa et al. | A new chaos based medical image encryption scheme | |
Tralic et al. | Robust image encryption based on balanced cellular automaton and pixel separation | |
RU2288544C2 (en) | Method for embedding additional information into digital images | |
Yassin | Data Hiding Technique for Color Images using Pixel Value Differencing and Chaotic Map | |
Zou et al. | A meaningful image encryption algorithm based on prediction error and wavelet transform | |
Waghmare et al. | Holo-entropy and advanced encryption standard for wavelet-based image steganography | |
CN113949782B (en) | Complex chaotic system data encryption method based on cubic memristor | |
CN115426199B (en) | Website data safety protection method |
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 |