CN115776410A - Face data encryption transmission method for terminal identity authentication - Google Patents
Face data encryption transmission method for terminal identity authentication Download PDFInfo
- Publication number
- CN115776410A CN115776410A CN202310043171.1A CN202310043171A CN115776410A CN 115776410 A CN115776410 A CN 115776410A CN 202310043171 A CN202310043171 A CN 202310043171A CN 115776410 A CN115776410 A CN 115776410A
- Authority
- CN
- China
- Prior art keywords
- characteristic image
- hog
- hog characteristic
- gradient
- image
- 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
Images
Abstract
The invention relates to the technical field of data encryption, in particular to a face data encryption transmission method for terminal identity authentication, which comprises the following steps: the method comprises the steps of collecting a face image, segmenting the face image to obtain a plurality of same image blocks, obtaining a first importance degree of an HOG characteristic image, obtaining a second importance degree of the HOG characteristic image, obtaining a comprehensive importance degree of each HOG characteristic image, obtaining a final HOG characteristic image of each image block, obtaining an encrypted image and transmitting the encrypted image.
Description
Technical Field
The invention relates to the technical field of data encryption, in particular to a face data encryption transmission method for terminal identity authentication.
Background
Face recognition is a biometric technology for identity recognition based on facial feature information of a person, and implementation scenarios for face authentication of a terminal are increasing day by day, for example, face recognition of a mobile phone during payment and use in places with access scenario restrictions such as a high-speed rail station, so that in order to prevent face data from being cracked, payment loss is caused, and encryption of face data is also synchronous.
The traditional encryption mode is an attack mode of carrying out normalization on a gradient direction histogram corresponding to an HOG characteristic image to resist statistical analysis, but the conversion mode is single, the other attack modes cannot be effectively resisted, and particularly the safety of data is difficult to guarantee when violent cracking occurs.
Disclosure of Invention
The invention provides a face data encryption transmission method for terminal identity authentication, which aims to solve the problem that the safety of data is difficult to ensure when the existing face data is cracked violently.
The invention relates to a face data encryption transmission method for terminal identity authentication, which adopts the following technical scheme:
collecting a face image, and segmenting the face image to obtain a plurality of same image blocks;
acquiring a HOG characteristic image of each image block, and taking the standard deviation of the gradient amplitudes of all gradient directions in each HOG characteristic image as a first importance degree of each HOG characteristic image;
acquiring the integral gradient direction of each HOG characteristic image according to the horizontal gradient amplitude component and the vertical gradient amplitude component of the gradient amplitude in all the gradient directions in each HOG characteristic image; acquiring a second importance degree of each HOG characteristic image according to a direction deviation value of the overall gradient direction of each HOG characteristic image and the overall gradient direction of each HOG characteristic image in the neighborhood and a gradient amplitude difference value of each HOG characteristic image and each HOG characteristic image in the neighborhood in the corresponding gradient direction;
acquiring the comprehensive importance degree of each HOG characteristic image according to the first importance degree and the second importance degree;
obtaining an initial transformation gradient amplitude value of each gradient direction according to the gradient amplitude value mean value of each gradient direction in each HOG characteristic image and the gradient amplitude value of each gradient direction; obtaining a target gradient amplitude of each gradient direction in each HOG characteristic image by using the gradient amplitude of each gradient direction in each HOG characteristic image and the initial transformation gradient amplitude of each gradient direction;
obtaining a transformation coefficient of each gradient direction according to the initial transformation gradient amplitude and the target gradient amplitude of each gradient direction, obtaining a final transformation gradient amplitude of each gradient direction of the HOG characteristic image according to the transformation coefficient and the initial transformation gradient amplitude of each gradient direction and the comprehensive importance degree of the HOG characteristic image, and obtaining a final HOG characteristic image of each image block according to all the final transformation gradient amplitudes;
and obtaining an encrypted image according to all the final HOG characteristic images, and transmitting the encrypted image, the corresponding transformation coefficient of each final HOG characteristic image and the comprehensive importance degree.
Preferably, the method further comprises:
acquiring each HOG characteristic image and a target HOG characteristic image which is symmetrical about a vertical central line of the face image;
acquiring the directional symmetry degree of each HOG characteristic image in the neighborhood of the HOG characteristic image and the HOG characteristic image at the symmetrical position in the neighborhood of the corresponding target HOG characteristic image according to the overall gradient direction of each HOG characteristic image and the corresponding target HOG characteristic image;
acquiring the integral gradient direction symmetry degree of the HOG characteristic image and the corresponding target HOG characteristic image in a neighborhood range according to the direction deviation value of the integral gradient direction of the HOG characteristic image and each HOG characteristic image in the neighborhood thereof and the direction symmetry degree of the HOG characteristic image at the symmetric position in the neighborhood of each HOG characteristic image in the neighborhood of the HOG characteristic image and the corresponding target HOG characteristic image;
judging whether to adjust the neighborhood size according to the sum of the direction deviation values of the overall gradient direction of the HOG characteristic image and all the HOG characteristic images in the neighborhood of the HOG characteristic image, and obtaining the final neighborhood size corresponding to each HOG characteristic image;
normalizing according to the length of the final neighborhood size corresponding to each HOG characteristic image to obtain the necessary degree of the HOG characteristic image;
acquiring an adjustment value of each HOG characteristic image according to the corresponding necessity degree of the HOG characteristic image, the symmetry degree of the whole gradient direction and the sum of the gradient amplitudes of the HOG characteristic image and the corresponding target HOG characteristic image;
and adjusting the comprehensive importance degree of each corresponding HOG characteristic image according to the adjustment value to obtain the final comprehensive importance degree.
Preferably, obtaining the final neighborhood size comprises:
when the sum of the direction deviation values of the overall gradient direction of the HOG characteristic image and all the HOG characteristic images in the neighborhood of the HOG characteristic image is smaller than a preset sum threshold, gradually increasing the neighborhood size of the HOG characteristic image to obtain an increased target neighborhood;
and acquiring the sum of the direction deviation values of the overall gradient directions of the HOG characteristic image and each HOG characteristic image in the target neighborhood, and taking the size of the corresponding target neighborhood as the final neighborhood size when the sum of the direction deviation values of the overall gradient directions of the HOG characteristic image and each HOG characteristic image in the target neighborhood is greater than or equal to a preset sum threshold.
Preferably, the degree of necessity for obtaining the HOG feature image includes:
acquiring the length of the corresponding final neighborhood size and the length of the minimum neighborhood size in the lengths of the final neighborhood sizes corresponding to all the HOG characteristic images;
acquiring a target neighborhood size corresponding to the normalized HOG characteristic image according to the length of the corresponding final neighborhood size, the length of the minimum neighborhood size and the length of the final neighborhood size corresponding to each HOG characteristic image;
and taking the length corresponding to the target neighborhood size as the necessary degree of the HOG characteristic image.
Preferably, the calculation formula of the directional symmetry degree of each HOG feature image in the neighborhood of the HOG feature image and the HOG feature image at the symmetric position in the neighborhood of the corresponding target HOG feature image is:
in the formula (I), the compound is shown in the specification,
representing HOG feature images
HOG feature images in the neighborhood of (1)
With corresponding target HOG characteristic image
And HOG feature images
The directional symmetry degree of the position-symmetric HOG characteristic image;
Preferably, the obtaining of the degree of symmetry of the overall gradient direction of the HOG feature image and the target HOG feature image corresponding to the HOG feature image in the neighborhood range includes:
acquiring a direction deviation value of the overall gradient direction of the HOG characteristic image and each HOG characteristic image in the neighborhood thereof, and a sum value of the ratio of the direction symmetry degree of each HOG characteristic image in the neighborhood of the HOG characteristic image and the HOG characteristic image at the symmetric position in the neighborhood of the corresponding target HOG characteristic image;
and taking the sum value as the degree of symmetry of the HOG characteristic image and the corresponding target HOG characteristic image in the whole gradient direction in the neighborhood range.
Preferably, the calculation formula of the adjustment value of each HOG feature image is:
in the formula (I), the compound is shown in the specification,
representing HOG feature images
The adjustment value of (a);
Preferably, the obtaining the second degree of importance of each HOG feature image includes:
acquiring the sum of absolute values of gradient amplitude differences of the HOG characteristic image and the HOG characteristic image in the neighborhood of the HOG characteristic image in all corresponding gradient directions;
and taking the sum of products of the absolute value sum of the gradient amplitude difference values corresponding to all the HOG characteristic images in the neighborhood of the HOG characteristic image and the direction deviation value of the overall gradient direction as the second importance degree of the HOG characteristic image.
Preferably, obtaining the final transform gradient magnitude for each gradient direction of the HOG feature image comprises:
obtaining the product of the transformation coefficient and the comprehensive importance degree;
and acquiring the ratio of the initial transformation gradient amplitude corresponding to each gradient direction in the HOG characteristic image to the product of the transformation coefficient and the comprehensive importance degree, and taking the ratio as the final transformation gradient amplitude of each gradient direction of the HOG characteristic image.
Preferably, the method further comprises the following steps: decrypting the encrypted data, the decrypting step comprising:
acquiring the gradient of each HOG characteristic image before transformation in each gradient direction according to each final HOG characteristic image, the corresponding transformation coefficient and the comprehensive importance degree;
acquiring the HOG characteristic image according to the gradient of the HOG characteristic image before transformation in each gradient direction;
and obtaining a face image according to all the HOG characteristic images.
The face data encryption transmission method for terminal identity authentication has the beneficial effects that:
because the gradient directions of the regions corresponding to different face organs in the face image are different, the face image is divided into a plurality of image blocks, then HOG characteristic images representing each image block are obtained, the first importance degree of the HOG characteristic images is reflected by the standard difference of the gradient amplitudes of the HOG characteristic images in all the gradient directions, the larger the standard difference is, the larger the gradient amplitude difference is, the larger the corresponding first importance degree is, namely, the first importance degree reflects the importance degree of the HOG characteristic image per se, then, the direction deviation value and the gradient amplitude difference value of the HOG characteristic images and all the HOG characteristic images in the neighborhood thereof are used for reflecting the second importance degree of the HOG characteristic images, namely, the second importance degree reflects the importance degree of the HOG characteristic images and the HOG characteristic images in the neighborhood thereof, so the first importance degree of the HOG characteristic images is combined, the comprehensive importance degree of the HOG characteristic image is comprehensively evaluated with the second importance degree of the HOG characteristic image and the HOG characteristic image in the field thereof, so that when the HOG characteristic image is attacked, the wrong cracking of one HOG characteristic image can cause that the cracking results of all subsequent HOG characteristic images are wrong, therefore, the cracking has an avalanche effect, so that the security of the encrypted data obtained by encrypting based on the comprehensive importance degree is higher, secondly, the comprehensive importance degree represents the significance of the gradient direction in the HOG characteristic image, because the direction gradient of the region corresponding to the human face organ is different from the forehead region and the cheek region, the HOG characteristic image corresponding to the human face organ region has the significant gradient direction, if the magnitude of the significant gradient direction in the HOG characteristic image is transformed, the gradient magnitude of each HOG characteristic image in the whole image is similar, the difference between all the HOG characteristic images of the whole image is small, even if the stored encrypted data is stolen, the stored encrypted data cannot be cracked, so that the gradient of the HOG characteristic images is transformed according to the comprehensive importance degree and the transformation coefficient in each gradient direction to obtain the final transformation gradient amplitude, and the final HOG characteristic images of each image block are obtained according to the final transformation gradient amplitude, so that the gradient amplitudes corresponding to all the final HOG characteristic images are similar, namely, different degrees of comprehensive importance of the HOG characteristic images are utilized to encrypt different HOG characteristic images in different degrees, further the security of transmitted data is improved, meanwhile, each final HOG characteristic image corresponds to one key, the complexity of the key is increased, and the security of the transmitted data is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an embodiment of a face data encryption transmission method for terminal identity authentication according to the present invention;
fig. 2 is a schematic diagram of an HOG feature image and a symmetric HOG feature image in an embodiment of a face data encryption transmission method for terminal identity authentication according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention relates to a face data encryption transmission method for terminal identity authentication, which comprises the following steps:
s1, collecting a face image, and segmenting the face image to obtain a plurality of same image blocks;
specifically, the height of the collecting device is consistent with the height of the head of the collected person, the collecting device faces the person in front, a face image of the person in front is obtained, and the collected face image is subjected to person segmentation through semantic segmentationSegmentation of face region, dividing image into size
Wherein the block size is
Wherein
Is the size of the acquired face image,
an empirical value of 50 is given (the particular size implementer may be adjusted according to the particular scenario,
too large increases the definition, but the recognition speed decreases).
At this point, a face image is acquired and divided into a plurality of same image blocks.
S2, acquiring a first importance degree of the HOG characteristic image;
because the gradient directions of the pixel points corresponding to the face and the forehead area are uniform, and the gradient directions of the pixel points corresponding to the five sense organs are disordered, the HOG feature images corresponding to the five sense organs are obviously different from the cheek, and the HOG feature images corresponding to the forehead area, namely the HOG feature images corresponding to the five sense organs have obvious gradient directions, namely strong identification, so that the gradient amplitude of the gradient direction with the identification needs to be changed, the gradient amplitude of each HOG feature image in the whole face image is close, the gradient amplitude of each HOG feature image in the whole face image is smaller than the difference even if the gradient amplitude of each two HOG feature images in the whole face image is smaller, and therefore, the subsequent stored data is not easy to crack even if being stolen.
Therefore, in this embodiment, the HOG feature image of each image block is obtained first, and after each HOG feature image is obtained, each HOG feature image corresponds to one directional gradient histogram, so that a standard deviation of gradient magnitudes in all gradient directions in the directional gradient histogram corresponding to the HOG feature image is obtained, and the standard deviation is used as a first importance degree of the HOG feature image, where a calculation formula of the first importance degree is:
in the formula (I), the compound is shown in the specification,
representing HOG feature images
The standard deviation of the gradient magnitudes of all gradient directions, namely the first importance degree of the HOG feature image;
it should be noted that the superscript 9 of the summation formula represents 9 angles obtained by equally dividing 180 °, that is, 9 gradient directions corresponding to the histogram of directional gradients, and the standard deviation represents the HOG feature image
The greater the standard deviation is, the greater the corresponding gradient amplitude difference is, i.e. the gradient amplitude in one or more gradient directions is much greater than the gradient amplitudes in the other gradient directions, and secondly, the standard deviation formula is the prior art formula, which is the same as the prior art formulaThe embodiment will not be described in detail.
S3, acquiring a second importance degree of the HOG characteristic image;
specifically, the overall gradient direction of each HOG characteristic image is obtained according to the horizontal gradient amplitude component and the vertical gradient amplitude component of the gradient amplitude in all the gradient directions in each HOG characteristic image; and acquiring a second significance level of each HOG characteristic image according to the direction deviation value of the overall gradient direction of each HOG characteristic image and the overall gradient direction of each HOG characteristic image in the neighborhood and the gradient amplitude difference value of each HOG characteristic image and each HOG characteristic image in the neighborhood in the corresponding gradient direction.
Specifically, the second importance degree of each HOG feature image is acquired: calculating the gradient direction of each pixel point in the image block through the HOG direction characteristics
And gradient magnitude
And statistically putting the data into a histogram of directional gradients to obtain a histogram of directional gradients, wherein the abscissa of the histogram of directional gradients equally divides 180 ° into 9 angles, that is, the angles are 9 gradient directions, and the 9 gradient directions are sequentially:
(ii) a During calculation, the gradient direction interval of the gradient direction of the pixel point is judged, and the gradient direction interval is sequentially
，
……
And is distributed according to the maximum gradient direction, the minimum gradient direction and each gradient direction in each gradient direction interval, for example, when a certain pixel point in the image block
LadderIn the direction of degree of
Then it exists in the gradient direction interval at this time
In the middle, it is allocated in the gradient direction interval
Has a maximum gradient direction of
The gradient amplitude assigned to the direction of the minimum gradient is
Wherein
Is a pixel point
The gradient amplitude value of each image block can be obtained, and a directional gradient histogram corresponding to each image block can be obtained, and an H0G feature image of each image block can be obtained, it should be noted that, the obtaining manner of the H0G feature is the prior art, which is not described in detail in this embodiment, that is, a triangular formula is used to obtain horizontal gradient amplitude components and vertical gradient amplitude components of gradient amplitudes of all gradient directions in an HOG feature image, and obtain an overall gradient direction of each HOG feature image, and a calculation formula of the overall gradient direction is:
in the formula (I), the compound is shown in the specification,
representing HOG feature images
The overall gradient direction of;
it should be noted that, in the formula, the superscript 9 of the summation formula is the total number of gradient directions of the HOG feature image, and the horizontal gradient magnitude component and the vertical gradient magnitude component in the formula are positive or negative based on the pointing direction, for example, when the gradient direction is 40 °, the corresponding gradient is in the horizontal direction: (
Direction) is positive, and the gradient direction is 150 degrees, the corresponding gradient is in the horizontal direction (
Direction) is a negative value, and secondly, the calculation formula of the overall gradient direction is a formula of the prior art, which is not described again in this embodiment.
Obtaining the overall gradient direction of the HOG characteristic image in the 8 neighborhood range of each HOG characteristic image by the same calculation by utilizing a calculation formula of the overall gradient direction, and acquiring the direction deviation value of the overall gradient direction corresponding to the HOG characteristic image and each HOG characteristic image in the neighborhood thereof according to the overall gradient direction corresponding to the HOG characteristic image and each HOG characteristic image in the neighborhood thereof on the basis of the overall gradient direction, wherein the calculation formula of the direction deviation value of the overall gradient direction corresponding to the HOG characteristic image and each HOG characteristic image in the neighborhood thereof is as follows:
in the formula (I), the compound is shown in the specification,
representing HOG feature images
HOG feature image in the neighborhood thereof
The direction deviation value of the overall gradient direction of (1);
note that, when the HOG feature image is used
And HOG feature images in its neighborhood
The larger the overall gradient direction deviation, i.e. the direction difference
The closer to 90 °, the larger the directional deviation value, thereby indicating the HOG featureSign image
On HOG feature images
The more obvious the identification in the local area is, in the formula, the denominator +1 is used for preventing the denominator from being 0, so that the direction deviation value of the whole gradient direction corresponding to each HOG characteristic image and each HOG characteristic image in the neighborhood is obtained.
Obtaining a direction deviation value of the overall gradient direction corresponding to the HOG feature image and each HOG feature image in the neighborhood based on a calculation formula of the direction deviation value of the overall gradient direction corresponding to the HOG feature image and each HOG feature image in the neighborhood, reflecting the identification property in the neighborhood of the HOG feature image according to the direction deviation value, and further adjusting the importance degree in the local range of the subsequent HOG feature image according to the direction deviation value, so that obtaining the second importance degree of each HOG feature image according to the direction deviation value and the gradient amplitude difference value comprises the following steps: acquiring the sum of absolute values of gradient amplitude differences of the HOG characteristic image and the HOG characteristic image in the neighborhood of the HOG characteristic image in all corresponding gradient directions; acquiring the product of the sum of absolute values of the gradient amplitude difference values and the direction deviation value of the overall gradient direction of the HOG characteristic image and the corresponding HOG characteristic image in the neighborhood of the HOG characteristic image; and taking the sum of absolute values of gradient amplitude difference values corresponding to all the HOG characteristic images in the neighborhood of the HOG characteristic image and the sum of products of direction deviation values of the whole gradient direction as a second importance degree of the HOG characteristic image, wherein the calculation formula of the second importance degree is as follows:
in the formula (I), the compound is shown in the specification,
representing HOG feature images
A second degree of importance;
It should be noted that, in this embodiment, the neighborhood size is 8 neighborhoods, so that the 8-neighborhood range of one HOG feature image has similarity in the face image, and the gradient direction and the corresponding gradient magnitude of the HOG feature image reflected in the HOG feature image are all similar, and when the difference value between the HOG feature image and the rest of the HOG feature images in the neighborhood range in the gradient direction and the corresponding gradient magnitude is very large, it is indicated that the HOG feature image also has high identification, that is, the formula is used to reflect the HOG feature image
The significance of the gradient in its neighborhood, i.e., the second significance.
S4, acquiring the comprehensive importance degree of each HOG characteristic image;
specifically, the acquiring the integrated importance level of each HOG feature image according to the first importance level and the second importance level includes: setting the weights of the first importance degree and the second importance degree to be 0.5, and adding the first importance degree corresponding to the HOG characteristic image to 0.5 and the second importance degree corresponding to the HOG characteristic image to 0.5 to obtain the comprehensive importance degree of the HOG characteristic image.
In addition, the invention considers that when the face information is collected, the problem of influence of light rays under the collection scene and the stereo characteristics of five sense organs exist, more or less shadow situations and light reflection situations exist on the face of a person, and the shadow situations and the light reflection situations can cause that the characteristics of partial areas in the obtained HOG characteristic image are incomplete, for example, shadow can appear on one side of a nose area, so that the characteristics of all gradient amplitude distribution in the HOG characteristic image are weakened, the second importance degree obtained by the local characteristics is reduced, and finally, when the change degree is obtained subsequently, the transformation degree obtained by the important HOG characteristic image is smaller, therefore, the collected HOG characteristic image needs to be correspondingly adjusted.
Therefore, the face data encryption transmission method for terminal identity authentication of the present invention further comprises: acquiring each HOG characteristic image and a target HOG characteristic image which is symmetrical about a vertical central line of the face image; acquiring the directional symmetry degree of each HOG characteristic image in the neighborhood of the HOG characteristic image and the HOG characteristic image at the symmetrical position in the neighborhood of the corresponding target HOG characteristic image according to the overall gradient direction of each HOG characteristic image and the corresponding target HOG characteristic image, and as shown in FIG. 2, acquiring the directional symmetry degree of each HOG characteristic image in the neighborhood of the HOG characteristic image and the HOG characteristic image at the symmetrical position in the neighborhood of the corresponding target HOG characteristic image
And HOG feature image
Symmetry; according to the HOG characteristic image and the neighborhood thereofObtaining the integral gradient direction symmetry degree of each HOG characteristic image and the corresponding target HOG characteristic image in the neighborhood range; judging whether to adjust the neighborhood size according to the sum of the direction deviation values of the overall gradient direction of the HOG characteristic image and all the HOG characteristic images in the neighborhood of the HOG characteristic image, and obtaining the final neighborhood size corresponding to each HOG characteristic image; normalizing according to the length of the final neighborhood size corresponding to each HOG characteristic image to obtain the necessity degree of the HOG characteristic image; and adjusting the comprehensive importance degree of each corresponding HOG characteristic image according to the corresponding necessity degree of the HOG characteristic image, the symmetry degree of the whole gradient direction and the sum of the gradient amplitudes of the HOG characteristic image and the corresponding target HOG characteristic image and the adjustment value to obtain the final comprehensive importance degree.
Wherein, obtaining the final neighborhood size comprises: when the sum of the direction deviation values of the overall gradient direction of the HOG characteristic image and all the HOG characteristic images in the neighborhood of the HOG characteristic image is smaller than a preset sum threshold, increasing the neighborhood size of the HOG characteristic image to obtain an increased target neighborhood; obtaining a sum of direction deviation values of the overall gradient directions of the HOG feature image and each HOG feature image in the target neighborhood of the HOG feature image, and taking a size of the target neighborhood corresponding to the condition that the sum of the direction deviation values of the overall gradient directions of the HOG feature image and each HOG feature image in the target neighborhood of the HOG feature image is greater than or equal to a preset sum threshold as a final neighborhood size
The direction deviation values of the overall gradient directions of the feature images in the 3*3 neighborhood range are summed, i.e.
，
Representing HOG feature imagesThe sum of the directional offset values from the overall gradient direction of all the feature images in the neighborhood of 3*3,
representing HOG feature images
HOG feature image in the neighborhood of the HOG feature image
The direction deviation value of the overall gradient direction of the present embodiment is set as a sum threshold value
(threshold value)
The implementer can adjust parameters such as the set size of the precision when converting into the HOG human face data model according to the resolution when the terminal collects the human face image, wherein the empirical value is 500), if the implementer needs to use the terminal to collect the human face image, the implementer can set the size according to the resolution when converting into the HOG human face data model
Then, the length of the neighborhood range is increased by step 2 to obtain the increased neighborhood range, i.e. the increased neighborhood range is
Calculating HOG feature image
The direction deviation values of the overall gradient direction of the feature images in the 5*5 neighborhood range are added
If, if
Continue to increase the neighborhood range until
When the neighborhood is within
Then will be
As the final neighborhood size.
Wherein, the necessity degree of obtaining the HOG feature image comprises: acquiring the length of the corresponding final neighborhood size and the length of the minimum neighborhood size in the lengths of the final neighborhood sizes corresponding to all the HOG characteristic images; acquiring a target neighborhood size corresponding to the normalized HOG characteristic image according to the length of the corresponding final neighborhood size, the length of the minimum neighborhood size and the length of the final neighborhood size corresponding to each HOG characteristic image; taking the length corresponding to the target neighborhood size as the degree of necessity of the HOG feature image, it should be noted that, when considering face recognition, the recognition is performed based on local features, and if the corresponding adjustment is performed only by the amplitude difference of the symmetric positions, then some unimportant regions, such as hair, beard, cheek, etc., are also adjusted, so that the difference between the unimportant regions and the important regions is weakened, therefore, the degree of necessity of the adjustment of the HOG feature image needs to be calculated according to the identification expressed by the gradient direction feature of the local regions, specifically, the calculation formula of the degree of necessity of the HOG feature image is as follows:
in the formula (I), the compound is shown in the specification,
representing HOG feature images
The degree of necessity of;
it should be noted that, when the accumulated value of the overall gradient direction deviation value in the neighborhood range where the HOG feature image is located reaches the threshold value, the larger the required range is, the worse the identification of the local position where the HOG feature image is located is, the lower the importance degree of the HOG feature image in face recognition is, that is, the smaller the necessity degree of adjustment is, and secondly, the normalization formula is the formula in the prior art, which is not described in detail in this embodiment.
The calculation formula of the directional symmetry degree of each HOG characteristic image in the neighborhood of the HOG characteristic image and the HOG characteristic image at the symmetrical position in the neighborhood of the corresponding target HOG characteristic image is as follows:
in the formula (I), the compound is shown in the specification,
representing HOG feature images
HOG feature images in the neighborhood of (1)
With corresponding target HOG characteristic image
And HOG feature images
Positionally symmetric HOG feature mapsDegree of directional symmetry of the image;
it should be noted that, in this embodiment, the vertical center line of the face image is taken as a symmetry line, that is, the face image is symmetrical left and right about the vertical center line, the horizontal direction is 0 ° to the right in this embodiment, and therefore, the vertical center line is 90 °, and the left and right symmetries are taken as 135 ° and 45 ° for example, and are symmetrical about the 90 ° center line, so that the half of the sum of the amplitudes of the two gradient directions is closer to 90 °, which indicates that the degree of left and right symmetries of the two gradient directions is higher, and the denominator in the equation is increased by 1 in order to prevent the denominator from being 0.
Acquiring the integral gradient direction symmetry degree of the HOG characteristic image and the corresponding target HOG characteristic image in a neighborhood range comprises the following steps: acquiring a direction deviation value of the overall gradient direction of the HOG characteristic image and each HOG characteristic image in the neighborhood thereof, and a sum value of the ratio of the direction symmetry degree of each HOG characteristic image in the neighborhood of the HOG characteristic image and the HOG characteristic image at the symmetric position in the neighborhood of the corresponding target HOG characteristic image; and taking the sum value as the symmetry degree of the overall gradient direction of the HOG characteristic image and the corresponding target HOG characteristic image in the neighborhood range, wherein the calculation formula of the symmetry degree of the overall gradient direction is as follows:
in the formula (I), the compound is shown in the specification,
representing the symmetry degree of the HOG characteristic image and the corresponding target HOG characteristic image in the whole gradient direction in the neighborhood range;
note that the degree of directional symmetry
The larger the HOG feature image is, the larger the HOG feature image is
With corresponding target HOG characteristic image
The more bilaterally symmetrical the HOG characteristic in a local range, i.e. the greater the degree of directional symmetry, and the overall gradient direction deviation value
The larger the difference is, two points reflecting the bilateral symmetry position in the face image do not necessarily correspond to the actual symmetry position completely, but the symmetry position still retains the characteristic that the whole gradient direction is bilateral symmetry, and because of local similarity, the face region corresponding to the 8 neighborhood range is actually smaller, therefore, the whole gradient direction should be very close, so the deviation value of the whole gradient direction is large, the confidence of the whole gradient direction in the symmetry judgment of the local position is very low, and the direction deviation value is very close
Degree of symmetry with overall gradient direction
Is a negative correlation.
Wherein, the formula for calculating the adjustment value of the HOG characteristic image is as follows:
in the formula (I), the compound is shown in the specification,
representing HOG feature images
The adjustment value of (d);
it should be noted that, when the sum of the gradient amplitudes of the HOG feature images is greater than or equal to the sum of the gradient amplitudes of the corresponding target HOG feature images, the adjustment value is 1, that is, adjustment is not required, and when the sum of the gradient amplitudes of the HOG feature images is less than the sum of the gradient amplitudes of the corresponding target HOG feature images, it is indicated that adjustment is required, so that when the degree of symmetry of the overall gradient direction of the HOG feature images and the corresponding target HOG feature images in the neighborhood range is greater, it is indicated that the HOG feature images and the target HOG feature images at the symmetric positions are more symmetric, the corresponding adjustment values are greater, and the greater the degree of necessity is, the greater the corresponding adjustment values are, and the smaller the ratio of the sum of the gradient amplitudes of the HOG feature images to the sum of the gradient amplitudes of the corresponding target HOG feature images is, the greater the adjustment is indicated, so that the smaller the ratio is, the corresponding adjustment values are indicated.
Acquiring the comprehensive importance degree of each HOG characteristic image according to the adjustment value, the first importance degree and the second importance degree, wherein the calculation formula of the comprehensive importance degree is as follows:
in the formula (I), the compound is shown in the specification,
representing HOG feature images
The degree of comprehensive importance of;
the first degree of importance,The second importance level is positively correlated with the importance level, while the importance of the first importance level and the second importance level is considered to be equal in this embodiment, and therefore, the same weight value of 0.5 is set for the first importance level and the second importance level here, and secondly,
the larger the size, the more obvious the self-identification of the reaction HOG feature image is,
the larger the HOG characteristic image is, the larger the local identification of the HOG characteristic image in the neighborhood range is, the larger the local identification is, the stronger the identification of the HOG characteristic image is, namely the higher the comprehensive importance degree is, the more encryption is needed, and the important regional characteristic is smaller in amplitude instead when the HOG characteristic image identifies face data due to the light influence when a terminal collects the face.
S5, acquiring a final HOG characteristic image of each image block;
specifically, an initial transformation gradient amplitude value in each gradient direction is obtained according to the gradient amplitude value mean value in each gradient direction and the gradient amplitude value in each gradient direction in each HOG characteristic image; and obtaining a target gradient amplitude value of each gradient direction in each HOG characteristic image by using the gradient amplitude value of each gradient direction in each HOG characteristic image and the initial transformation gradient amplitude value of each gradient direction, obtaining a transformation coefficient of each gradient direction according to the initial transformation gradient amplitude value and the target gradient amplitude value of each gradient direction, obtaining a final transformation gradient amplitude value of each gradient direction of the HOG characteristic image according to the transformation coefficient and the initial transformation gradient amplitude value of each gradient direction and the comprehensive importance degree of the HOG characteristic image, and obtaining a final HOG characteristic image of each image block according to all the final transformation gradient amplitude values.
Because the gradient direction histogram has a great difference degree between partial amplitudes, the partial gradient amplitudes with a great amplitude need to be transformed, so that the part with a great difference of gradient amplitudes in each HOG feature image is eliminated, and further the directional gradient histograms of all HOG feature images are similar, therefore, the gradient amplitude of each gradient direction in each HOG feature image is differed from the mean value of the gradient amplitudes of the corresponding gradient directions in the HOG feature image to obtain an initial transformation gradient amplitude of each gradient direction, then the initial transformation gradient amplitude of each gradient direction is subtracted from the gradient amplitude of each gradient direction to obtain the gradient after each direction transformation, namely a target gradient amplitude, and the proportion of the initial transformation gradient amplitude in the transformed target gradient amplitude is calculated and is used as a transformation coefficient, because the gradient is a vector, the transformation coefficient is positive and negative, and finally the final transformation gradient after the transformation is calculated, and the final transformation gradient of each gradient direction is calculated as follows:
in the formula (I), the compound is shown in the specification,
second to show HOG feature image
Final transform gradient magnitudes for each gradient direction;
it should be noted that, because the prior art performs preliminary normalization on the histogram of directional gradients, at this time, the transformation rules between the histograms of directional gradients corresponding to each HOG feature image are all the same, and the obtained key is too simple, although the attack manner of histogram statistical analysis can be resisted to a certain extent, the resistance to the attack manner of brute force cracking is weak, and the security is also low, therefore, in this embodiment, the comprehensive importance degree is used as the adjustment value of the transformation coefficient, and the transformation coefficient is adjusted, so that the amplitude of the transformation gradient is also adjusted, and thus the security of the final HOG feature image is higher.
Based on a calculation formula of the final change gradient in each gradient direction, all final transformation gradient amplitudes of each HOG characteristic image can be obtained, so that the HOG characteristic images with different comprehensive importance degrees are transformed in different direction gradients, the amplitude difference among a plurality of direction gradients in the same HOG characteristic image is reduced, and meanwhile, the identification of the HOG characteristic image in the neighborhood range is also reduced.
S6, acquiring an encrypted image and transmitting the encrypted image;
specifically, an encrypted image is obtained according to all the final HOG feature images, and the encrypted image, the transform coefficient corresponding to each final HOG feature image and the comprehensive importance degree are transmitted.
And storing the transformation coefficient and the comprehensive importance degree corresponding to each final HOG characteristic image as a key of each corresponding final HOG characteristic image, thereby realizing the encrypted transmission of the face image.
Further comprising: decrypting the encrypted data, the decrypting step comprising: obtaining the gradient of each HOG characteristic image in each gradient direction before transformation according to each final HOG characteristic image, the corresponding transformation coefficient and the comprehensive importance degree; from HOG feature imagesObtaining HOG characteristic images by the gradient before transformation in each gradient direction; obtaining a face image according to all HOG characteristic images, and obtaining the gradient before transformation in each gradient direction
Wherein, in the step (A),
is shown as
Transform coefficients of the respective gradient directions;
indicating the overall importance of the HOG feature image,
second to represent final HOG feature image
Because the final transformation gradient amplitude of each HOG characteristic image is obtained based on the own HOG characteristic and the local HOG characteristic in the neighborhood thereof, namely the comprehensive importance degree obtained based on the second importance degree and the first importance degree, when the cracking of one HOG characteristic image is wrong, the subsequent cracking results of the HOG characteristic image are wrong, so that the avalanche effect is realized during cracking, and the safety of encrypted data is higher.
The invention relates to a human face data encryption transmission method for terminal identity authentication, which is characterized in that a human face image is divided into a plurality of image blocks because the gradient directions of regions corresponding to different face organs in the human face image are different, then HOG characteristic images representing each image block are obtained, the first importance degree of the HOG characteristic images is reflected by the standard difference of the gradient amplitudes of the HOG characteristic images in all the gradient directions, the larger the standard difference is, the larger the gradient amplitude difference is, the larger the corresponding first importance degree is, namely the first importance degree reflects the importance degree of the HOG characteristics of the HOG characteristic images, then the direction deviation value and the gradient amplitude difference value of the HOG characteristic images in the neighborhood of the HOG characteristic images are utilized to reflect the second importance degree of the HOG characteristic images, namely the second importance degree reflects the importance degree of the HOG characteristics of the HOG characteristic images and the HOG characteristic images in the field, therefore, by combining the first importance degree of the HOG characteristic image, the second importance degree of the HOG characteristic image and the HOG characteristic image in the field of the HOG characteristic image and the comprehensive importance degree of the HOG characteristic image comprehensively evaluated, when the HOG characteristic image is attacked, the cracking error of one HOG characteristic image can cause the subsequent cracking results of the HOG characteristic image to be wrong, so that the safety of the encrypted data obtained by encrypting based on the comprehensive importance degree is higher due to the avalanche effect during cracking, secondly, the comprehensive importance degree represents the significance of the gradient direction in the HOG characteristic image, as the direction gradient of the region corresponding to the human face organ is different from the forehead region and the cheek region, the HOG characteristic image corresponding to the human face organ region has the significant gradient direction, if the amplitude of the significant gradient direction is changed, the gradient amplitudes of all the HOG characteristic images in the whole image are close to each other, so that the difference of all the HOG characteristic images of the whole image is small, even if the stored encrypted data is stolen, the stored encrypted data cannot be cracked, the gradient of the HOG characteristic images is transformed according to the comprehensive importance degree and the transformation coefficient of each gradient direction to obtain the final transformed gradient amplitude, the final HOG characteristic image of each image block is obtained according to the final transformed gradient amplitude, the gradient amplitudes corresponding to all the final HOG characteristic images are close to each other, namely the different comprehensive importance degrees of the HOG characteristic images are utilized, different degrees of encryption of different HOG characteristic images are realized, the security of transmitted data is further improved, meanwhile, each final HOG characteristic image corresponds to one key, the complexity of the key is increased, and the security of the transmitted data is ensured.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A face data encryption transmission method for terminal identity authentication is characterized by comprising the following steps:
collecting a face image, and segmenting the face image to obtain a plurality of same image blocks;
acquiring a HOG characteristic image of each image block, and taking the standard deviation of the gradient amplitudes of all gradient directions in each HOG characteristic image as a first importance degree of each HOG characteristic image;
acquiring the overall gradient direction of each HOG characteristic image according to the horizontal gradient amplitude component and the vertical gradient amplitude component of the gradient amplitude in all the gradient directions in each HOG characteristic image; acquiring a second importance degree of each HOG characteristic image according to a direction deviation value of the overall gradient direction of each HOG characteristic image and the overall gradient direction of each HOG characteristic image in the neighborhood and a gradient amplitude difference value of each HOG characteristic image and each HOG characteristic image in the neighborhood in the corresponding gradient direction;
acquiring the comprehensive importance degree of each HOG characteristic image according to the first importance degree and the second importance degree;
acquiring an initial transformation gradient amplitude value of each gradient direction according to the gradient amplitude value mean value of each gradient direction in each HOG characteristic image and the gradient amplitude value of each gradient direction; obtaining a target gradient amplitude of each gradient direction in each HOG characteristic image by using the gradient amplitude of each gradient direction in each HOG characteristic image and the initial transformation gradient amplitude of each gradient direction;
obtaining a transformation coefficient of each gradient direction according to the initial transformation gradient amplitude and the target gradient amplitude of each gradient direction, obtaining a final transformation gradient amplitude of each gradient direction of the HOG characteristic image according to the transformation coefficient and the initial transformation gradient amplitude of each gradient direction and the comprehensive importance degree of the HOG characteristic image, and obtaining a final HOG characteristic image of each image block according to all the final transformation gradient amplitudes;
and obtaining an encrypted image according to all the final HOG characteristic images, and transmitting the encrypted image, the corresponding transformation coefficient of each final HOG characteristic image and the comprehensive importance degree.
2. The method for encrypting and transmitting the face data for terminal identity authentication according to claim 1, further comprising:
acquiring each HOG characteristic image and a target HOG characteristic image which is symmetrical about a vertical central line of the face image;
acquiring the directional symmetry degree of each HOG characteristic image in the neighborhood of the HOG characteristic image and the HOG characteristic image at the symmetrical position in the neighborhood of the corresponding target HOG characteristic image according to the overall gradient direction of each HOG characteristic image and the corresponding target HOG characteristic image;
acquiring the integral gradient direction symmetry degree of the HOG characteristic image and the corresponding target HOG characteristic image in a neighborhood range according to the direction deviation value of the integral gradient direction of the HOG characteristic image and each HOG characteristic image in the neighborhood thereof and the direction symmetry degree of the HOG characteristic image at the symmetric position in the neighborhood of each HOG characteristic image in the neighborhood of the HOG characteristic image and the corresponding target HOG characteristic image;
judging whether to adjust the neighborhood size according to the sum of the direction deviation values of the overall gradient direction of the HOG characteristic image and all the HOG characteristic images in the neighborhood of the HOG characteristic image, and obtaining the final neighborhood size corresponding to each HOG characteristic image;
normalizing according to the length of the final neighborhood size corresponding to each HOG characteristic image to obtain the necessary degree of the HOG characteristic image;
acquiring an adjustment value of each HOG characteristic image according to the corresponding necessity degree of the HOG characteristic image, the symmetry degree of the whole gradient direction and the sum of the gradient amplitudes of the HOG characteristic image and the corresponding target HOG characteristic image;
and adjusting the comprehensive importance degree of each corresponding HOG characteristic image according to the adjustment value to obtain the final comprehensive importance degree.
3. The method for encrypting and transmitting the face data for terminal identity authentication according to claim 2, wherein obtaining the final neighborhood size comprises:
when the sum of the direction deviation values of the overall gradient direction of the HOG characteristic image and all the HOG characteristic images in the neighborhood of the HOG characteristic image is smaller than a preset sum threshold, gradually increasing the neighborhood size of the HOG characteristic image to obtain an increased target neighborhood;
and acquiring the sum of the direction deviation values of the overall gradient directions of the HOG characteristic image and each HOG characteristic image in the target neighborhood, and taking the size of the corresponding target neighborhood as the final neighborhood size when the sum of the direction deviation values of the overall gradient directions of the HOG characteristic image and each HOG characteristic image in the target neighborhood is greater than or equal to a preset sum threshold.
4. The method for encrypting and transmitting the face data for terminal identity authentication according to claim 2, wherein obtaining the degree of necessity of the HOG feature image comprises:
acquiring the length of the corresponding final neighborhood size and the length of the minimum neighborhood size in the lengths of the final neighborhood sizes corresponding to all the HOG characteristic images;
acquiring a target neighborhood size corresponding to the normalized HOG characteristic image according to the length of the corresponding final neighborhood size, the length of the minimum neighborhood size and the length of the final neighborhood size corresponding to each HOG characteristic image;
and taking the length corresponding to the target neighborhood size as the necessary degree of the HOG characteristic image.
5. The face data encryption transmission method for terminal identity authentication according to claim 2, wherein the calculation formula of the directional symmetry degree of each HOG feature image in the neighborhood of the HOG feature image and the HOG feature image at the symmetric position in the neighborhood of the corresponding target HOG feature image is as follows:
in the formula (I), the compound is shown in the specification,
representing HOG feature images
HOG feature images in the neighborhood of (1)
With corresponding target HOG characteristic image
And HOG feature images
The directional symmetry degree of the position-symmetric HOG characteristic image;
6. The method for encrypting and transmitting the face data for the terminal identity authentication according to claim 2, wherein the obtaining of the overall gradient direction symmetry degree of the HOG feature image and the corresponding target HOG feature image in the neighborhood range comprises:
acquiring a direction deviation value of the overall gradient direction of the HOG characteristic image and each HOG characteristic image in the neighborhood thereof, and a sum value of the ratio of the direction symmetry degree of each HOG characteristic image in the neighborhood of the HOG characteristic image and the HOG characteristic image at the symmetric position in the neighborhood of the corresponding target HOG characteristic image;
and taking the sum value as the degree of symmetry of the HOG characteristic image and the corresponding target HOG characteristic image in the whole gradient direction in the neighborhood range.
7. The method for encrypting and transmitting the face data for terminal identity authentication according to claim 2, wherein the calculation formula of the adjustment value of each HOG feature image is as follows:
in the formula (I), the compound is shown in the specification,
representing HOG feature images
The adjustment value of (d);
8. The method for encrypting and transmitting the face data for terminal identity authentication according to claim 1, wherein the obtaining the second importance degree of each HOG feature image comprises:
acquiring the sum of absolute values of gradient amplitude differences of the HOG characteristic image and the HOG characteristic image in the neighborhood of the HOG characteristic image in all corresponding gradient directions;
and taking the sum of products of the absolute value sum of the gradient amplitude difference values corresponding to all the HOG characteristic images in the neighborhood of the HOG characteristic image and the direction deviation value of the overall gradient direction as the second importance degree of the HOG characteristic image.
9. The method as claimed in claim 1, wherein obtaining the final transformation gradient magnitude for each gradient direction of the HOG feature image comprises:
obtaining the product of the transformation coefficient and the comprehensive importance degree;
and acquiring the ratio of the initial transformation gradient amplitude corresponding to each gradient direction in the HOG characteristic image to the product of the transformation coefficient and the comprehensive importance degree, and taking the ratio as the final transformation gradient amplitude of each gradient direction of the HOG characteristic image.
10. The face data encryption transmission method for terminal identity authentication according to claim 1, further comprising: decrypting the encrypted data, the decrypting step comprising:
obtaining the gradient of each HOG characteristic image in each gradient direction before transformation according to each final HOG characteristic image, the corresponding transformation coefficient and the comprehensive importance degree;
acquiring the HOG characteristic image according to the gradient of the HOG characteristic image before transformation in each gradient direction;
and obtaining a face image according to all the HOG characteristic images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310043171.1A CN115776410B (en) | 2023-01-29 | 2023-01-29 | Face data encryption transmission method for terminal identity authentication |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310043171.1A CN115776410B (en) | 2023-01-29 | 2023-01-29 | Face data encryption transmission method for terminal identity authentication |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115776410A true CN115776410A (en) | 2023-03-10 |
| CN115776410B CN115776410B (en) | 2023-05-02 |
Family
ID=85393743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310043171.1A Active CN115776410B (en) | 2023-01-29 | 2023-01-29 | Face data encryption transmission method for terminal identity authentication |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115776410B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116541872A (en) * | 2023-07-07 | 2023-08-04 | 深圳奥联信息安全技术有限公司 | Data information safety transmission method and system |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550646A (en) * | 2015-12-08 | 2016-05-04 | 中山大学 | Generalized illumination invariant face feature description method based on logarithmic gradient histogram |
| CN109712143A (en) * | 2018-12-27 | 2019-05-03 | 北京邮电大学世纪学院 | A kind of Fast image segmentation method based on super-pixel multiple features fusion |
| CN111008589A (en) * | 2019-12-02 | 2020-04-14 | 杭州网易云音乐科技有限公司 | Face key point detection method, medium, device and computing equipment |
| CN111832405A (en) * | 2020-06-05 | 2020-10-27 | 天津大学 | Face recognition method based on HOG and depth residual error network |
| WO2021139171A1 (en) * | 2020-07-28 | 2021-07-15 | 平安科技（深圳）有限公司 | Facial enhancement based recognition method, apparatus and device, and storage medium |
| WO2021227349A1 (en) * | 2020-05-11 | 2021-11-18 | 华南理工大学 | Front-end facial image encryption and recognition method for biometric privacy protection |
| CN113762970A (en) * | 2021-05-17 | 2021-12-07 | 腾讯科技（深圳）有限公司 | Data processing method and device, computer readable storage medium and computer equipment |
| CN113766085A (en) * | 2021-05-17 | 2021-12-07 | 腾讯科技（深圳）有限公司 | Image processing method and related device |
| CN114419716A (en) * | 2022-01-26 | 2022-04-29 | 北方工业大学 | Calibration method for face key point calibration of face image |
| US20230004666A1 (en) * | 2021-07-01 | 2023-01-05 | Deka Products Limited Partnership | Surveillance data filtration techniques |
| CN115620117A (en) * | 2022-12-20 | 2023-01-17 | 吉林省信息技术研究所 | Face information encryption method and system for network access authority authentication |
-
2023
- 2023-01-29 CN CN202310043171.1A patent/CN115776410B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550646A (en) * | 2015-12-08 | 2016-05-04 | 中山大学 | Generalized illumination invariant face feature description method based on logarithmic gradient histogram |
| CN109712143A (en) * | 2018-12-27 | 2019-05-03 | 北京邮电大学世纪学院 | A kind of Fast image segmentation method based on super-pixel multiple features fusion |
| CN111008589A (en) * | 2019-12-02 | 2020-04-14 | 杭州网易云音乐科技有限公司 | Face key point detection method, medium, device and computing equipment |
| WO2021227349A1 (en) * | 2020-05-11 | 2021-11-18 | 华南理工大学 | Front-end facial image encryption and recognition method for biometric privacy protection |
| CN111832405A (en) * | 2020-06-05 | 2020-10-27 | 天津大学 | Face recognition method based on HOG and depth residual error network |
| WO2021139171A1 (en) * | 2020-07-28 | 2021-07-15 | 平安科技（深圳）有限公司 | Facial enhancement based recognition method, apparatus and device, and storage medium |
| CN113762970A (en) * | 2021-05-17 | 2021-12-07 | 腾讯科技（深圳）有限公司 | Data processing method and device, computer readable storage medium and computer equipment |
| CN113766085A (en) * | 2021-05-17 | 2021-12-07 | 腾讯科技（深圳）有限公司 | Image processing method and related device |
| US20230004666A1 (en) * | 2021-07-01 | 2023-01-05 | Deka Products Limited Partnership | Surveillance data filtration techniques |
| CN114419716A (en) * | 2022-01-26 | 2022-04-29 | 北方工业大学 | Calibration method for face key point calibration of face image |
| CN115620117A (en) * | 2022-12-20 | 2023-01-17 | 吉林省信息技术研究所 | Face information encryption method and system for network access authority authentication |
Non-Patent Citations (1)
| Title |
|---|
| 赖韬等: "融合人脸特征与密码算法的身份认证系统", 《电讯技术》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116541872A (en) * | 2023-07-07 | 2023-08-04 | 深圳奥联信息安全技术有限公司 | Data information safety transmission method and system |
| CN116541872B (en) * | 2023-07-07 | 2024-04-09 | 深圳奥联信息安全技术有限公司 | Data information safety transmission method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115776410B (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104834849B (en) | Dual-factor identity authentication method and system based on Application on Voiceprint Recognition and recognition of face | |
| CN108921191B (en) | Multi-biological-feature fusion recognition method based on image quality evaluation | |
| El-Shafai et al. | Efficient and secure cancelable biometric authentication framework based on genetic encryption algorithm | |
| CN115776410A (en) | Face data encryption transmission method for terminal identity authentication | |
| CN111507206A (en) | Finger vein identification method based on multi-scale local feature fusion | |
| Hofbauer et al. | Image metric-based biometric comparators: A supplement to feature vector-based hamming distance? | |
| CN115086315A (en) | Cloud edge collaborative security authentication method and system based on image sensitivity identification | |
| CN110163123B (en) | Fingerprint finger vein fusion identification method based on single near-infrared finger image | |
| CN113766085B (en) | Image processing method and related device | |
| CN204576520U (en) | Based on the Dual-factor identity authentication device of Application on Voiceprint Recognition and recognition of face | |
| CN106599841A (en) | Full face matching-based identity verifying method and device | |
| CN110503697B (en) | Iris feature hiding method based on random noise mechanism | |
| Rane et al. | Face and palmprint Biometric recognition by using weighted score fusion technique | |
| CN105809132A (en) | Improved compressed sensing-based face recognition method | |
| CN116545774B (en) | Audio and video conference security method and system | |
| CN116778562A (en) | Face verification method, device, electronic equipment and readable storage medium | |
| CN113190858B (en) | Image processing method, system, medium and device based on privacy protection | |
| CN112651319B (en) | Video detection method and device, electronic equipment and storage medium | |
| Adamović et al. | Information analysis of iris biometrics for the needs of cryptology key extraction | |
| Samira et al. | Biometric Template Security Using Watermarking Reinforcement Based Cancellable Transformation | |
| CN110956098B (en) | Image processing method and related equipment | |
| CN112070956A (en) | Identity recognition system based on face image | |
| CN113591650A (en) | Privacy identity authentication method based on characteristic face | |
| Kamil et al. | Makeup-Invariant Face Recognition using combined Gabor Filter Bank and Histogram of Oriented Gradients | |
| Paunwala et al. | Dct watermarking approach for security enhancement of multimodal system |
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 |