CN110910380B - Detection method and device for synthesized picture - Google Patents
Detection method and device for synthesized picture Download PDFInfo
- Publication number
- CN110910380B CN110910380B CN201911205016.5A CN201911205016A CN110910380B CN 110910380 B CN110910380 B CN 110910380B CN 201911205016 A CN201911205016 A CN 201911205016A CN 110910380 B CN110910380 B CN 110910380B
- Authority
- CN
- China
- Prior art keywords
- picture
- pixel
- preset
- value
- difference
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The application discloses a method and a device for detecting a synthesized picture. The method comprises the steps of firstly adopting a first quality factor to compress an obtained picture to be detected in a preset format to obtain a first compressed picture, and then adopting at least one second quality factor to sequentially recompress the first compressed picture to obtain at least one second compressed picture; calculating the pixel value of the first compressed picture and the pixel value of at least one second compressed picture by adopting a preset detection algorithm to obtain the distortion degree of the at least one second compressed picture and the variation value of the distortion degree of the at least one second compressed picture corresponding to the first compressed picture, wherein the distortion degree is used for representing the distortion degree of each second compressed picture relative to the first compressed picture, and the variation value is used for representing the variation degree of the distortion degree; and if the variation value is larger than a preset variation threshold value, determining that the picture to be detected is a synthetic picture. The method does not depend on a training data set, and improves the accuracy of detection.
Description
Technical Field
The present application relates to the field of artificial intelligence and image forensics technologies, and in particular, to a method and an apparatus for detecting a composite picture.
Background
At present, the deep learning technology has achieved great success in the field of video image processing, and in the field of video image recognition, the accuracy of the deep learning method even exceeds that of human beings. Due to the powerful capability of deep learning techniques in the field of video picture processing, the risk of misuse is also increasing. Video synthesized using deep learning techniques (e.g., deepfake) has been able to reach a level of falseness. It is difficult to find a video synthesized using the deep learning technique by only visual observation. The synthesized or tampered video is misled to the public when being transmitted on the network, and the daily life of people is disturbed. There is therefore a need for a method that can efficiently detect composite video.
The current academic and industrial world detection methods for synthetic videos mostly adopt deep learning models, that is, deep neural networks are used for detecting videos generated by the deep learning models. The method mainly includes the steps of collecting real videos and fake videos synthesized by a deep learning method, and then training a fake video recognition classifier by the aid of the videos to detect the synthesized or tampered videos. This method can achieve 99% or even higher accuracy after parameter tuning in some specific data sets. The accuracy of deep learning based detection methods is greatly affected by the training set data. If video picture content not available in the training set appears, the accuracy of the method is reduced, and the detection accuracy is low.
That is, the detection method is affected by the quality of the training data, and the detection accuracy rate has a large relationship with the content of the video.
Disclosure of Invention
The embodiment of the application provides a method and a device for detecting a synthesized picture, which solve the problems in the prior art, the detection process does not depend on training data, the content of a video to be detected is not limited, and the detection accuracy is improved.
In a first aspect, a method for detecting a composite picture is provided, where the method may include:
compressing the acquired picture to be detected in a preset format by adopting a first quality factor to obtain a first compressed picture;
sequentially recompressing the first compressed picture by adopting at least one second quality factor to obtain at least one recompressed picture; the at least one second quality factor is at least one quality factor arranged between a preset quality factor and the first quality factor according to the size sequence, and the preset quality factor is smaller than the first quality factor;
calculating the pixel value of the first compressed picture and the pixel value of the at least one second compressed picture by adopting a preset detection algorithm to obtain the distortion degree of the at least one second compressed picture and the variation value of the distortion degree of the first compressed picture corresponding to the at least one second compressed picture, wherein the distortion degree is used for representing the distortion degree of each second compressed picture relative to the first compressed picture, and the variation value is used for representing the variation degree of the distortion degree;
and if the variation value is larger than a preset variation threshold value T, determining that the picture to be detected is a composite picture.
In an optional implementation, calculating, by using a preset detection algorithm, a pixel value of the first compressed picture and a pixel value of the at least one second compressed picture to obtain a distortion of the at least one second compressed picture and a variation value of the distortion of the first compressed picture corresponding to the at least one second compressed picture includes:
calculating the pixel value of the first compressed picture and the pixel value of the at least one second compressed picture by adopting a preset distortion algorithm to obtain the distortion degree of the first compressed picture corresponding to the at least one second compressed picture;
and calculating the distortion degree corresponding to the at least one recompressed picture by adopting a preset variation algorithm to obtain a variation value of the distortion degree.
In an optional implementation, calculating the pixel value of the first compressed picture and the pixel value of the at least one second compressed picture by using a preset distortion algorithm to obtain the distortion of the at least one second compressed picture includes:
performing difference operation on the pixel value of the first compressed picture and the pixel value of the pixel point corresponding to each second compressed picture in the at least one second compressed picture by adopting a preset difference algorithm to obtain a pixel difference matrix corresponding to each second compressed picture;
calculating the pixel value of each pixel point in the pixel difference value matrix by adopting a preset sum-of-squares algorithm to obtain a pixel sum-of-squares corresponding to the pixel difference value matrix;
performing mean operation on the pixel square sum corresponding to the pixel difference value matrix by adopting a preset mean algorithm to obtain a pixel mean value corresponding to each secondary compression image;
and determining the pixel mean value as the distortion degree of each re-compressed picture.
In an optional implementation, a preset sum of squares algorithm is adopted to calculate a pixel value of each pixel point in the pixel difference matrix to obtain a pixel sum of squares corresponding to the pixel difference matrix, including:
dividing the pixel difference matrix into a preset number of sub-matrices;
calculating the pixel value of a pixel point in each sub-matrix in the preset number of sub-matrices by adopting a preset square sum algorithm to obtain a pixel square sum corresponding to each sub-matrix;
and performing mean operation on the pixel square sum corresponding to the pixel difference value matrix by adopting a preset mean algorithm to obtain a pixel mean value corresponding to each secondary compression image, wherein the mean operation comprises the following steps:
and performing mean value operation on the pixel square sum corresponding to the preset number of sub-matrixes in the pixel difference value matrix by adopting a preset mean value algorithm to obtain a pixel mean value corresponding to each secondary compression picture.
In an optional implementation, the calculating, by using a preset variation algorithm, a distortion factor corresponding to the at least one recompressed picture to obtain a variation value of the distortion factor includes:
performing difference operation on the distortion degrees corresponding to every two adjacent recompressed pictures in the at least one recompressed picture by adopting a preset difference algorithm to obtain a corresponding difference list;
acquiring the ratio of the standard deviation of the difference values in the difference value list to the mean value of the difference values by adopting a preset ratio algorithm;
and determining the ratio as the variation value of the distortion degree.
In an optional implementation, if the picture to be detected is at least one frame of picture of the video to be detected, the number of the first compressed pictures is at least one;
after determining that the picture to be detected is a composite picture, the method further comprises:
acquiring the number of the variation values larger than a preset variation threshold value T;
and if the ratio of the number to the number of the first compressed pictures is larger than a preset ratio threshold value, determining that the video to be detected is a composite video.
In a second aspect, an apparatus for detecting a composite picture is provided, which may include: a compression unit, an arithmetic unit and a determination unit;
the compression unit is used for compressing the acquired picture to be detected in the preset format by adopting a first quality factor to obtain a first-time compressed picture;
the compression unit is further configured to sequentially recompress the first compressed picture by using at least one second quality factor to obtain at least one recompressed picture; the at least one second quality factor is at least one quality factor arranged between a preset quality factor and the first quality factor according to the size sequence, and the preset quality factor is smaller than the first quality factor;
the operation unit is configured to calculate, by using a preset detection algorithm, a pixel value of the first compressed picture and a pixel value of the at least one second compressed picture to obtain a distortion degree of the at least one second compressed picture and a variation value of the distortion degree of the first compressed picture corresponding to the at least one second compressed picture, where the distortion degree is used to represent a distortion degree of each second compressed picture relative to the first compressed picture, and the variation value is used to represent a variation degree of the distortion degree;
the determining unit is configured to determine that the picture to be detected is a composite picture if the variation value is greater than a preset variation threshold T.
In an optional implementation, the operation unit is specifically configured to calculate a pixel value of the first compressed picture and a pixel value of the at least one second compressed picture by using a preset distortion algorithm, so as to obtain a distortion degree of the at least one second compressed picture;
and calculating the distortion degree corresponding to the at least one recompressed picture by adopting a preset variation algorithm to obtain a variation value of the distortion degree.
In an optional implementation, the operation unit is further specifically configured to perform, by using a preset difference algorithm, a difference operation on a pixel value of the first compressed picture and a pixel value of a pixel point corresponding to each second compressed picture in the at least one second compressed picture to obtain a pixel difference matrix corresponding to each second compressed picture;
calculating the pixel value of each pixel point in the pixel difference value matrix by adopting a preset sum-of-squares algorithm to obtain a pixel sum-of-squares corresponding to the pixel difference value matrix;
performing mean operation on the pixel square sum corresponding to the pixel difference value matrix by adopting a preset mean algorithm to obtain a pixel mean value corresponding to each secondary compression image;
and determining the pixel mean value as the distortion degree of each re-compressed picture.
In an optional implementation, the operation unit is further specifically configured to divide the pixel difference matrix into a preset number of sub-matrices;
calculating the pixel value of a pixel point in each sub-matrix in the preset number of sub-matrices by adopting a preset sum-of-squares algorithm to obtain a pixel sum-of-squares corresponding to each sub-matrix;
and performing mean value operation on the pixel square sum corresponding to the preset number of sub-matrixes in the pixel difference value matrix by adopting a preset mean value algorithm to obtain a pixel mean value corresponding to each secondary compression picture.
In an optional implementation, the operation unit is further specifically configured to perform a difference operation on distortion degrees corresponding to every two adjacent recompressed pictures in the at least one recompressed picture by using a preset difference algorithm to obtain a corresponding difference list;
acquiring the ratio of the standard deviation of the difference values in the difference value list to the mean value of the difference values by adopting a preset ratio algorithm;
and determining the ratio as the variation value of the distortion degree.
In an optional implementation, if the picture to be detected is at least one frame of picture of the video to be detected, the number of the first compressed pictures is at least one;
the determining unit is further configured to obtain the number of the variation values larger than a preset variation threshold T;
and if the ratio of the number to the number of the first compressed pictures is greater than a preset proportion threshold value, determining that the video to be detected is a composite video.
In a third aspect, an electronic device is provided, which includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
a processor adapted to perform the method steps of any of the above first aspects when executing a program stored in the memory.
In a fourth aspect, a computer-readable storage medium is provided, having stored therein a computer program which, when executed by a processor, performs the method steps of any of the above first aspects.
The detection method of the synthesized picture provided by the embodiment of the invention firstly adopts the first quality factor to compress the obtained picture to be detected with the preset format to obtain a first compressed picture, and then adopts at least one second quality factor to sequentially recompress the first compressed picture to obtain at least one second compressed picture; calculating the pixel value of the first compressed picture and the pixel value of at least one second compressed picture by adopting a preset detection algorithm to obtain the distortion degree of the at least one second compressed picture and the variation value of the distortion degree of the first compressed picture corresponding to the at least one second compressed picture, wherein the distortion degree is used for representing the distortion degree of each second compressed picture relative to the first compressed picture, and the variation value is used for representing the variation degree of the distortion degree; and if the variation value is larger than a preset variation threshold value, determining that the picture to be detected is a synthetic picture. Compared with the prior art, the method detects whether the picture is synthesized or tampered by the characteristic that the distortion degree of the picture subjected to JPEG compression processing of different quality factors for many times in the JPEG compression characteristic of the picture is larger along with the fluctuation of the quality factors, and the detection process of the method does not depend on a deep learning model, namely a training data set is not needed, so that the method has a good detection effect on videos with different contents, and the detection accuracy is improved.
Drawings
Fig. 1 is a schematic flowchart of a method for detecting a composite picture according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an apparatus for detecting a composite picture according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without any creative effort belong to the protection scope of the present application.
The detection method of the composite picture provided by the embodiment of the invention can be applied to a server and can also be applied to terminal equipment. In order to ensure the detection accuracy, the server can be an application server or a cloud server with stronger computing capacity; the terminal may be a User Equipment (UE), a computing device, or the like, such as a laptop, a Personal Digital Assistant (PDA), a tablet computer (PAD), or the like, which have a relatively high computing power.
The storage format of the picture may include a GIF format, a PNG format, a JPEG format, a BMP format, and the like.
In order to reduce the storage space of the pictures, the pictures generally need to be compressed. For example, compressing a picture in JPEG format, the JPEG compression process is as follows:
the picture to be compressed is first divided into 8 by 8 unit sub-blocks.
Performing Discrete Cosine Transform (DCT) on each sub-block to obtain a DCT coefficient matrix, quantizing the DCT coefficients in the DCT coefficient matrix by using a quantization table, and encoding the quantized DCT coefficients.
The quantization process removes the high frequency part in the sub-block, so that the compressed picture has distortion, and the degree of the distortion depends on the quality factor. The distortion degree caused by the higher quality factor is smaller, and the finally obtained picture has higher quality. Wherein, the quality factor is a positive integer.
Meanwhile, traces of quality factors of each compression are often left in the process of JPEG compressing the picture for multiple times.
For example, for a frame, a quality factor Q is used A Compressed picture imgA, using quality factor Q B And compressing the imgA again to obtain a picture imgB. Then, in the process of compressing the picture imgB again by adopting the quality factor Q, when Q is Q A The distortion caused by time is small, that is, the distortion of compression is small when Q is equal to Q A A minimum is taken.
Since each frame of a video corresponds to a still picture, the detection of the composition or tampering of the video content can be attributed to the detection of each frame of picture (or "picture") of the video content. When the deep learning method is adopted to synthesize or tamper the video, the modification of each frame of static picture is equivalent. Although the modified picture is difficult to find by naked eyes, the frequency distribution of a part of sub-blocks in the picture is often damaged in the modification process, so that the part of sub-blocks is equivalent to JPEG compression processing with different quality factors which is subjected to a plurality of times.
When the JPEG compression method is adopted to compress the synthesized JPEG format picture, the distortion degree of the picture has a minimum value at a plurality of quality factors, namely, the distortion degree has larger fluctuation along with the quality factors. Therefore, the processor of the terminal or the server in the embodiment of the invention detects whether the picture is synthesized by adopting a multi-time JPEG compression method, compared with the existing detection method based on deep learning, the method does not need a training set, the detection effect is only influenced by the parameters of the algorithm, and the detection can be carried out in different videos by adjusting the parameters of the algorithm, namely the content of the video to be detected is not limited.
It should be noted that compression of a JPEG format picture by using a quality factor belongs to quality compression, that is, the size of the compressed picture is not changed, and the quality of the picture is reduced.
The preferred embodiments of the present application will be described below with reference to the accompanying drawings of the specification, it being understood that the preferred embodiments described herein are merely for illustrating and explaining the present invention and are not intended to limit the present invention, and that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Fig. 1 is a schematic flowchart of a method for detecting a composite picture according to an embodiment of the present invention. The execution subject of the method may be a processor of a terminal or a server, as shown in fig. 1, the method includes:
and 110, compressing the acquired picture to be detected in the preset format by adopting a first quality factor to obtain a first-time compressed picture.
The preset format may be a JPEG format, and is described in detail below in the JPEG format of the picture to be detected.
The processor stores each frame of the video to be detected as a to-be-detected picture in JPEG format, namely converts the color video into a plurality of gray pictures, and stores the plurality of to-be-detected pictures according to the playing sequence of the video to be detected. The size of the picture to be detected is M × N, and M and N are integers larger than zero.
Then, a first quality factor Q is used H And compressing each acquired picture to be detected in the JPEG format to obtain a corresponding first-time compressed picture, and storing the obtained first-time compressed picture in a list imgList 0. Wherein the first quality factor Q H For higher quality factors, e.g. Q H ＝100。
And step 120, sequentially recompressing the first compressed picture by using at least one second quality factor to obtain at least one recompressed picture.
Wherein at least one second quality factor Q 1 For presetting a quality factor Q L And a first quality factor Q H The quality factors are arranged in the order of magnitude, and the preset quality factor is smaller than the first quality factor Q H 。
Since each Q 1 Recompressing the same first compressed picture results in a recompressed picture, so that at least one second quality factor Q 1 Can obtainA corresponding re-compressed picture, i.e. a compressed picture sequence comprising at least one re-compressed picture.
In addition, the sub-Q is adopted H The picture size of the first compressed picture obtained after compressing the picture to be detected, and the sub-Q 1 The picture size of the second compressed picture obtained after the first compressed picture is compressed is the same as the picture size of the picture to be detected, and is M × N, that is, the quality factor is adopted to compress the picture, and only the quality of the picture is compressed, that is, the pixel value is changed, and the size of the picture is not changed.
Step 130, calculating the pixel value of the first compressed picture and the pixel value of the at least one second compressed picture by using a preset detection algorithm to obtain the distortion of the at least one second compressed picture and the variation value of the distortion of the first compressed picture corresponding to the at least one second compressed picture.
The distortion degree is used for representing the distortion degree of each re-compressed picture relative to the first compressed picture, and the variation value is used for representing the variation degree of the distortion degree.
And calculating the pixel value of the first compressed picture and the pixel value of the at least one second compressed picture by adopting a preset distortion algorithm to obtain the distortion of the at least one second compressed picture.
Because the pixel values of the pictures before and after compression can change and the distortion phenomenon occurs, a first compression pixel matrix I formed by the pixel values of all the pixel points in the first compression picture and a second compression pixel matrix I formed by the pixel values of all the pixel points in each second compression picture in the compression picture sequence are obtained 1 。
Adopting a preset difference value algorithm to carry out the first compression pixel matrix I consisting of the pixel values of the first compression picture and the second compression pixel matrix I consisting of the pixel values of the corresponding pixel points of each second compression picture 1 And performing difference value operation to obtain a pixel difference value matrix D corresponding to each recompressed picture, so that at least one pixel difference value matrix D can be obtained.
The pixel difference matrix D corresponding to each recompressed picture can be expressed as:
D(m,n)＝I(m,n)-I 1 (m,n)；
wherein (M, N) is a pixel coordinate, M is a positive number not less than 1 and not more than M, and N is a positive number not less than 1 and not more than N.
And aiming at one pixel difference matrix D, calculating the pixel value of each pixel point in the pixel difference matrix D by adopting a preset sum-of-squares algorithm to obtain the pixel sum-of-squares corresponding to the pixel difference matrix D, and then, calculating the mean value of the pixel sum-of-squares corresponding to the pixel difference matrix D by adopting a preset mean value algorithm to obtain the pixel mean value corresponding to each secondary compression picture.
The process of obtaining the pixel mean value may include the following two ways:
the method comprises the steps of dividing a pixel difference value matrix into a preset number of sub-matrixes; calculating the pixel value of a pixel point in each sub-matrix in a preset number of sub-matrices by adopting a preset sum-of-squares algorithm to obtain the pixel sum-of-squares corresponding to each sub-matrix;
acquiring a pixel square sum matrix F corresponding to the pixel difference matrix according to the pixel square corresponding to the preset number of sub-matrices and the position of the preset number of sub-matrices relative to the pixel difference matrix;
for example, let the pixel difference matrix D be a 4 × 4 matrix, and divide the pixel difference matrix D into 4 sub-matrices D of 2 × 2 1 -d 4 。
Wherein the content of the first and second substances,
therefore, d 1 The position of the pixel sum-of-squares matrix F is (1,1), d 2 The position of the pixel sum of squares matrix F is (1,2), d 3 The position of the pixel sum of squares matrix F is (2,1), d 4 The position of the pixel sum-of-squares matrix F is (2, 2).
That is, after the pixel difference matrix D is an M × M matrix and is divided into a predetermined number of sub-matrices D × D, the sum of squares of each sub-matrix can be expressed as:
wherein F (i, j) represents the position of the sub-block in the pixel sum-of-squares matrix F,
indicating a rounding down.
And then, performing mean operation on the pixel square sum corresponding to the preset number of sub-matrixes in the pixel difference value matrix by adopting a preset mean algorithm to obtain the pixel mean value corresponding to each re-compressed picture.
And secondly, performing sum-of-squares operation on the pixel value of each pixel point in the pixel difference matrix D by adopting a preset sum-of-squares algorithm to obtain a pixel sum-of-squares corresponding to the pixel difference matrix D, and performing mean operation on the pixel sum-of-squares corresponding to the pixel difference matrix D and the number of the pixel points in the pixel difference matrix D by adopting a preset mean algorithm to obtain a pixel mean value corresponding to each secondary compression picture.
And determining the calculated pixel mean value as the distortion degree of each re-compressed picture, thereby obtaining at least one distortion degree. According to the arrangement order of at least one compressed picture in the compressed picture sequence, at least one distortion factor arranged in sequence can be obtained.
Further, a preset variation algorithm is adopted to calculate the distortion degree of at least one secondary compressed picture, and a variation value CV of the distortion degree is obtained. The larger the variation value CV is, the larger the modification degree is, namely, the higher the probability that the picture to be detected is a synthetic picture is; the smaller the variation value CV, the smaller the modification degree, i.e. the smaller the probability that the picture to be detected is a composite picture.
Performing difference operation on distortion degrees corresponding to every two adjacent recompressed pictures in at least one recompressed picture by adopting a preset difference algorithm to obtain a corresponding difference list;
acquiring the ratio of the standard deviation of the difference value in the difference value list to the mean value of the difference value by adopting a preset ratio algorithm;
the ratio is determined as the variation value CV of the distortion factor.
And step 140, determining whether the picture to be detected is a synthetic picture according to a comparison result of the acquired variation value and a preset variation threshold value.
Comparing the obtained variation value CV with a preset variation threshold value T;
and if the variation value CV is larger than a preset variation threshold T, determining that the picture to be detected is a synthetic picture.
Further, a single picture to be detected can be detected as a composite picture according to the condition that the variation value CV is greater than the preset variation threshold T, but for the video to be detected, the accuracy of judging whether the whole video to be detected is a composite video is not high only through a single-frame picture.
Therefore, the number r of the variation value CV which is larger than the preset variation threshold value T is obtained;
if the ratio of the number r to the number of the first compressed pictures is larger than the preset ratio threshold value r 0 And determining the video to be detected as a composite video.
That is, the ratio of the number of frames of the picture to be synthesized in the video to be detected exceeds r 0 The video to be detected can be considered to be synthesized or tampered with a higher degree of confidence.
It can be understood that, for videos to be detected with different contents, the detection method provided by the embodiment of the invention only needs to modify parameters in a detection algorithm, so that the contents of the videos to be detected are not limited, and therefore, the detection method has a good detection effect on the videos with different contents, and the detection method does not depend on a deep learning model, so that a GPU is not required for training, and the requirement on hardware is low.
The detection method of the synthesized picture provided by the embodiment of the invention firstly adopts the first quality factor to compress the obtained picture to be detected with the preset format to obtain a first compressed picture, and then adopts at least one second quality factor to sequentially recompress the first compressed picture to obtain at least one second compressed picture; at least one second quality factor is a quality factor which is arranged between a preset low quality factor and the first quality factor according to the size sequence; calculating the pixel value of the first compressed picture and the pixel value of at least one second compressed picture by adopting a preset detection algorithm to obtain the distortion degree of the at least one second compressed picture and the variation value of the distortion degree of the first compressed picture corresponding to the at least one second compressed picture, wherein the distortion degree is used for representing the distortion degree of each second compressed picture relative to the first compressed picture, and the variation value is used for representing the variation degree of the distortion degree; and if the variation value is larger than a preset variation threshold value, determining that the picture to be detected is a synthetic picture. Compared with the prior art, the method detects whether the picture is synthesized or tampered by the characteristic that the distortion degree of the picture subjected to JPEG compression processing of different quality factors for multiple times in the JPEG compression characteristic of the picture is larger along with the fluctuation of the quality factors, and the detection process of the method does not depend on a deep learning model, namely a training data set is not needed, so that the method has a good detection effect on videos with different contents, and the detection accuracy is improved.
Corresponding to the above method, an embodiment of the present invention further provides a device for detecting a synthesized picture, as shown in fig. 2, the device for detecting a synthesized picture includes: a compression unit 210, an arithmetic unit 220, and a determination unit 230;
a compressing unit 210, configured to compress the acquired to-be-detected picture in the preset format by using a first quality factor to obtain a first-time compressed picture;
the compressing unit 210 is further configured to sequentially recompress the first compressed picture by using at least one second quality factor to obtain at least one recompressed picture; the at least one second quality factor is at least one quality factor arranged between a preset quality factor and the first quality factor according to the size sequence, and the preset quality factor is smaller than the first quality factor;
an operation unit 220, configured to calculate, by using a preset detection algorithm, a pixel value of the first compressed picture and a pixel value of the at least one second compressed picture to obtain a distortion of the at least one second compressed picture and a variation value of the distortion of the first compressed picture corresponding to the at least one second compressed picture, where the distortion is used to indicate a distortion degree of each second compressed picture relative to the first compressed picture, and the variation value is used to indicate a variation degree of the distortion;
a determining unit 230, configured to determine that the picture to be detected is a composite picture if the variation value is greater than a preset variation threshold T.
In an optional implementation, the operation unit is specifically configured to calculate a pixel value of the first compressed picture and a pixel value of the at least one second compressed picture by using a preset distortion algorithm, so as to obtain a distortion of the at least one second compressed picture;
and calculating the distortion degree corresponding to the at least one recompressed picture by adopting a preset variation algorithm to obtain a variation value of the distortion degree.
In an optional implementation, the operation unit 220 is further specifically configured to perform a difference operation on the pixel value of the first compressed picture and the pixel value of the pixel point corresponding to each second compressed picture in the at least one second compressed picture by using a preset difference algorithm, so as to obtain a pixel difference matrix corresponding to each second compressed picture;
calculating the pixel value of each pixel point in the pixel difference value matrix by adopting a preset sum-of-squares algorithm to obtain a pixel sum-of-squares corresponding to the pixel difference value matrix;
performing mean operation on the pixel square sum corresponding to the pixel difference value matrix by adopting a preset mean algorithm to obtain a pixel mean value corresponding to each secondary compression image;
and determining the pixel mean value as the distortion degree of each re-compressed picture.
In an optional implementation, the operation unit 220 is further specifically configured to divide the pixel difference matrix into a preset number of sub-matrices;
calculating the pixel value of a pixel point in each sub-matrix in the preset number of sub-matrices by adopting a preset sum-of-squares algorithm to obtain a pixel sum-of-squares corresponding to each sub-matrix;
and performing mean value operation on the pixel square sum corresponding to the preset number of sub-matrixes in the pixel difference value matrix by adopting a preset mean value algorithm to obtain a pixel mean value corresponding to each secondary compression picture.
In an optional implementation, the operation unit 220 is further specifically configured to perform a difference operation on distortion degrees corresponding to every two adjacent recompressed pictures in the at least one recompressed picture by using a preset difference algorithm to obtain a corresponding difference list;
acquiring the ratio of the standard deviation of the difference values in the difference value list to the mean value of the difference values by adopting a preset ratio algorithm;
and determining the ratio as the variation value of the distortion factor.
In an optional implementation, if the picture to be detected is at least one frame of picture of the video to be detected, the number of the first compressed pictures is at least one;
a determining unit 230, further configured to obtain the number of the variance values greater than a preset variance threshold T;
and if the ratio of the number to the number of the first compressed pictures is greater than a preset proportion threshold value, determining that the video to be detected is a composite video.
The functions of the functional units of the apparatus for detecting a synthesized picture according to the above embodiments of the present invention can be implemented by the above method steps, and therefore, detailed working processes and beneficial effects of the units in the apparatus for detecting a synthesized picture according to the embodiments of the present invention are not repeated herein.
An embodiment of the present invention further provides an electronic device, as shown in fig. 3, including a processor 310, a communication interface 320, a memory 330, and a communication bus 340, where the processor 310, the communication interface 320, and the memory 330 complete mutual communication through the communication bus 340.
A memory 330 for storing a computer program;
the processor 310, when executing the program stored in the memory 330, implements the following steps:
compressing the acquired picture to be detected in a preset format by adopting a first quality factor to obtain a first compressed picture;
sequentially recompressing the first compressed picture by adopting at least one second quality factor to obtain at least one recompressed picture; the at least one second quality factor is at least one quality factor arranged between a preset quality factor and the first quality factor according to the size sequence, and the preset quality factor is smaller than the first quality factor;
calculating the pixel value of the first compressed picture and the pixel value of the at least one second compressed picture by adopting a preset detection algorithm to obtain the distortion degree of the at least one second compressed picture and the variation value of the distortion degree of the first compressed picture corresponding to the at least one second compressed picture, wherein the distortion degree is used for representing the distortion degree of each second compressed picture relative to the first compressed picture, and the variation value is used for representing the variation degree of the distortion degree;
and if the variation value is larger than a preset variation threshold value T, determining that the picture to be detected is a synthetic picture.
In an optional implementation, calculating, by using a preset detection algorithm, a pixel value of the first compressed picture and a pixel value of the at least one second compressed picture to obtain a distortion of the at least one second compressed picture and a variation value of the distortion of the first compressed picture corresponding to the at least one second compressed picture, includes:
calculating the pixel value of the first compressed picture and the pixel value of the at least one second compressed picture by adopting a preset distortion algorithm to obtain the distortion degree of the first compressed picture corresponding to the at least one second compressed picture;
and calculating the distortion degree corresponding to the at least one recompressed picture by adopting a preset variation algorithm to obtain a variation value of the distortion degree.
In an optional implementation, calculating the pixel value of the first compressed picture and the pixel value of the at least one second compressed picture by using a preset distortion algorithm to obtain the distortion of the at least one second compressed picture includes:
performing difference operation on the pixel value of the first compressed picture and the pixel value of the corresponding pixel point of each second compressed picture in the at least one second compressed picture by adopting a preset difference algorithm to obtain a pixel difference matrix corresponding to each second compressed picture;
calculating the pixel value of each pixel point in the pixel difference value matrix by adopting a preset sum-of-squares algorithm to obtain a pixel sum-of-squares corresponding to the pixel difference value matrix;
performing mean operation on the pixel square sum corresponding to the pixel difference value matrix by adopting a preset mean algorithm to obtain a pixel mean value corresponding to each secondary compression image;
and determining the pixel mean value as the distortion degree of each re-compressed picture.
In an optional implementation, a preset sum of squares algorithm is adopted to calculate a pixel value of each pixel point in the pixel difference matrix to obtain a pixel sum of squares corresponding to the pixel difference matrix, including:
dividing the pixel difference matrix into a preset number of sub-matrices;
calculating the pixel value of a pixel point in each sub-matrix in the preset number of sub-matrices by adopting a preset sum-of-squares algorithm to obtain a pixel sum-of-squares corresponding to each sub-matrix;
and performing mean operation on the pixel square sum corresponding to the pixel difference value matrix by adopting a preset mean algorithm to obtain a pixel mean value corresponding to each secondary compression image, wherein the mean operation comprises the following steps:
and performing mean value operation on the pixel square sum corresponding to the preset number of sub-matrixes in the pixel difference value matrix by adopting a preset mean value algorithm to obtain a pixel mean value corresponding to each secondary compression picture.
In an optional implementation, the calculating, by using a preset variation algorithm, a distortion factor corresponding to the at least one recompressed picture to obtain a variation value of the distortion factor includes:
performing difference operation on the distortion degrees corresponding to every two adjacent recompressed pictures in the at least one recompressed picture by adopting a preset difference algorithm to obtain a corresponding difference list;
acquiring the ratio of the standard deviation of the difference values in the difference value list to the mean value of the difference values by adopting a preset ratio algorithm;
and determining the ratio as the variation value of the distortion degree.
In an optional implementation, if the picture to be detected is at least one frame of picture of the video to be detected, the number of the first compressed pictures is at least one;
after determining that the picture to be detected is a composite picture, the method further comprises:
acquiring the number of the variation values larger than a preset variation threshold T;
and if the ratio of the number to the number of the first compressed pictures is greater than a preset proportion threshold value, determining that the video to be detected is a composite video.
The aforementioned communication bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
Since the implementation manner and the beneficial effects of the problem solving of each device of the electronic device in the foregoing embodiment can be implemented by referring to each step in the embodiment shown in fig. 1, detailed working processes and beneficial effects of the electronic device provided by the embodiment of the present invention are not described herein again.
In another embodiment of the present invention, there is further provided a computer-readable storage medium, in which instructions are stored, and when the instructions are executed on a computer, the instructions cause the computer to execute the method for detecting a composite picture according to any one of the above embodiments.
In another embodiment of the present invention, there is also provided a computer program product containing instructions, which when run on a computer, causes the computer to execute the method for detecting a composite picture according to any one of the above embodiments.
As will be appreciated by one of skill in the art, the embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the true scope of the embodiments of the present application.
It is apparent that those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. Thus, if such modifications and variations of the embodiments of the present application fall within the scope of the claims of the embodiments of the present application and their equivalents, the embodiments of the present application are also intended to include such modifications and variations.
Claims (10)
1. A method for detecting a composite picture, the method comprising:
compressing the acquired picture to be detected in a preset format by adopting a first quality factor to obtain a first compressed picture;
sequentially recompressing the first compressed picture by adopting at least one second quality factor to obtain at least one recompressed picture; the at least one second quality factor is at least one quality factor arranged between a preset quality factor and the first quality factor according to the size sequence, and the preset quality factor is smaller than the first quality factor;
performing difference operation on the pixel value of the first compressed picture and the pixel value of the corresponding pixel point of each second compressed picture in the at least one second compressed picture by adopting a preset difference algorithm to obtain a pixel difference matrix corresponding to each second compressed picture; calculating the pixel value of each pixel point in the pixel difference value matrix by adopting a preset sum-of-squares algorithm to obtain a pixel sum-of-squares corresponding to the pixel difference value matrix; performing mean operation on the pixel square sum corresponding to the pixel difference value matrix by adopting a preset mean algorithm to obtain a pixel mean value corresponding to each secondary compression image; determining the pixel mean value as a distortion degree of each secondary compressed picture, wherein the distortion degree is used for representing the distortion degree of each secondary compressed picture relative to the primary compressed picture;
calculating the distortion degree corresponding to the at least one secondary compressed picture by adopting a preset variation algorithm to obtain a variation value of the distortion degree of the primary compressed picture corresponding to the at least one secondary compressed picture, wherein the variation value is used for expressing the variation degree of the distortion degree;
and if the variation value is larger than a preset variation threshold value, determining that the picture to be detected is a composite picture.
2. The method of claim 1, wherein calculating a pixel value of each pixel in the pixel difference matrix using a preset sum-of-squares algorithm to obtain a pixel sum-of-squares corresponding to the pixel difference matrix comprises:
dividing the pixel difference matrix into a preset number of sub-matrices;
calculating the pixel value of a pixel point in each sub-matrix in the preset number of sub-matrices by adopting a preset sum-of-squares algorithm to obtain a pixel sum-of-squares corresponding to each sub-matrix;
and performing mean operation on the pixel square sum corresponding to the pixel difference value matrix by adopting a preset mean algorithm to obtain a pixel mean value corresponding to each secondary compression image, wherein the mean operation comprises the following steps:
and performing mean value operation on the pixel square sum corresponding to the preset number of sub-matrixes in the pixel difference value matrix by adopting a preset mean value algorithm to obtain a pixel mean value corresponding to each secondary compression picture.
3. The method as claimed in claim 1, wherein the step of calculating the distortion factor corresponding to the at least one recompressed picture by using a predetermined variance algorithm to obtain a variance value of the distortion factor comprises:
performing difference operation on the distortion degrees corresponding to every two adjacent recompressed pictures in the at least one recompressed picture by adopting a preset difference algorithm to obtain a corresponding difference list;
acquiring the ratio of the standard deviation of the difference values in the difference value list to the mean value of the difference values by adopting a preset ratio algorithm;
and determining the ratio as the variation value of the distortion factor.
4. The method according to claim 1, wherein if the picture to be detected is at least one frame of picture of the video to be detected, the number of the first compressed pictures is at least one;
after determining that the picture to be detected is a composite picture, the method further comprises:
acquiring the number of the variation values larger than a preset variation threshold;
and if the ratio of the number to the number of the first compressed pictures is greater than a preset proportion threshold value, determining that the video to be detected is a composite video.
5. An apparatus for detecting a composite picture, the apparatus comprising: a compression unit, an arithmetic unit and a determination unit;
the compression unit is used for compressing the acquired picture to be detected in the preset format by adopting a first quality factor to obtain a first-time compressed picture;
the compression unit is further configured to sequentially recompress the first compressed picture by using at least one second quality factor to obtain at least one recompressed picture; the at least one second quality factor is at least one quality factor arranged between a preset quality factor and the first quality factor according to the size sequence, and the preset quality factor is smaller than the first quality factor;
the operation unit is used for performing difference operation on the pixel value of the first compressed picture and the pixel value of the pixel point corresponding to each second compressed picture in the at least one second compressed picture by adopting a preset difference algorithm to obtain a pixel difference matrix corresponding to each second compressed picture; calculating the pixel value of each pixel point in the pixel difference value matrix by adopting a preset sum-of-squares algorithm to obtain a pixel sum-of-squares corresponding to the pixel difference value matrix; performing mean operation on the pixel square sum corresponding to the pixel difference value matrix by adopting a preset mean algorithm to obtain a pixel mean value corresponding to each secondary compression image; determining the pixel mean value as a distortion degree of each secondary compressed picture, wherein the distortion degree is used for representing the distortion degree of each secondary compressed picture relative to the primary compressed picture; calculating the distortion degree corresponding to the at least one secondary compressed picture by adopting a preset variation algorithm to obtain a variation value of the distortion degree of the primary compressed picture corresponding to the at least one secondary compressed picture, wherein the variation value is used for expressing the variation degree of the distortion degree;
the determining unit is configured to determine that the picture to be detected is a composite picture if the variation value is greater than a preset variation threshold.
6. The apparatus of claim 5,
the operation unit is further specifically configured to divide the pixel difference matrix into a preset number of sub-matrices;
calculating the pixel value of a pixel point in each sub-matrix in the preset number of sub-matrices by adopting a preset square sum algorithm to obtain a pixel square sum corresponding to each sub-matrix;
and performing mean value operation on the pixel square sum corresponding to the preset number of sub-matrixes in the pixel difference value matrix by adopting a preset mean value algorithm to obtain a pixel mean value corresponding to each secondary compression picture.
7. The apparatus of claim 6,
the operation unit is further specifically configured to perform a difference operation on distortion degrees corresponding to every two adjacent recompressed pictures in the at least one recompressed picture by using a preset difference algorithm to obtain a corresponding difference list;
acquiring the ratio of the standard deviation of the difference values in the difference value list to the mean value of the difference values by adopting a preset ratio algorithm;
and determining the ratio as the variation value of the distortion degree.
8. The apparatus according to claim 5, wherein if the picture to be detected is at least one frame of picture of the video to be detected, the number of the first compressed pictures is at least one;
the determining unit is further configured to obtain the number of the variation values larger than a preset variation threshold;
and if the ratio of the number to the number of the first compressed pictures is greater than a preset proportion threshold value, determining that the video to be detected is a composite video.
9. An electronic device, characterized in that the electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1-4 when executing a program stored on a memory.
10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911205016.5A CN110910380B (en) | 2019-11-29 | 2019-11-29 | Detection method and device for synthesized picture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911205016.5A CN110910380B (en) | 2019-11-29 | 2019-11-29 | Detection method and device for synthesized picture |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110910380A CN110910380A (en) | 2020-03-24 |
| CN110910380B true CN110910380B (en) | 2022-09-20 |
Family
ID=69820812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911205016.5A Active CN110910380B (en) | 2019-11-29 | 2019-11-29 | Detection method and device for synthesized picture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110910380B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117252879B (en) * | 2023-11-17 | 2024-04-05 | 深圳禾思众成科技有限公司 | Microscopic line scanning imaging system for semiconductor detection and control method thereof |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007271940A (en) * | 2006-03-31 | 2007-10-18 | Toshiba Corp | Video displaying device and video displaying method |
| CN102957915B (en) * | 2012-11-15 | 2015-03-25 | 西安理工大学 | Double JPEG (Joint Photographic Experts Group) compressed image-targeted tamper detection and tamper locating method |
| CN104796726B (en) * | 2015-04-10 | 2018-02-02 | 北京邮电大学 | A kind of method of detection image compression vestige |
| CN105654448B (en) * | 2016-03-29 | 2018-11-27 | 微梦创科网络科技（中国）有限公司 | A kind of image interfusion method and system based on bilateral filtering and weight reconstruction |
| CN107045551B (en) * | 2017-04-26 | 2020-10-27 | 湖南人文科技学院 | Hunan embroidery image gene construction and Hunan embroidery image digital processing method |
| CN107274334A (en) * | 2017-06-28 | 2017-10-20 | 南京信息工程大学 | A kind of color image-adaptive water mark method based on Quaternion Transformation |
-
2019
- 2019-11-29 CN CN201911205016.5A patent/CN110910380B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110910380A (en) | 2020-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10692218B2 (en) | Method and system of detecting image tampering, electronic device and storage medium | |
| WO2016082277A1 (en) | Video authentication method and apparatus | |
| US20230008085A1 (en) | Method for embedding watermark in video data and apparatus, method for extracting watermark in video data and apparatus, device, and storage medium | |
| CN112950581A (en) | Quality evaluation method and device and electronic equipment | |
| WO2022022154A1 (en) | Facial image processing method and apparatus, and device and storage medium | |
| CN107770525B (en) | Image coding method and device | |
| CN106203461B (en) | Image processing method and device | |
| Yang et al. | Analyzing the effect of JPEG compression on local variance of image intensity | |
| JP6570155B2 (en) | Video reconstruction method, system, electronic device and storage medium using compressed sensing | |
| CN110378893B (en) | Image quality evaluation method and device and electronic equipment | |
| CN103067713B (en) | Method and system of bitmap joint photographic experts group (JPEG) compression detection | |
| CN110136052B (en) | Image processing method and device and electronic equipment | |
| CN111814776B (en) | Image processing method, device, server and storage medium | |
| CN104392207A (en) | Characteristic encoding method for recognizing digital image content | |
| CN110910380B (en) | Detection method and device for synthesized picture | |
| CN112116568A (en) | Image quality evaluation method and device and storage medium | |
| CN114119560A (en) | Image quality evaluation method, system, and computer-readable storage medium | |
| Li et al. | A content-aware image retargeting quality assessment method using foreground and global measurement | |
| CN109685757B (en) | Non-reference image quality evaluation method and system based on gray difference statistics | |
| CN113298102B (en) | Training method and device for target classification model | |
| CN103530886A (en) | Low-calculation background removing method for video analysis | |
| CN112183359A (en) | Violent content detection method, device and equipment in video | |
| CN110647805A (en) | Reticulated image identification method and device and terminal equipment | |
| CN112465028B (en) | Perception visual safety assessment method and system | |
| CN114494146A (en) | Visual security assessment method and system for selectively encrypted image |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100089 Beijing city Haidian District Road No. 4 North wa Yitai three storey building Applicant after: NSFOCUS Technologies Group Co.,Ltd. Applicant after: NSFOCUS TECHNOLOGIES Inc. Address before: 100089 Beijing city Haidian District Road No. 4 North wa Yitai three storey building Applicant before: NSFOCUS INFORMATION TECHNOLOGY Co.,Ltd. Applicant before: NSFOCUS TECHNOLOGIES Inc. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |