CN116452836A - New media material content acquisition system based on image data processing - Google Patents
New media material content acquisition system based on image data processing Download PDFInfo
- Publication number
- CN116452836A CN116452836A CN202310519453.4A CN202310519453A CN116452836A CN 116452836 A CN116452836 A CN 116452836A CN 202310519453 A CN202310519453 A CN 202310519453A CN 116452836 A CN116452836 A CN 116452836A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- port
- violation
- materials
- 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
- 239000000463 material Substances 0.000 title claims abstract description 392
- 238000012545 processing Methods 0.000 title claims abstract description 94
- 238000003860 storage Methods 0.000 claims abstract description 61
- 239000012634 fragment Substances 0.000 claims abstract description 42
- 238000004458 analytical method Methods 0.000 claims abstract description 23
- 238000009432 framing Methods 0.000 claims abstract description 21
- 239000013598 vector Substances 0.000 claims description 121
- 230000005540 biological transmission Effects 0.000 claims description 48
- 238000000605 extraction Methods 0.000 claims description 36
- 239000011159 matrix material Substances 0.000 claims description 36
- 238000004364 calculation method Methods 0.000 claims description 32
- 238000000034 method Methods 0.000 claims description 14
- 230000009466 transformation Effects 0.000 claims description 12
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/001—Texturing; Colouring; Generation of texture or colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a new media material content acquisition system based on image data processing, which relates to the technical field of multimedia and comprises a material acquisition port, a material analysis port, a material processing port, a material classification port and a material storage port, wherein the material analysis port is used for framing images in materials, calculating the similarity between the images in the materials and the acquired images related to illegal contents in a material library through python software, forming illegal fragments with similarity larger than a comparison value, submitting the illegal fragments to an administrator to confirm whether illegal information exists or not, and the material processing port is used for processing the images in the fragments with the illegal information confirmed to exist by the administrator through an image processing formula, so that the labor cost and the time cost required by manual auditing of the material content are reduced, the efficiency of material auditing is improved, and the illegal fragments are stored in the material library to increase the diversity of the materials, so that the illegal contents are easier to be identified.
Description
Technical Field
The invention relates to the technical field of multimedia, in particular to a new media material content acquisition system based on image data processing.
Background
Image data processing is a technology for processing image data according to requirements by means of image data denoising, graph segmentation, image data enhancement and the like, and in recent years, the image processing technology is mature and is widely applied to aerospace, military, biomedicine, artificial intelligence and the like;
the development of scientific technology continuously promotes the rapid development of new media, the acquisition of material content is an indispensable ring in the new media, the acquired material content is good and uneven, even illegal content exists, however, in the prior art, the number of the material with illegal content in a material library is less, the illegal content in some materials cannot be identified due to lack of diversity, and the manpower cost and the time cost required for auditing the material content in a manual mode are high, so that the auditing efficiency of the material is low;
for example, chinese patent with grant publication number CN110248198B discloses a media information aggregation method, device and system, wherein the information aggregation method comprises the following steps: a receiving step: receiving and storing media materials with labels, which are sent by a first user through a network; classification: classifying the media materials according to the labels, and gathering the media materials in the same category; and the processing steps: the media materials are processed according to the collected categories of the media materials, so that large-scale and real-time collection of news materials can be realized, a large number of first-line news materials can be collected, and more first-line materials are provided for news content production;
for example, chinese patent application publication No. CN109151360a discloses a method and apparatus for previewing multimedia content, in a process of performing a time shooting based on a first multimedia content and a second multimedia content, if a time shooting preview instruction is received, acquiring a first time shooting material and a second time shooting material according to the time shooting preview instruction, where the first time shooting material is a copy of the first multimedia content acquired by the terminal through an acquisition device in the time shooting process, and the second time shooting material is a copy of the second multimedia content; synthesizing the first photographing material and the second photographing material into preview content; and playing the preview content. The preview content is synthesized based on the copy of the first multimedia content and the copy of the second multimedia content, so that the preview of the multimedia content in the process of shooting in time can be realized;
the invention provides a new media material content acquisition system based on image data processing, which aims to solve the technical problems in the background technology.
Disclosure of Invention
The invention aims to provide a new media material content acquisition system based on image data processing, which is used for solving the technical problems in the background technology: the collected material content is good and even has illegal content, however, in the prior art, the material quantity of the illegal content in the material library is less, the illegal content in some materials cannot be identified due to lack of diversity, and the manpower cost and the time cost required for auditing the material content in a manual mode are large, so that the auditing efficiency of the material is lower.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
a new media material content acquisition system based on image data processing comprises a material acquisition port, a material analysis port, a material processing port, a material classification port and a material storage port;
the material acquisition port is used for acquiring and storing materials;
the material storage port is used for storing material classification ports classified materials and material fragments with illegal contents;
the invention further improves that the material analysis port is used for framing the images in the materials, calculating the similarity between the framed images and the acquired images related to the illegal contents in the material library through python software, forming illegal fragments with the similarity larger than a comparison value, submitting the illegal fragments to an administrator to confirm whether illegal information exists;
the material processing port is used for carrying out replacement processing on the image after confirming that the administrator has the image vector transformation in the fragment of the violation information through the image processing formula;
the material classification port is used for comparing the images after framing with the images in the material library materials, and classifying the collected materials into the same type with the materials in the material library with the highest similarity with the materials.
The material analysis port comprises an image extraction module, a first color feature vector extraction module, a violation image similarity calculation module, a data feedback module and a first data transmission module, wherein the image extraction module is used for carrying out framing processing on materials and extracting images in each frame; the first color feature vector extraction module is used for extracting color feature vectors of each frame of image in the material and the acquired images in the fragments related to the illegal contents in the material library through python software; the violation image similarity calculation module calculates the similarity between each frame of image and the acquired images related to the violation content fragments in the material library through a violation image similarity calculation formula; the data feedback module is used for submitting the fragments with the similarity alpha of the violation images larger than the comparison value to an administrator, and the administrator confirms whether violation information exists or not; the first data transmission module is used for data transmission among the image extraction module, the first color feature vector extraction module, the illegal image similarity calculation module and the data feedback module.
The invention further improves that the similarity of the illegal images in the material analysis port is as follows:wherein cosine similarity->So wherein A is i B is the color feature vector of the image in the segment related to the offence content acquired in the material library i For each frame of image, t is a color feature vector i For the duration of the illegal content in the collected materials, N is dividing the image after framing into N equal divisions, setting the contrast value of alpha to be 0.8 and x i Is 0.8.
The material processing port comprises a first data acquisition and storage module, an image processing module and a second data transmission module, wherein the first data acquisition and storage module is used for acquiring and storing the color feature vector B of each frame of image calculated by the material analysis port i And cosine similarity x i The method comprises the steps of carrying out a first treatment on the surface of the The image processing module is used for processing cosine similarity x in the segments related to illegal contents in the materials through an image processing formula in python software i Processing the images with the contrast value to obtain color vectors of the processed violation images, and replacing the violation images in the material by pictures formed by the color vectors of the processed violation images; the second data transmission module is used for data transmission between the first data acquisition and storage module and the image processing module.
Further of the invention the improvement lies in that, the image processing formula is B 1 =xb, where B is the n-order color feature vector of the image passing through the violation information present in the material (B 1 ，b 2 ，b 3 ，…，b n ) X is a defined n-order transform matrix as a transform matrix (z 1 ，z 2 ，z 3 ，…，z n )，B 1 Color vectors of images with violation information in the transformed materials; processed violationsColor vector y=db of image 1 Wherein D is a python software randomly generated nth order matrix (D 1 ，d 2 ，d 3 ，…，d n ) The color vector Y of the processed offending image is (Y 1 ，y 2 ，y 3 ，…，y n ) And enabling the color vector Y of the processed violation image and the n-order color feature vector B of the image with violation information in the material to meet the replacement condition.
A further improvement of the invention is that the substitution conditions are:setting the contrast value of phi to be 0.5, and when phi is smaller than 0.5, the replacement condition is satisfied, wherein B is an n-order color feature vector (B) of an image with violation information in the material 1 ，b 2 ，b 3 ，…，b n ) Y is the color vector (Y 1 ，y 2 ，y 3 ，…，y n )。
The material classification port comprises a material acquisition module, a second color feature vector extraction module, a material similarity calculation module, a material classification module and a third data transmission module, wherein the material acquisition module is used for acquiring the image processed by the material processing port; the second color feature vector extraction module is used for extracting color feature vectors of images in the acquired materials; the material similarity calculation module calculates the similarity beta of the collected materials and the materials in the material library through a material similarity calculation formula; the material classification module is used for classifying the collected materials according to the material similarity beta and classifying the collected materials and the materials in the material library with the maximum material similarity beta into the same type of materials; the third data transmission module is used for data transmission among the material acquisition module, the second color feature vector extraction module, the material similarity calculation module and the material classification module.
The invention further improves that the material similarity formula in the material classification port is as follows:wherein->Wherein E is i For the color feature vector of the image in the collected materials in the material library, F i And (3) dividing the image after framing into M equal parts for the color feature vector of the image in the acquired material, wherein T is the duration of the acquired material.
The material storage port comprises a second data acquisition and storage module, a material storage module, an offending fragment storage module and a fourth data transmission module, wherein the second data acquisition and storage module is used for acquiring and storing data of a material processing port, and the data comprises a vector B of an image with offending information in the transformed material 1 The vector Y of the processed violation image, the transformation matrix X and the n-order matrix D randomly generated by python software; the material storage module is used for storing images of the same category in the corresponding category of the material library according to the classification result of the material classification port; the violation segment storage module restores the vector of the processed image with the violation information through inputting an image restoration formula into the python software, obtains the violation segment according to the vector of the restored image with the violation information, and stores the violation segment into a violation segment library in the material library; the fourth data transmission module is used for data transmission among the second data acquisition and storage module, the material storage module and the violation fragment storage module.
The invention is further improved in that the image restoration formula is: b (B) 1 ＝YD -1 Wherein D is -1 For the inverse matrix of the n-th order matrix D randomly generated by the python software, Y is the vector of the processed offending image, b=b 1 X -1 Wherein B is 1 For the vector of the image with violation information in the transformed material, X is defined n-order transformation matrix, X -1 An inverse of the n-th order matrix X randomly generated for the python software.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention provides a new media material content acquisition system based on image data processing, which can compare illegal contents in materials through the system and submit the illegal contents to an administrator for confirmation, thereby greatly reducing the labor cost and time cost required by manually auditing the material contents and improving the material auditing efficiency.
2. The invention provides a new media material content acquisition system based on image data processing, which can process the checked material with illegal content and store the illegal fragments into a material library to increase the diversity of the material, so that the illegal content is easier to identify.
3. The invention provides a new media material content acquisition system based on image data processing, which can calculate the similarity of acquired materials and materials in a material library and accurately classify the materials.
Drawings
FIG. 1 is a block diagram of a new media material content acquisition system based on image data processing in accordance with the present invention.
Detailed Description
The following examples of the present invention are presented in order to illustrate and describe the invention in more detail and not to limit the invention to the form disclosed, and many modifications and variations will be apparent to those skilled in the art.
Example 1
The invention provides a new media material content acquisition system based on image data processing, which can compare illegal contents in materials through the system and then submit the illegal contents to an administrator for confirmation, thereby greatly reducing labor cost and time cost required by manually auditing the material contents and improving material auditing efficiency, and the specific scheme is that, as shown in figure 1, the new media material content acquisition system based on image data processing comprises the following specific contents:
a new media material content acquisition system based on image data processing comprises a material acquisition port, a material analysis port, a material processing port, a material classification port and a material storage port;
the material acquisition port is used for acquiring and storing materials;
the material storage port is used for storing the materials classified by the material classification port and the material fragments with illegal contents;
the material analysis port is used for framing images in the materials, calculating the similarity between the framed images and the acquired images related to the illegal contents in the material library through python software, forming illegal fragments by fragments with the similarity larger than a comparison value, and submitting the illegal fragments to an administrator to confirm whether illegal information exists;
the material processing port is used for carrying out replacement processing on the image after confirming that the image vector in the fragment with the violation information is transformed by the administrator through the image processing formula;
the material classification port is used for comparing the images after framing with the images in the material library materials, and classifying the collected materials into the same type with the materials in the material library with the highest similarity with the materials.
The material analysis port comprises an image extraction module, a first color feature vector extraction module, a violation image similarity calculation module, a data feedback module and a first data transmission module, wherein the image extraction module is used for carrying out framing treatment on materials and extracting images in each frame; the first color feature vector extraction module is used for extracting color feature vectors of each frame of image in the material and the acquired images in the segments related to the illegal contents in the material library through python software; the violation image similarity calculation module calculates the similarity between each frame of image and the collected images related to the violation content fragments in the material library through a violation image similarity calculation formula; the data feedback module is used for submitting the fragments with the similarity alpha of the violation images larger than the comparison value to an administrator, and the administrator confirms whether the violation information exists; the first data transmission module is used for data transmission among the image extraction module, the first color feature vector extraction module, the illegal image similarity calculation module and the data feedback module.
The similarity of the illegal images in the material analysis port is as follows:wherein cosine similaritySo wherein A is i B is the color feature vector of the image in the segment related to the offence content acquired in the material library i For each frame of image, t is a color feature vector i For the duration of the illegal content in the collected materials, N is dividing the image after framing into N equal divisions, setting the contrast value of alpha to be 0.8 and x i Is 0.8.
The material processing port comprises a first data acquisition and storage module, an image processing module and a second data transmission module, wherein the first data acquisition and storage module is used for acquiring and storing the color feature vector B of each frame of image calculated by the material analysis port i And cosine similarity x i The method comprises the steps of carrying out a first treatment on the surface of the The image processing module is used for processing the cosine similarity x in the segments related to the illegal contents in the materials through an image processing formula in python software i Processing the images with the contrast value to obtain color vectors of the processed violation images, and replacing the violation images in the material by pictures formed by the color vectors of the processed violation images; the second data transmission module is used for data transmission between the first data acquisition and storage module and the image processing module.
The image processing formula is B 1 =xb, where B is the n-order color feature vector of the image passing through the violation information present in the material (B 1 ，b 2 ，b 3 ，…，b n ) X is a defined n-order transform matrix as a transform matrix (z 1 ，z 2 ，z 3 ，…，z n )，B 1 Color vectors of images with violation information in the transformed materials; color vector y=db of the processed offence image 1 Wherein D is pythe thon software randomly generates an n-order matrix (d 1 ，d 2 ，d 3 ，…，d n ) The color vector Y of the processed offending image is (Y 1 ，y 2 ，y 3 ，…，y n ) And enabling the color vector Y of the processed violation image and the n-order color feature vector B of the image with violation information in the material to meet the replacement condition.
The replacement conditions are:setting the contrast value of phi to be 0.5, and when phi is smaller than 0.5, the replacement condition is satisfied, wherein B is an n-order color feature vector (B) of an image with violation information in the material 1 ，b 2 ，b 3 ，…，b n ) Y is the color vector (Y 1 ，y 2 ，y 3 ，…，y n )。
The material classification port comprises a material acquisition module, a second color feature vector extraction module, a material similarity calculation module, a material classification module and a third data transmission module, wherein the material acquisition module is used for acquiring the image processed by the material processing port; the second color feature vector extraction module is used for extracting color feature vectors of images in the acquired materials; the material similarity calculation module calculates the similarity beta of the collected materials and the materials in the material library through a material similarity calculation formula; the material classification module is used for classifying the collected materials according to the material similarity beta and classifying the collected materials and the materials in the material library with the maximum material similarity beta into the same type of materials; the third data transmission module is used for data transmission among the material acquisition module, the second color feature vector extraction module, the material similarity calculation module and the material classification module.
The material similarity formula in the material classification port is:wherein->Wherein E is i For the color feature vector of the image in the collected materials in the material library, F i And (3) dividing the image after framing into M equal parts for the color feature vector of the image in the acquired material, wherein T is the duration of the acquired material.
The material storage port comprises a second data acquisition and storage module, a material storage module, a violation fragment storage module and a fourth data transmission module, wherein the second data acquisition and storage module is used for acquiring and storing data of a material processing port and comprises a vector B of an image with violation information in the transformed material 1 The vector Y of the processed violation image, the transformation matrix X and the n-order matrix D randomly generated by python software; the material storage module is used for storing images of the same category in the corresponding category of the material library according to the classification result of the material classification port; the violation segment storage module restores the vector of the processed image with the violation information through inputting an image restoration formula into python software, obtains the violation segment according to the vector of the restored image with the violation information, and stores the violation segment into a violation segment library in the material library; the fourth data transmission module is used for data transmission among the second data acquisition and storage module, the material storage module and the violation fragment storage module.
The image restoration formula is: b (B) 1 ＝YD -1 Wherein D is -1 For the inverse matrix of the n-th order matrix D randomly generated by the python software, Y is the vector of the processed offending image, b=b 1 X -1 Wherein B is 1 For the vector of the image with violation information in the transformed material, X is defined n-order transformation matrix, X -1 An inverse of the n-th order matrix X randomly generated for the python software.
In this embodiment, the similarity α of the offending image in the material analysis port is 0.96, greater than the contrast value, and the contrast value is 0.8, and should be submitted to the administrator to confirm whether offending information exists.
Example 2
The invention provides a new media material content acquisition system based on image data processing, which can process the checked material with illegal content, and store the illegal fragments into a material library to increase the diversity of the material, so that the illegal content is easier to be identified.
A new media material content acquisition system based on image data processing comprises a material acquisition port, a material analysis port, a material processing port, a material classification port and a material storage port;
the material acquisition port is used for acquiring and storing materials;
the material storage port is used for storing the materials classified by the material classification port and the material fragments with illegal contents;
the material analysis port is used for framing images in the materials, calculating the similarity between the framed images and the acquired images related to the illegal contents in the material library through python software, forming illegal fragments by fragments with the similarity larger than a comparison value, and submitting the illegal fragments to an administrator to confirm whether illegal information exists;
the material processing port is used for carrying out replacement processing on the image after confirming that the image vector in the fragment with the violation information is transformed by the administrator through the image processing formula;
the material classification port is used for comparing the images after framing with the images in the material library materials, and classifying the collected materials into the same type with the materials in the material library with the highest similarity with the materials.
The material analysis port comprises an image extraction module, a first color feature vector extraction module, a violation image similarity calculation module, a data feedback module and a first data transmission module, wherein the image extraction module is used for carrying out framing treatment on materials and extracting images in each frame; the first color feature vector extraction module is used for extracting color feature vectors of each frame of image in the material and the acquired images in the segments related to the illegal contents in the material library through python software; the violation image similarity calculation module calculates the similarity between each frame of image and the collected images related to the violation content fragments in the material library through a violation image similarity calculation formula; the data feedback module is used for submitting the fragments with the similarity alpha of the violation images larger than the comparison value to an administrator, and the administrator confirms whether the violation information exists; the first data transmission module is used for data transmission among the image extraction module, the first color feature vector extraction module, the illegal image similarity calculation module and the data feedback module.
The similarity of the illegal images in the material analysis port is as follows:wherein cosine similaritySo wherein A is i B is the color feature vector of the image in the segment related to the offence content acquired in the material library i For each frame of image, t is a color feature vector i For the duration of the illegal content in the collected materials, N is dividing the image after framing into N equal divisions, setting the contrast value of alpha to be 0.8 and x i Is 0.8.
The material processing port comprises a first data acquisition and storage module, an image processing module and a second data transmission module, wherein the first data acquisition and storage module is used for acquiring and storing the color feature vector B of each frame of image calculated by the material analysis port i And cosine similarity x i The method comprises the steps of carrying out a first treatment on the surface of the The image processing module is used for processing the cosine similarity x in the segments related to the illegal contents in the materials through an image processing formula in python software i Processing the images with the contrast value to obtain color vectors of the processed violation images, and replacing the violation images in the material by pictures formed by the color vectors of the processed violation images; the second data transmission module is used for data transmission between the first data acquisition and storage module and the image processing module.
The image processing formula is B 1 =xb, where B is the n-order color feature vector of the image passing through the violation information present in the material (B 1 ，b 2 ，b 3 ，…，b n ) X is defined n-orderA transformation matrix as a transformation matrix (z 1 ，z 2 ，z 3 ，…，z n )，B 1 Color vectors of images with violation information in the transformed materials; color vector y=db of the processed offence image 1 Wherein D is a python software randomly generated nth order matrix (D 1 ，d 2 ，d 3 ，…，d n ) The color vector Y of the processed offending image is (Y 1 ，y 2 ，y 3 ，…，y n ) And enabling the color vector Y of the processed violation image and the n-order color feature vector B of the image with violation information in the material to meet the replacement condition.
The replacement conditions are:setting the contrast value of phi to be 0.5, and when phi is smaller than 0.5, the replacement condition is satisfied, wherein B is an n-order color feature vector (B) of an image with violation information in the material 1 ，b 2 ，b 3 ，…，b n ) Y is the color vector (Y 1 ，y 2 ，y 3 ，…，y n )。
The material classification port comprises a material acquisition module, a second color feature vector extraction module, a material similarity calculation module, a material classification module and a third data transmission module, wherein the material acquisition module is used for acquiring the image processed by the material processing port; the second color feature vector extraction module is used for extracting color feature vectors of images in the acquired materials; the material similarity calculation module calculates the similarity beta of the collected materials and the materials in the material library through a material similarity calculation formula; the material classification module is used for classifying the collected materials according to the material similarity beta and classifying the collected materials and the materials in the material library with the maximum material similarity beta into the same type of materials; the third data transmission module is used for data transmission among the material acquisition module, the second color feature vector extraction module, the material similarity calculation module and the material classification module.
Element in material classification portThe formula of the similarity of the materials is as follows:wherein->Wherein E is i For the color feature vector of the image in the collected materials in the material library, F i And (3) dividing the image after framing into M equal parts for the color feature vector of the image in the acquired material, wherein T is the duration of the acquired material.
The material storage port comprises a second data acquisition and storage module, a material storage module, a violation fragment storage module and a fourth data transmission module, wherein the second data acquisition and storage module is used for acquiring and storing data of a material processing port and comprises a vector B of an image with violation information in the transformed material 1 The vector Y of the processed violation image, the transformation matrix X and the n-order matrix D randomly generated by python software; the material storage module is used for storing images of the same category in the corresponding category of the material library according to the classification result of the material classification port; the violation segment storage module restores the vector of the processed image with the violation information through inputting an image restoration formula into python software, obtains the violation segment according to the vector of the restored image with the violation information, and stores the violation segment into a violation segment library in the material library; the fourth data transmission module is used for data transmission among the second data acquisition and storage module, the material storage module and the violation fragment storage module.
The image restoration formula is: b (B) 1 ＝YD -1 Wherein D is -1 For the inverse matrix of the n-th order matrix D randomly generated by the python software, Y is the vector of the processed offending image, b=b 1 X -1 Wherein B is 1 For the vector of the image with violation information in the transformed material, X is defined n-order transformation matrix, X -1 An inverse of the n-th order matrix X randomly generated for the python software.
In the present embodiment, cosine similarity x i A value of 0.88, which is greater than the comparative value of 0.8, should be passed through the graphAnd processing the illegal contents by using an image processing formula, and replacing the illegal images in the material by using pictures formed by color vectors of the processed illegal images.
It is evident that the embodiments described are only some, but not all, embodiments of the present invention, and that all other embodiments, both to the person skilled in the art and to the relevant art(s), based on the embodiments of the present invention without creative effort, shall fall within the scope of protection of the present invention, as structures, devices and methods of operation not specifically described and illustrated herein are all carried out according to the conventional means of the art, unless specifically described and defined.
Claims (10)
1. A new media material content acquisition system based on image data processing comprises a material acquisition port, a material analysis port, a material processing port, a material classification port and a material storage port;
the material acquisition port is used for acquiring and storing materials;
the material storage port is used for storing the materials classified by the material classification port and the material fragments with illegal contents;
the method is characterized in that: the material analysis port is used for framing images in the materials, calculating the similarity between the framed images and the acquired images related to the illegal contents in the material library through python software, forming illegal fragments with the similarity larger than a comparison value, submitting the illegal fragments to an administrator, and confirming whether illegal information exists;
the material processing port is used for carrying out replacement processing on the image after confirming that the administrator has the image vector transformation in the fragment of the violation information through the image processing formula;
the material classification port is used for comparing the images after framing with the images in the material library materials, and classifying the collected materials into the same type with the materials in the material library with the highest similarity with the materials.
2. A new media material content acquisition system based on image data processing as claimed in claim 1, wherein: the material analysis port comprises an image extraction module, a first color feature vector extraction module, a violation image similarity calculation module, a data feedback module and a first data transmission module, wherein the image extraction module is used for carrying out framing processing on materials and extracting images in each frame; the first color feature vector extraction module is used for extracting color feature vectors of each frame of image in the material and the acquired images in the fragments related to the illegal contents in the material library through python software; the violation image similarity calculation module calculates the similarity between each frame of image and the acquired images related to the violation content fragments in the material library through a violation image similarity calculation formula; the data feedback module is used for submitting the fragments with the similarity alpha of the violation images larger than the comparison value to an administrator, and the administrator confirms whether violation information exists or not; the first data transmission module is used for data transmission among the image extraction module, the first color feature vector extraction module, the illegal image similarity calculation module and the data feedback module.
3. A new media material content acquisition system based on image data processing as claimed in claim 2, wherein: the similarity of the illegal images in the material analysis port is as follows:wherein cosine similaritySo wherein A is i B is the color feature vector of the image in the segment related to the offence content acquired in the material library i For each frame of image, t is a color feature vector i And N is the time length of the illegal content in the collected materials, and the image after framing is divided into N equal parts.
4. A new media material content acquisition system based on image data processing as claimed in claim 3, wherein: the material processing port comprises a first data acquisition and storage module, an image processing module and a second data transmission module, wherein the first data acquisition and storage module is used for acquiring and storing the color feature vector B of each frame of image calculated by the material analysis port i And cosine similarity x i The method comprises the steps of carrying out a first treatment on the surface of the The image processing module is used for processing cosine similarity x in the segments related to illegal contents in the materials through an image processing formula in python software i Processing the images with the contrast value to obtain color vectors of the processed violation images, and replacing the violation images in the material by pictures formed by the color vectors of the processed violation images; the second data transmission module is used for data transmission between the first data acquisition and storage module and the image processing module.
5. A new media material content acquisition system based on image data processing as claimed in claim 4, wherein: the image processing formula is B 1 =xb, where B is the n-order color feature vector of the image passing through the violation information present in the material (B 1 ，b 2 ，b 3 ，…，b n ) X is a defined n-order transform matrix as a transform matrix (z 1 ，z 2 ，z 3 ，…，z n )，B 1 Color vectors of images with violation information in the transformed materials; color vector y=db of the processed offence image 1 Wherein D is a python software randomly generated nth order matrix (D 1 ，d 2 ，d 3 ，…，d n ) The color vector Y of the processed offending image is (Y 1 ，y 2 ，y 3 ，…，y n ) And enabling the color vector Y of the processed violation image and the n-order color feature vector B of the image with violation information in the material to meet the replacement condition.
6. A new media material content acquisition system based on image data processing as claimed in claim 5, wherein: the replacement conditions are:setting the contrast value of phi to be 0.5, and when phi is smaller than 0.5, the replacement condition is satisfied, wherein B is an n-order color feature vector (B) of an image with violation information in the material 1 ，b 2 ，b 3 ，…，b n ) Y is the color vector (Y 1 ，y 2 ，y 3 ，…，y n )。
7. A new media material content acquisition system based on image data processing as claimed in claim 6, wherein: the material classification port comprises a material acquisition module, a second color feature vector extraction module, a material similarity calculation module, a material classification module and a third data transmission module, wherein the material acquisition module is used for acquiring the image processed by the material processing port; the second color feature vector extraction module is used for extracting color feature vectors of images in the acquired materials; the material similarity calculation module calculates the similarity beta of the collected materials and the materials in the material library through a material similarity calculation formula; the material classification module is used for classifying the collected materials according to the similarity beta of the materials, dividing the collected materials and the materials in the material library with the maximum similarity beta into the same type of materials; the third data transmission module is used for data transmission among the material acquisition module, the second color feature vector extraction module, the material similarity calculation module and the material classification module.
8. A new media material content acquisition system based on image data processing as claimed in claim 7, wherein: the material similarity formula in the material classification port is as follows:wherein->Wherein E is i For the color feature vector of the image in the collected materials in the material library, F i And (3) dividing the image after framing into M equal parts for the color feature vector of the image in the acquired material, wherein T is the duration of the acquired material.
9. A new media material content acquisition system based on image data processing as claimed in claim 8, wherein: the material storage port comprises a second data acquisition and storage module, a material storage module, an offending fragment storage module and a fourth data transmission module, wherein the second data acquisition and storage module is used for acquiring and storing data of a material processing port, and the data comprises a vector B of an image with offending information in the transformed material 1 The vector Y of the processed violation image, the transformation matrix X and the n-order matrix D randomly generated by python software; the material storage module is used for storing images of the same category in the corresponding category of the material library according to the classification result of the material classification port; the violation segment storage module restores the vector of the processed image with the violation information through inputting an image restoration formula into the python software, obtains the violation segment according to the vector of the restored image with the violation information, and stores the violation segment into a violation segment library in the material library; the fourth data transmission module is used for data transmission among the second data acquisition and storage module, the material storage module and the violation fragment storage module.
10. A new media material content acquisition system based on image data processing as claimed in claim 9, wherein: the image restoration formula is as follows: b (B) 1 ＝YD -1 Wherein D is -1 For the inverse matrix of the n-th order matrix D randomly generated by the python software, Y is the vector of the processed offending image, b=b 1 X -1 Wherein B is 1 For the vector of the image with violation information in the transformed material, X is defined n-order transformation matrix, X -1 An inverse of the n-th order matrix X randomly generated for the python software.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310519453.4A CN116452836B (en) | 2023-05-10 | 2023-05-10 | New media material content acquisition system based on image data processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310519453.4A CN116452836B (en) | 2023-05-10 | 2023-05-10 | New media material content acquisition system based on image data processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116452836A true CN116452836A (en) | 2023-07-18 |
| CN116452836B CN116452836B (en) | 2023-11-28 |
Family
ID=87122057
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310519453.4A Active CN116452836B (en) | 2023-05-10 | 2023-05-10 | New media material content acquisition system based on image data processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116452836B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117541269A (en) * | 2023-12-08 | 2024-02-09 | 北京中数睿智科技有限公司 | Third party module data real-time monitoring method and system based on intelligent large model |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130055088A1 (en) * | 2011-08-29 | 2013-02-28 | Ting-Yee Liao | Display device providing feedback based on image classification |
| US10402640B1 (en) * | 2017-10-31 | 2019-09-03 | Intuit Inc. | Method and system for schematizing fields in documents |
| CN112579986A (en) * | 2020-12-25 | 2021-03-30 | 特赞（上海）信息科技有限公司 | Image infringement detection method, device and system |
| WO2021237570A1 (en) * | 2020-05-28 | 2021-12-02 | 深圳市欢太科技有限公司 | Image auditing method and apparatus, device, and storage medium |
| CN113887432A (en) * | 2021-09-30 | 2022-01-04 | 瑞森网安(福建)信息科技有限公司 | Video auditing method and system |
| CN113920495A (en) * | 2021-10-14 | 2022-01-11 | 翟晓磊 | Big data based picture content auditing system |
| CN114241253A (en) * | 2021-11-25 | 2022-03-25 | 网宿科技股份有限公司 | Model training method, system, server and storage medium for illegal content identification |
| CN114238787A (en) * | 2020-08-31 | 2022-03-25 | 腾讯科技（深圳）有限公司 | Answer processing method and device |
| CN114338617A (en) * | 2021-12-23 | 2022-04-12 | 上海欣方智能系统有限公司 | Audio and video auditing method and illegal number identification method based on video call |
| CN115344805A (en) * | 2022-08-17 | 2022-11-15 | 掌阅科技股份有限公司 | Material auditing method, computing equipment and storage medium |
| CN115700809A (en) * | 2021-07-21 | 2023-02-07 | 北京智视数策科技发展有限公司 | Intelligent AI image pornography detection method based on deep learning |
| CN115834935A (en) * | 2022-12-21 | 2023-03-21 | 阿里云计算有限公司 | Multimedia information auditing method, advertisement auditing method, equipment and storage medium |
-
2023
- 2023-05-10 CN CN202310519453.4A patent/CN116452836B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130055088A1 (en) * | 2011-08-29 | 2013-02-28 | Ting-Yee Liao | Display device providing feedback based on image classification |
| US10402640B1 (en) * | 2017-10-31 | 2019-09-03 | Intuit Inc. | Method and system for schematizing fields in documents |
| CN115443490A (en) * | 2020-05-28 | 2022-12-06 | 深圳市欢太科技有限公司 | Image auditing method and device, equipment and storage medium |
| WO2021237570A1 (en) * | 2020-05-28 | 2021-12-02 | 深圳市欢太科技有限公司 | Image auditing method and apparatus, device, and storage medium |
| CN114238787A (en) * | 2020-08-31 | 2022-03-25 | 腾讯科技（深圳）有限公司 | Answer processing method and device |
| CN112579986A (en) * | 2020-12-25 | 2021-03-30 | 特赞（上海）信息科技有限公司 | Image infringement detection method, device and system |
| CN115700809A (en) * | 2021-07-21 | 2023-02-07 | 北京智视数策科技发展有限公司 | Intelligent AI image pornography detection method based on deep learning |
| CN113887432A (en) * | 2021-09-30 | 2022-01-04 | 瑞森网安(福建)信息科技有限公司 | Video auditing method and system |
| CN113920495A (en) * | 2021-10-14 | 2022-01-11 | 翟晓磊 | Big data based picture content auditing system |
| CN114241253A (en) * | 2021-11-25 | 2022-03-25 | 网宿科技股份有限公司 | Model training method, system, server and storage medium for illegal content identification |
| CN114338617A (en) * | 2021-12-23 | 2022-04-12 | 上海欣方智能系统有限公司 | Audio and video auditing method and illegal number identification method based on video call |
| CN115344805A (en) * | 2022-08-17 | 2022-11-15 | 掌阅科技股份有限公司 | Material auditing method, computing equipment and storage medium |
| CN115834935A (en) * | 2022-12-21 | 2023-03-21 | 阿里云计算有限公司 | Multimedia information auditing method, advertisement auditing method, equipment and storage medium |
Non-Patent Citations (5)
| Title |
|---|
| DAN GARBER等: "Faster Eigenvector Computation via Shift-and-Invert Preconditioning", ARXIV * |
| MASSIMO GALLO等: "Performance Evaluation of the Random Replacement Policy for Networks of Caches", ARXIV * |
| 刘鸣;: "多媒体素材库管理系统的研究与实现", 电脑与电信, no. 08 * |
| 张家亮;曾兵;沈宜;李斌;贾宇;: "基于新媒体的视图像内容识别技术研究", 通信技术, no. 11 * |
| 韩子寅;: "影标识别在互联网境外节目监管中的应用", 广播电视信息, no. 06 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117541269A (en) * | 2023-12-08 | 2024-02-09 | 北京中数睿智科技有限公司 | Third party module data real-time monitoring method and system based on intelligent large model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116452836B (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Anwar et al. | Densely residual laplacian super-resolution | |
| Li et al. | An efficient deep convolutional neural networks model for compressed image deblocking | |
| CN116452836B (en) | New media material content acquisition system based on image data processing | |
| Ning et al. | Uncertainty-driven loss for single image super-resolution | |
| US7860308B2 (en) | Approach for near duplicate image detection | |
| CN108961186A (en) | A kind of old film reparation recasting method based on deep learning | |
| CN114640881A (en) | Video frame alignment method and device, terminal equipment and computer readable storage medium | |
| CN112598587A (en) | Image processing system and method combining face mask removal and super-resolution | |
| Li et al. | DLGSANet: lightweight dynamic local and global self-attention networks for image super-resolution | |
| CN109977769B (en) | Method for identifying micro expression in low-resolution environment | |
| Liu et al. | Multi-scale skip-connection network for image super-resolution | |
| CN114187463A (en) | Electronic archive generation method and device, terminal equipment and storage medium | |
| Yang et al. | HQ-50K: A Large-scale, High-quality Dataset for Image Restoration | |
| CN112699270A (en) | Monitoring security data transmission and storage method and system based on cloud computing, electronic equipment and computer storage medium | |
| CN112235598A (en) | Video structured processing method and device and terminal equipment | |
| CN106708876B (en) | Similar video retrieval method and system based on Lucene | |
| US11928855B2 (en) | Method, device, and computer program product for video processing | |
| Zhao et al. | Pyramid Convolutional Network for Single Image Deraining. | |
| CN109657098B (en) | Video fingerprint extraction method and device | |
| Qiao et al. | Conditional generative adversarial network with densely-connected residual learning for single image super-resolution | |
| Wang et al. | Single image deraining using deep convolutional networks | |
| Gao et al. | Gradient guided dual-branch network for image dehazing | |
| CN113836972A (en) | Security audit method, device, equipment and storage medium based on OCR | |
| CN116887010B (en) | Self-media short video material processing control system | |
| CN112837312B (en) | Method and system for improving image quality of polarization infrared thermal imager |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231102 Address after: Room 408, 2nd Floor, Building 2, Wansheng Commercial City, Tangqi Town, Linping District, Hangzhou City, Zhejiang Province, 311119 Applicant after: Hangzhou Yuanmei Technology Co.,Ltd. Address before: 430074 Department of advertising, Central South University for nationalities, No. 182, Minzu Avenue, Hongshan District, Wuhan City, Hubei Province Applicant before: Wuhan Jingyue Digital Media Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |