CN110493640A - A kind of system and method that the Video Quality Metric based on video processing is PPT - Google Patents
A kind of system and method that the Video Quality Metric based on video processing is PPT Download PDFInfo
- Publication number
- CN110493640A CN110493640A CN201910706271.1A CN201910706271A CN110493640A CN 110493640 A CN110493640 A CN 110493640A CN 201910706271 A CN201910706271 A CN 201910706271A CN 110493640 A CN110493640 A CN 110493640A
- Authority
- CN
- China
- Prior art keywords
- processing
- video
- audio
- picture
- server
- 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.)
- Pending
Links
- 238000012545 processing Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000013442 quality metrics Methods 0.000 title claims abstract description 11
- 238000013500 data storage Methods 0.000 claims abstract description 14
- 239000000284 extract Substances 0.000 claims description 7
- 238000011946 reduction process Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000013459 approach Methods 0.000 claims description 2
- 238000003708 edge detection Methods 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005111 flow chemistry technique Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/60—Editing figures and text; Combining figures or text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/4402—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display
- H04N21/440236—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display by media transcoding, e.g. video is transformed into a slideshow of still pictures, audio is converted into text
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/85—Assembly of content; Generation of multimedia applications
- H04N21/854—Content authoring
- H04N21/8547—Content authoring involving timestamps for synchronizing content
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a kind of system and methods that the Video Quality Metric based on video processing is PPT, the system comprises have data storage server, using processing server and WEB server, wherein, the application processing server has pattern process module, audio processing modules and document integrate module, the data storage server isolates voice flow and video flowing, voice flow will be isolated and video flowing is transferred to pattern process module using processing server respectively, audio processing modules, the processing of great amount of images data is carried out in pattern process module, the processing of audio is carried out in audio processing modules, and it is converted into text；Then picture and lteral data are exported integrate module to document respectively by pattern process module, audio processing modules, and document integrates module and matches picture and text, and export a whole set of complete PPT document to WEB server.
Description
Technical field
The present invention relates to information technology fields and field of Educational Technology, particularly relate to a kind of video turn based on video processing
It is changed to the system and method for PPT.
Background technique
With the growth of the value of knowledge of modern society, useful information is likely to just written in water, such as opens in leader
When meeting, class-teaching of teacher, when public speaking, speaker says quickly, causes us the time not remember so multi information, for this
Class problem, currently used method are exactly to save information by hand-written notes, shooting explanation video etc..Both above-mentioned solutions
Method all brings some problems, for hand-written notes: notes it is incomplete, causing cannot be accurately by useful letter
Breath preserves, and looks back scene when having no idea to reappear explanation when notes；And for shooting explanation video: video
It is likely to grow very much, dozens of minutes to several hours etc., this is one and no small chooses when looking back information for us
War, and the voice recorded may be smudgy, and sounding can be gruelling.
Patent application 201710179528.3 discloses a kind of video, handout PPT and voice content precisely matched method
And system, the method shoot with video-corder teachers video by video camera, and the record installed on the computer of PPT is played by class-teaching of teacher
Screen software records computer video and teachers video and computer video is merged processing with course entitled index；According to figure
Video segmentation is several video-frequency bands by picture variation, and the identical video-frequency band of text in video is merged, the time of video segmentation is recorded
Value；It extracts the voice messaging in teachers video and is converted to text, record the time value of every language；With course name and when
Between value for index, establish the data correlation between video, image, voice and content.The present invention is applied in field of Educational Technology, can
When realizing online broadcasting teaching resource, user can position oneself interested PPT handout content or classroom by search service
Voice content, and the instructional video of program request relevant time period can be positioned at any time, play the PPT handout content of related pages.
However, above-mentioned method is only to record to specific PPT, it cannot achieve video and be converted into PPT.To sum up,
Existing solution can all lead to huge waste of the information in transmission process and increase the difficulty of understanding.
Summary of the invention
Shortcoming present in view of the above technology, the present invention provide it is a kind of based on video processing Video Quality Metric be
The system of PPT, the video flowing which has PPT to explain by a shooting, can be believed huge video using this system
A whole set of complete PPT document of boil down to is ceased, user can quickly extract the part of oneself needs from bulk information, and
And the speech of the speaker of remarks can deepen understanding of the user to problem, the efficiency for improving study, looking back.
It is a further object to provide a kind of system that the Video Quality Metric based on video processing is PPT, the systems
It is convenient to realize, it is only necessary to which the equipment that can be shot can be realized, and easy to operate, it is only necessary to video is passed to this system, just
It can be converted into complete PPT document, be suitable for a variety of places.
To achieve the above object, the invention is realized in this way.
A kind of system that the Video Quality Metric based on video processing is PPT, it is characterised in that the system comprises have data to deposit
Store up server, using processing server and WEB server, wherein the application processing server has pattern process module, sound
Frequency processing module and document integrate module, and the data storage server isolates voice flow and video flowing, will isolate voice
Stream is transferred to the pattern process module using processing server, audio processing modules with video flowing respectively, in pattern process module
The processing of great amount of images data is carried out, carries out the processing of audio in audio processing modules, and be converted into text；Then graphics process
Picture and lteral data are exported integrate module to document respectively by module, audio processing modules, document integrate module by picture and
Text is matched, and exports a whole set of complete PPT document to WEB server.
A method of the Video Quality Metric based on video processing is PPT, and this method is isolated by data storage server
Voice flow and video flowing, then will isolate voice flow and video flowing is transferred to graphics process mould using processing server respectively
Block, audio processing modules carry out the processing of image data in pattern process module, convert picture, audio processing mould for video
The processing of audio is carried out in block, and is converted into text；Then pattern process module, audio processing modules are respectively by picture and text
Data, which are exported, integrates module to document, and document integrates module and matches picture and text, and it is complete to export a whole set of
PPT document is to WEB server.+
Further, the method receives the request for the uploaded videos that client is sent, video first with data storage server
Stream is passed to data storage server first and carries out data backup, and data processing is carried out in data storage server, is isolated
Voice flow and video flowing, and be N frame picture by Video segmentation (N is the positive integer more than or equal to 1)；Again by image data and voice
Data are incoming to apply processing server, carries out image procossing and speech processes in application processing server.
Further, in application processing server: giving a kind of processing great amount of images number in pattern process module
According to method, this method may have inclination along x, tri- axis of y, z in view of PPT view field, need to become by perspective
Changing commanders, it is inverted to parallel position.Specifically: grayscale image is converted by each frame image first and is filtered noise reduction process, then
Switch to two-value picture, PPT view field is rectangular area, and is highlight regions compared to ambient enviroment, is then calculated using Canny
Method carries out edge detection and extracts profile, objective contour is chosen by the method for extracting the maximum profile of area, then with more
The method of side shape fitting surrounds profile, then obtain rectangular corners coordinate by finding the convex closure of profile, then to obtaining four
The coordinate of a point is ranked up, and separates upper left, upper right, bottom right, lower-left, is coordinately transformed to obtain most finally by transformation matrix
The image wanted eventually, that is, the position projected, and be cut into, then as the defeated of image processing model
Enter.
Further, in image processing model, Gauss gold word (is first used using gaussian filtering+down-sampled operation
Tower), then detect characteristic point and extract feature vector, for two pictures, if feature vector is more similar, just represent this two
Picture is more similar, and more similar picture temporarily only retains one, remaining similar pictures is stored in set, after reduction
The operand in face is finally before recognition restored picture by up-sampling operation (using laplacian pyramid)；
Then the text in remaining each frame picture is identified with the convolutional neural networks model that training is completed with image, and remembered
The coordinate for recording word and image in picture, is finally reconfigured each element by coordinate on the new PPT of one page.
Further, the step of a kind of processing audio is given in audio processing modules, it may be assumed that progress VAD detection first,
Voice and environmental noise are classified using GM model, audio is subjected to noise reduction process, then by based on artificial neural network
Hybrid algorithm identifies audio, and is converted into text.
Further, it is integrated in document and provides the algorithm of a kind of voice and video matching in module, it is specific as follows: in figure
In image collection obtained in processing module, this is found out by calculating the time interval of each image collection, then from audio
The text that time interval is converted to thus may be implemented accurately to match the voice of speaker into the remarks section at PPT pages, and
And a whole set of complete PPT document is exported to WEB server.
Further, in pattern process module, for the picture addition time label being converted into, meanwhile, for sound
Frequency does the text being converted into and also carries out time label, in order to be matched with the text that audio is converted into.
The method for the video flow processing that the present invention is realized: it in terms of image, can effectively be captured by target positioning
Projection information on classroom or meeting, it is bright occurring in video using continuous frame difference method under the premise of carrying out video denoising
The frame image of aobvious frame variation obtains, avoids the motion image blurring generated between frame in video, loss of detail and again
Shadow problem, while improving the image quality of video；Substantially increase the transformation efficiency and clarity of video.
Compared with prior art, the beneficial effects of the present invention are:
The mode in meeting, classroom recorded information on the market is to carry out hand-written notes or directly regard under record mostly now
Frequently, and these modes can not only have inconvenience, also result in the loss of precious information, the present invention, which proposes one to this, to be had
The solution of effect, the present invention only need user that the video that shooting has PPT to explain is passed to this system, and system will utilize each skill
PPT in video is extracted and is attached to text made of the speech conversion of speaker by the processing of art module.
In structure, product on the market is inputted by mobile phone terminal mostly, and the present invention supports multi-platform input,
It is also more diversified in core technology as long as the platform that can connect internet is ok, it has been divided at different logics
Server is managed, the processing of multimode is realized, avoids mixing in logic.
Detailed description of the invention
Fig. 1 is the structural schematic diagram for the system that the present invention is realized.
Specific embodiment
In order to more clearly state the present invention, the present invention is further described with reference to the accompanying drawing.
Refering to Figure 1, as shown in the figure, present invention institute is real shown in the system structure diagram realized for the present invention
The system that the existing Video Quality Metric based on video processing is PPT, include data storage server, using processing server and
WEB server, wherein there is the application processing server pattern process module, audio processing modules and document to integrate module,
The data storage server isolates voice flow and video flowing, will isolate voice flow and video flowing is transferred to respectively at
Pattern process module, the audio processing modules of server are managed, the processing of great amount of images data, audio are carried out in pattern process module
The processing of audio is carried out in processing module, and is converted into text；Then pattern process module, audio processing modules are respectively by picture
It is exported with lteral data and integrates module to document, document integrates module and matches picture and text, and exports a whole set of
Complete PPT document is to WEB server.
The method that the Video Quality Metric that the present invention is realized as a result, is PPT are as follows:
S1 server receives the request for the uploaded videos that client is sent, and video flowing is passed to S1 first and carries out data backup, In
Data processing is carried out in S1, isolates voice flow and video flowing, and is that (N is just more than or equal to 1 to N frame picture by Video segmentation
Integer)；Image data and voice data are passed to S2 application processing server again, carried out at image procossing and voice in S2
Reason.
Treatment process in S2 is specific as follows: a kind of processing great amount of images data are given in pattern process module S2.1
Method, it is contemplated that PPT view field may have inclination along x, tri- axis of y, z, need by perspective transform that it is anti-
Go to parallel position.Grayscale image is converted by each frame image first and is filtered noise reduction process, then turns to two-value picture,
PPT view field is rectangular area, and is highlight regions compared to ambient enviroment, so carrying out edge inspection using Canny algorithm
Profile is surveyed and extracted, objective contour is chosen by the method for extracting the maximum profile of area, then uses the side of polygon approach
Method surrounds profile, obtains rectangular corners coordinate followed by the convex closure for finding profile, first to obtain the coordinates of four points into
Row sequence, separates upper left, upper right, bottom right, lower-left, is coordinately transformed finally by transformation matrix and finally to be wanted
Image, that is, the position projected, and be cut into, then as the input of image processing model.
In image processing model, first using gaussian filtering+down-sampled operation (using gaussian pyramid), then spy is detected
Sign point simultaneously extracts feature vector, for two pictures, if feature vector is more similar, just represents this two picture and gets over phase
Seemingly, more similar picture temporarily only retains one, remaining similar pictures is stored in set, subsequent operation is reduced
Amount is finally before recognition restored picture by up-sampling operation (using laplacian pyramid).Then with instruction
Practice the convolutional neural networks model of completion to identify to the text in remaining each frame picture with image, and in recordable picture
The coordinate of word and image is finally reconfigured each element by coordinate on the new PPT of one page；In audio processing modules
A kind of the step of processing audio is given in S2.2, first progress VAD detection, uses GM model by voice and environment herein
Audio is carried out noise reduction process, then is identified by the hybrid algorithm based on artificial neural network to audio by noise classification, and
It is converted into text, the algorithm for providing a kind of voice and video matching in module S2.3 is integrated in document, it is specific as follows: in S2.1
In obtained image collection, by calculating the time interval of each image collection, then this time section is found out from audio and is turned
The text dissolved thus may be implemented accurately to match the voice of speaker into the remarks section at PPT pages, and it is whole to export one
Complete PPT document is covered to WEB server S3.
In short, the invention has the advantages that
Give it is a kind of take notes in modern society, review the solution looked back and had any problem, have PPT explanation by a shooting
Video flowing, use this system can be by huge video information compression for a whole set of complete PPT document, user can be with
The part of oneself needs is quickly extracted from bulk information, and the speech of the speaker of remarks can deepen user to asking
The understanding of topic, the efficiency for improving study, looking back.
Operation of the present invention is simple, it is only necessary to which video, which is passed to this system, can be converted into complete PPT document.
Strong applicability of the present invention is suitable for a variety of places, limits without occasion, and only need the equipment that can be shot
It is ok.
The present invention can tentatively solve the problems, such as identification one page PPT template.
Disclosed above is only several specific embodiments of the invention, but the present invention is not limited to this, any ability
What the technical staff in domain can think variation should all fall into protection scope of the present invention.
Claims (8)
1. a kind of system that the Video Quality Metric based on video processing is PPT, it is characterised in that the system comprises have data storage
Server, using processing server and WEB server, wherein the application processing server have pattern process module, audio
Processing module and document integrate module, and the data storage server isolates voice flow and video flowing, will isolate voice flow
Be transferred to the pattern process module using processing server, audio processing modules respectively with video flowing, in pattern process module into
The processing of row great amount of images data, the processing of audio is carried out in audio processing modules, and is converted into text；Then graphics process mould
Picture and lteral data are exported integrate module to document respectively by block, audio processing modules, and document integrates module for picture and text
Word is matched, and exports a whole set of complete PPT document to WEB server.
2. a kind of method that the Video Quality Metric based on video processing is PPT, this method isolate language by data storage server
Sound stream and video flowing, then will isolate voice flow and video flowing is transferred to graphics process mould using processing server respectively
Block, audio processing modules carry out the processing of image data in pattern process module, convert picture, audio processing mould for video
The processing of audio is carried out in block, and is converted into text；Then pattern process module, audio processing modules are respectively by picture and text
Data, which are exported, integrates module to document, and document integrates module and matches picture and text, and it is complete to export a whole set of
PPT document is to WEB server.
3. method according to claim 2, it is characterised in that the method receives client first with data storage server
The request of the uploaded videos sent is held, video flowing is passed to data storage server first and carries out data backup, stores in data
Data processing is carried out in server, isolates voice flow and video flowing, and is N frame picture by Video segmentation, and N is more than or equal to 1
Positive integer；It is again that image data and voice data is incoming using processing server, image is carried out in application processing server
Processing and speech processes.
4. method as claimed in claim 3, it is characterised in that in application processing server: first converting each frame image
It is filtered noise reduction process for grayscale image, then turns to two-value picture, PPT view field is rectangular area, and compared to surrounding
Environment is highlight regions, then carries out edge detection using Canny algorithm and extracts profile, by extracting the maximum wheel of area
Wide method chooses objective contour, is then surrounded profile with the method for polygon approach, then the convex closure by finding profile
Rectangular corners coordinate is obtained, then the coordinate for obtaining four points is ranked up, separates upper left, upper right, bottom right, lower-left, finally
It is coordinately transformed the image finally wanted by transformation matrix, that is, the position projected, and is cut into
Come, then as the input of image processing model.
5. method as claimed in claim 4, it is characterised in that in image processing model, first using gaussian filtering+down-sampled
Operation, then detect characteristic point and extract feature vector, for two pictures, if feature vector is more similar, just represent this
Two pictures are more similar, and more similar picture temporarily only retains one, remaining similar pictures is stored in set, reduce
Subsequent operand is finally before recognition restored picture by using laplacian pyramid；Then it uses and has trained
At convolutional neural networks model the text in remaining each frame picture identified with image, and in recordable picture word and
The coordinate of image is finally reconfigured each element by coordinate on the new PPT of one page.
6. method according to claim 2, it is characterised in that in audio processing modules: progress VAD detection first, using GM
Model classifies voice and environmental noise, audio is carried out noise reduction process, then calculate by the mixing based on artificial neural network
Method identifies audio, and is converted into text.
7. method according to claim 2, it is characterised in that integrated in module in document: obtained in pattern process module
In image collection, find out what this time section was converted to by calculating the time interval of each image collection, then from audio
Text thus may be implemented accurately to match the voice of speaker into the remarks section at PPT pages, and it is complete to export a whole set of
PPT document to WEB server.
8. method according to claim 2, it is characterised in that in pattern process module, added for the picture being converted into
Time label, meanwhile, the text being converted into is done for audio and also carries out time label, in order to the text that is converted into audio into
Row matching.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910706271.1A CN110493640A (en) | 2019-08-01 | 2019-08-01 | A kind of system and method that the Video Quality Metric based on video processing is PPT |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910706271.1A CN110493640A (en) | 2019-08-01 | 2019-08-01 | A kind of system and method that the Video Quality Metric based on video processing is PPT |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110493640A true CN110493640A (en) | 2019-11-22 |
Family
ID=68549096
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910706271.1A Pending CN110493640A (en) | 2019-08-01 | 2019-08-01 | A kind of system and method that the Video Quality Metric based on video processing is PPT |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110493640A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111741359A (en) * | 2020-05-28 | 2020-10-02 | 杨伟 | Method and system for converting video into PPTX |
| CN112203036A (en) * | 2020-09-14 | 2021-01-08 | 北京神州泰岳智能数据技术有限公司 | Method and device for generating text document based on video content |
| WO2021114824A1 (en) * | 2020-06-28 | 2021-06-17 | 平安科技（深圳）有限公司 | Presentation generation method, apparatus, and device, and medium |
| CN113779345A (en) * | 2021-09-06 | 2021-12-10 | 北京量子之歌科技有限公司 | Teaching material generation method and device, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030088546A (en) * | 2002-05-11 | 2003-11-20 | 김대성 | Multi-media system of making VOD (Video On Demand) using Word-processor(Powerpoint and etc.) with Voice and Music, which can be shown through internet |
| CN102799859A (en) * | 2012-06-20 | 2012-11-28 | 北京交通大学 | Method for identifying traffic sign |
| CN109309790A (en) * | 2018-11-02 | 2019-02-05 | 长春市长光芯忆科技有限公司 | A kind of meeting lantern slide intelligent recording method and system |
| CN109492206A (en) * | 2018-10-10 | 2019-03-19 | 深圳市容会科技有限公司 | PPT presentation file method for recording, device, computer equipment and storage medium |
-
2019
- 2019-08-01 CN CN201910706271.1A patent/CN110493640A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030088546A (en) * | 2002-05-11 | 2003-11-20 | 김대성 | Multi-media system of making VOD (Video On Demand) using Word-processor(Powerpoint and etc.) with Voice and Music, which can be shown through internet |
| CN102799859A (en) * | 2012-06-20 | 2012-11-28 | 北京交通大学 | Method for identifying traffic sign |
| CN109492206A (en) * | 2018-10-10 | 2019-03-19 | 深圳市容会科技有限公司 | PPT presentation file method for recording, device, computer equipment and storage medium |
| CN109309790A (en) * | 2018-11-02 | 2019-02-05 | 长春市长光芯忆科技有限公司 | A kind of meeting lantern slide intelligent recording method and system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111741359A (en) * | 2020-05-28 | 2020-10-02 | 杨伟 | Method and system for converting video into PPTX |
| WO2021114824A1 (en) * | 2020-06-28 | 2021-06-17 | 平安科技（深圳）有限公司 | Presentation generation method, apparatus, and device, and medium |
| CN112203036A (en) * | 2020-09-14 | 2021-01-08 | 北京神州泰岳智能数据技术有限公司 | Method and device for generating text document based on video content |
| CN112203036B (en) * | 2020-09-14 | 2023-05-26 | 北京神州泰岳智能数据技术有限公司 | Method and device for generating text document based on video content |
| CN113779345A (en) * | 2021-09-06 | 2021-12-10 | 北京量子之歌科技有限公司 | Teaching material generation method and device, computer equipment and storage medium |
| CN113779345B (en) * | 2021-09-06 | 2024-04-16 | 北京量子之歌科技有限公司 | Teaching material generation method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110493640A (en) | A kind of system and method that the Video Quality Metric based on video processing is PPT | |
| CN101271525B (en) | Fast image sequence characteristic remarkable picture capturing method | |
| CN112465008B (en) | Voice and visual relevance enhancement method based on self-supervision course learning | |
| CN111539370A (en) | Image pedestrian re-identification method and system based on multi-attention joint learning | |
| CN109117777A (en) | The method and apparatus for generating information | |
| EP2246807A1 (en) | Information processing apparatus and method, and program | |
| CN112261477B (en) | Video processing method and device, training method and storage medium | |
| CN112183468A (en) | Pedestrian re-identification method based on multi-attention combined multi-level features | |
| CN111160533A (en) | Neural network acceleration method based on cross-resolution knowledge distillation | |
| CN109165573A (en) | Method and apparatus for extracting video feature vector | |
| CN108922559A (en) | Recording terminal clustering method based on voice time-frequency conversion feature and integral linear programming | |
| CN108921038A (en) | A kind of classroom based on deep learning face recognition technology is quickly called the roll method of registering | |
| CN109977832A (en) | A kind of image processing method, device and storage medium | |
| CN115564993A (en) | Lip print image classification algorithm based on multi-scale feature fusion and attention mechanism | |
| CN111950487A (en) | Intelligent teaching analysis management system | |
| CN108363771B (en) | Image retrieval method for public security investigation application | |
| CN114519880A (en) | Active speaker identification method based on cross-modal self-supervision learning | |
| CN116229319A (en) | Multi-scale feature fusion class behavior detection method and system | |
| CN112183450A (en) | Multi-target tracking method | |
| Cheng et al. | The dku audio-visual wake word spotting system for the 2021 misp challenge | |
| WO2022205329A1 (en) | Object detection method, object detection apparatus, and object detection system | |
| Huang et al. | DS-UNet: A dual streams UNet for refined image forgery localization | |
| CN114266952A (en) | Real-time semantic segmentation method based on deep supervision | |
| CN109522865A (en) | A kind of characteristic weighing fusion face identification method based on deep neural network | |
| CN110689066B (en) | Training method combining face recognition data equalization and enhancement |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Ao Xin Inventor after: Zhu Hongtou Inventor after: Wu Yongman Inventor after: Huang Xinjie Inventor after: Chen Dian Inventor after: Ye Yongfu Inventor before: Ao Xin Inventor before: Zhu Hongtou Inventor before: Wu Yongman Inventor before: Huang Xinjie Inventor before: Chen Dian |
|
| CB03 | Change of inventor or designer information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191122 |
|
| RJ01 | Rejection of invention patent application after publication |