CN110147462A - The verification method and Related product of the short-sighted frequency of religion - Google Patents
The verification method and Related product of the short-sighted frequency of religion Download PDFInfo
- Publication number
- CN110147462A CN110147462A CN201910420066.9A CN201910420066A CN110147462A CN 110147462 A CN110147462 A CN 110147462A CN 201910420066 A CN201910420066 A CN 201910420066A CN 110147462 A CN110147462 A CN 110147462A
- Authority
- CN
- China
- Prior art keywords
- picture
- short
- value
- sighted frequency
- 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.)
- Withdrawn
Links
Classifications
-
- 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
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/74—Browsing; Visualisation therefor
-
- 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
-
- 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
- G06V20/44—Event detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The disclosure provides the verification method and Related product of a kind of short-sighted frequency of religion, and described method includes following steps: the first short-sighted frequency that server receiving terminal is sent；Server extracts the n frame picture of the first short-sighted frequency, and the n picture of setting position fixed size is extracted from n frame picture；Server compares the similarity for determining any 2 picture to n picture, and if similarity is more than or equal to first threshold, any one picture in 2 pictures is put into picture library to be detected, and if similarity is less than first threshold, 2 pictures are directly put into picture library to be detected；Picture to be detected is input to convolutional neural networks model and determines whether the first short-sighted frequency is religion video by server, is such as determined as religion video, by the first short video masking.Technical solution provided by the present application has the advantages that meet policy requirements.
Description
Technical field
The present invention relates to cultural medium technical fields, and in particular to a kind of verification method of the short-sighted frequency of religion and related produces
Product.
Background technique
Short-sighted frequency, that is, short-movie video is a kind of internet content circulation way, usually propagates on internet new media
Video transmission content of the duration within 1 minute.
The sharing of existing short-sighted frequency is based on network share, but existing short-sighted frequency may relate to the short-sighted frequency of religion,
The especially video of heresy, not only the common people dislike this video, what policy did not allowed, therefore its requirement for not meeting policy.
Summary of the invention
The embodiment of the invention provides the verification method and Related product of a kind of short-sighted frequency of religion, can to religion video into
Row is voluntarily verified and is shielded, and has the advantages that meet policy.
In a first aspect, the embodiment of the present invention provides a kind of verification method of short-sighted frequency of religion, the method includes walking as follows
It is rapid:
The first short-sighted frequency that server receiving terminal is sent；
Server extracts the n frame picture of the first short-sighted frequency, and n area of setting position fixed size is extracted from n frame picture
The n picture in domain；
Server compares the similarity for determining any 2 picture to n picture, if similarity is less than first threshold, by 2
Any one picture in picture is put into picture library to be detected, if similarity is more than or equal to first threshold, is directly put into 2 pictures
Picture library to be detected；
Picture to be detected is input to convolutional neural networks model and determines whether the first short-sighted frequency is religion view by server
Frequently, such as it is determined as religion video, by the first short video masking.
Optionally, the server, which compares n picture, determines that the similarity of any 2 picture specifically includes:
It extracts 2 pictures, i.e. the first picture and second picture in order from n picture, executes similarity calculation step,
It specifically includes: obtaining the H value and S value of each pixel of the first picture and second picture, the H value of the first picture is pressed into pixel
The position of point forms H1 matrix, and the S value of the first picture is formed S1 matrix by the position of pixel, the H value of second picture is pressed
The position of pixel forms H2 matrix, and the S value of second picture is formed S2 matrix by the position of pixel, calculates D1=H1-H2；
D2=S1-S2 calculates the element average value of D1And the element average value of D2
Optionally, the method also includes:
The upload user of first short-sighted frequency is marked, and to the history video masking for uploading Termination ID.
Optionally, the method also includes:
The address of the first short-sighted frequency and terminal is sent to public security organ's server.
Second aspect, provides a kind of server, and the server includes: communication module, processor,
Communication module, for receiving the first short-sighted frequency of terminal transmission；
Processor extracts the n of setting position fixed size for extracting the n frame picture of the first short-sighted frequency from n frame picture
The n picture in a region compares the similarity for determining any 2 picture to n picture, if similarity is less than first threshold, by 2
Any one picture in picture is put into picture library to be detected, if similarity is more than or equal to first threshold, directly puts 2 pictures
Enter picture library to be detected；Picture to be detected is input to convolutional neural networks model and determines whether the first short-sighted frequency is religion view
Frequently, such as it is determined as religion video, by the first short video masking.
Optionally, the processor, for extracting 2 pictures, i.e. the first picture and the second figure in order from n picture
Piece executes similarity calculation step, specifically includes: obtaining the H value and S of each pixel of the first picture and second picture
Value, forms H1 matrix by the position of pixel for the H value of the first picture, and the S value of the first picture is formed by the position of pixel
The H value of second picture is formed H2 matrix by the position of pixel, the S value of second picture is pressed to the position of pixel by S1 matrix
S2 matrix is formed, D1=H1-H2 is calculated；D2=S1-S2 calculates the element average value of D1And the element average value of D2
Optionally, the processor is also used to for the upload user of the first short-sighted frequency being marked, and to upload Termination ID
History video masking.
Optionally, the processor is also used to control communication unit and sends the address of the first short-sighted frequency and terminal
Give public security organ's server.
Optionally, the terminal are as follows: computer or cloud platform.
The third aspect provides a kind of computer readable storage medium, and storage is used for the program of electronic data interchange,
In, described program makes terminal execute the method that first aspect provides.
The implementation of the embodiments of the present invention has the following beneficial effects:
As can be seen that technical solution provided by the present application after receiving the first video, is obtained from the first short-sighted frequency
Then all n pictures determine whether n picture has the first common icon, such as have, after extracting first icon,
Determine whether the first icon is included in preset icon (i.e. heresy icon database), if so, being determined as religion video, shielding should
Video meets the requirement of policy.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of structural schematic diagram of terminal.
Fig. 2 is a kind of flow diagram of the verification method of short-sighted frequency of religion.
Fig. 3 is the structural schematic diagram of server provided in an embodiment of the present invention.
Fig. 4 is pixel matrix schematic diagram provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Description and claims of this specification and term " first ", " second ", " third " and " in the attached drawing
Four " etc. are not use to describe a particular order for distinguishing different objects.In addition, term " includes " and " having " and it
Any deformation, it is intended that cover and non-exclusive include.Such as it contains the process, method of a series of steps or units, be
System, product or equipment are not limited to listed step or unit, but optionally further comprising the step of not listing or list
Member, or optionally further comprising other step or units intrinsic for these process, methods, product or equipment.
Referenced herein " embodiment " is it is meant that the special characteristic, result or the characteristic that describe can wrap in conjunction with the embodiments
Containing at least one embodiment of the present invention.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
Refering to fig. 1, Fig. 1 provides a kind of terminal, which is specifically as follows smart phone, tablet computer, computer, clothes
Be engaged in device, which can specifically include for the terminal of the systems such as IOS, Android, above-mentioned terminal: processor, memory,
Camera and display screen, above-mentioned component can be connected by bus, can also be connected by other means, the application and limit of getting along well
Make the concrete mode of above-mentioned connection.
For server, it is specifically as follows computer or cloud platform.Its service side apparatus for belonging to short Video Applications.
Referring to Fig.2, Fig. 2 provides a kind of verification method of short-sighted frequency of religion, this method as shown in Fig. 2, by server Lai
It executes, this method comprises the following steps:
Step S201, the first short-sighted frequency that server receiving terminal is sent；
Step S202, server extracts the n frame picture of the first short-sighted frequency, and it is fixed big that setting position is extracted from n frame picture
Small n picture；
Above-mentioned setting position fixed size is specifically promising, in the upper left corner of n frame picture, the lower left corner, the upper right corner or the lower right corner
Any one, the fixed size can for extract n picture size it is identical, or the quantity of pixel is identical.
Just make it possible subsequent similarity calculation in this way.
Step S203, server compares the similarity for determining any 2 picture to n picture, if similarity is less than first
Any one picture in 2 pictures is put into picture library to be detected by threshold value, if similarity is more than or equal to first threshold, directly by 2
Picture is put into picture library to be detected.
Above-mentioned n is the integer more than or equal to 10, because only that the verifying of a certain number of pictures just has certain meaning.
Step S204, picture to be detected is input to whether convolutional neural networks model determines the first short-sighted frequency by server
For religion video, such as it is determined as religion video, by the first short video masking.
Above-mentioned convolutional neural networks model can use existing convolutional neural networks model, such as the convolutional Neural of Ali
Network model (specifically may refer to CN108509827A), naturally it is also possible to using Baidu's convolutional neural networks model etc..This
Application has no change to convolutional neural networks model.
Technical solution provided by the present application obtains all n after receiving the first video from the first short-sighted frequency
Then picture determines the similarity of any 2 picture in n picture, if similarity is more than or equal to given threshold, determine 2 figures
Piece is closely similar, determines whether religion video then retaining any one picture and being input to convolutional neural networks operation, if so, screen
The video is covered, the requirement of policy is met, in addition, the picture of input can be carried out the operation of similarity by the application before the input,
Under the premise of not influencing recognition accuracy, reduce calculation amount.
Optionally, above-mentioned server, which compares n picture, determines that the similarity of any 2 picture specifically includes:
Server extracts 2 pictures, i.e. the first picture and second picture in order from n picture, executes similarity meter
Step is calculated, is specifically included: the H value and S value of each pixel of the first picture and second picture are obtained, by the H of the first picture
Value forms H1 matrix by the position of pixel, the S value of the first picture is formed S1 matrix by the position of pixel, by second picture
H value by pixel position form H2 matrix, by the S value of second picture by pixel position form S2 matrix, calculate D1
=H1-H2；D2=S1-S2 calculates the element average value of D1And the element average value of D2
Above-mentioned H value and S value can be tone (H) value and saturation degree (S) value in HSI model.Need exist for explanation
It is not to be here using brightness (I) value because brightness is uncorrelated to color, it is whether consistent for picture, it is mainly reflected in color
Consistency, for 2 H value matrixs of 2 pictures of same size (such as pixel quantity is identical) matrix of differences D1 with
And the matrix of differences D2 of 2 S value matrixs differs very little, then illustrating that two pictures are substantially similar.
Below with Fig. 4 come illustrate (for convenience of explanation, by taking 12 pixels as an example, in practical applications, may have on
Thousand pixels),
The H value of above-mentioned first picture is specifically as follows by the position composition H1 matrix of pixel, obtains the H of each pixel
Value determines the H value in the position of H1 matrix, such as the H for the pixel that Fig. 4 is the first picture in the position of the first picture by pixel
Value is converted into the schematic diagram of H1 matrix, and wherein each square before the conversion of the left side Fig. 4 represents the H value an of pixel.
Conversion not only also has strict requirements to the position of pixel in this way, can further increase picture similarity in this way
Reliability.
Its thinking is, for cult, generally has fixed mark, and identifies and be generally located on similar to trade mark
Four corners of its video, and this four corners will not generally change with the scene changes of video, therefore the applicant's needle
Cult is determined whether it is to such characteristic, but if each picture carries out convolutional neural networks operation, fortune
Calculation amount can be bigger, and the operand of a convolutional neural networks operation is generally 106Secondary product calculation, and the square that the application proposes
The operand of battle array subtraction will be far smaller than this computing cost, therefore the purpose of the application is to reduce picture and input
Quantity, in order to reduce the quantity of picture input, by the higher picture of similarity retain a picture can, in this way can be right
Picture is identified, calculation amount can be also reduced.
Optionally, the above method can also include:
The upload user of first short-sighted frequency is marked, and to the history video masking for uploading Termination ID.
Optionally, the above method can also include:
The address of the first short-sighted frequency and terminal is sent to public security organ's server.It is convenient for public security organ to grab in this way
It catches.
A kind of server is provided refering to Fig. 3, Fig. 3, the server includes: communication module, processor,
Communication module, for receiving the first short-sighted frequency of terminal transmission；
Processor extracts the n of setting position fixed size for extracting the n frame picture of the first short-sighted frequency from n frame picture
Picture compares the similarity for determining any 2 picture to n picture, and if similarity is more than or equal to first threshold, 2 are schemed
Any one picture in piece is put into picture library to be detected, if similarity is less than first threshold, is directly put into 2 pictures to be detected
Picture library；Picture to be detected is input to convolutional neural networks model and determines whether the first short-sighted frequency is religion video, is such as determined
For religion video, by the first short video masking.
The embodiment of the present invention also provides a kind of computer storage medium, wherein computer storage medium storage is for electricity
The computer program of subdata exchange, it is as any in recorded in above method embodiment which execute computer
A kind of some or all of the verification method of the short-sighted frequency of religion step.
The embodiment of the present invention also provides a kind of computer program product, and the computer program product includes storing calculating
The non-transient computer readable storage medium of machine program, the computer program are operable to that computer is made to execute such as above-mentioned side
Some or all of the verification method for the short-sighted frequency of any religion recorded in method embodiment step.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the present invention is not limited by the sequence of acts described because
According to the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know
It knows, embodiment described in this description belongs to alternative embodiment, and related actions and modules is not necessarily of the invention
It is necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed device, it can be by another way
It realizes.For example, the apparatus embodiments described above are merely exemplary, such as the division of the unit, it is only a kind of
Logical function partition, there may be another division manner in actual implementation, such as multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be through some interfaces, the indirect coupling or communication connection of device or unit,
It can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also be realized in the form of software program module.
If the integrated unit is realized in the form of software program module and sells or use as independent product
When, it can store in a computer-readable access to memory.Based on this understanding, technical solution of the present invention substantially or
Person says that all or part of the part that contributes to existing technology or the technical solution can body in the form of software products
Reveal and, which is stored in a memory, including some instructions are used so that a computer equipment
(can be personal computer, server or network equipment etc.) executes all or part of each embodiment the method for the present invention
Step.And memory above-mentioned includes: USB flash disk, read-only memory (ROM, Read-Only Memory), random access memory
The various media that can store program code such as (RAM, Random Access Memory), mobile hard disk, magnetic or disk.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can store in a computer-readable memory, memory
May include: flash disk, read-only memory (English: Read-Only Memory, referred to as: ROM), random access device (English:
Random Access Memory, referred to as: RAM), disk or CD etc..
The embodiment of the present invention has been described in detail above, specific case used herein to the principle of the present invention and
Embodiment is expounded, and the above description of the embodiment is only used to help understand the method for the present invention and its core ideas；
At the same time, for those skilled in the art can in specific embodiments and applications according to the thought of the present invention
There is change place, in conclusion the contents of this specification are not to be construed as limiting the invention.
Claims (10)
1. a kind of verification method of the short-sighted frequency of religion, which is characterized in that described method includes following steps:
The first short-sighted frequency that server receiving terminal is sent；
Server extracts the n frame picture of the first short-sighted frequency, and the n picture of setting position fixed size is extracted from n frame picture；
Server compares the similarity for determining any 2 picture to n picture, if similarity is more than or equal to first threshold, by 2
Any one picture in picture is put into picture library to be detected, if similarity is less than first threshold, is directly put into 2 pictures to be checked
Mapping library；
Picture to be detected is input to convolutional neural networks model and determines whether the first short-sighted frequency is religion video by server, such as
It is determined as religion video, by the first short video masking；
The n is the integer more than or equal to 10.
2. the method according to claim 1, wherein the server, which compares n picture, determines any 2 figures
The similarity of piece specifically includes:
It extracts 2 pictures, i.e. the first picture and second picture in order from n picture, executes similarity calculation step, specifically
It include: the H value and S value for obtaining each pixel of the first picture and second picture, by the H value of the first picture by pixel
Position forms H1 matrix, and the S value of the first picture is formed S1 matrix by the position of pixel, the H value of second picture is pressed pixel
The position of point forms H2 matrix, and the S value of second picture is formed S2 matrix by the position of pixel, calculates D1=H1-H2；D2=
S1-S2 calculates the element average value of D1And the element average value of D2
3. the method according to claim 1, wherein the method also includes:
The upload user of first short-sighted frequency is marked, and to the history video masking for uploading Termination ID.
4. the method according to claim 1, wherein the method also includes:
The address of the first short-sighted frequency and terminal is sent to public security organ's server.
5. a kind of server, the server includes: communication module, processor, which is characterized in that
Communication module, for receiving the first short-sighted frequency of terminal transmission；
Processor extracts n figures of setting position fixed size for extracting the n frame picture of the first short-sighted frequency from n frame picture
Piece compares the similarity for determining any 2 picture to n picture, will be in 2 pictures if similarity is more than or equal to first threshold
Any one picture be put into picture library to be detected, if similarity be less than first threshold, 2 pictures are directly put into mapping to be checked
Library；Picture to be detected is input to convolutional neural networks model and determines whether the first short-sighted frequency is religion video, is such as determined as
Religion video, by the first short video masking.
6. terminal according to claim 5, which is characterized in that
The processor executes similar for extracting 2 pictures, i.e. the first picture and second picture in order from n picture
Degree calculates step, specifically includes: the H value and S value of each pixel of the first picture and second picture is obtained, by the first picture
H value by pixel position form H1 matrix, by the S value of the first picture by pixel position form S1 matrix, by second
The H value of picture forms H2 matrix by the position of pixel, and the S value of second picture is formed S2 matrix, meter by the position of pixel
Calculate D1=H1-H2；D2=S1-S2 calculates the element average value of D1And the element average value of D2
7. terminal according to claim 5, which is characterized in that
The processor is also used to for the upload user of the first short-sighted frequency being marked, and to the history video for uploading Termination ID
Shielding.
8. server according to claim 5, which is characterized in that
The processor is also used to control communication unit for the address of the first short-sighted frequency and terminal and is sent to public security organ's clothes
Business device.
9. according to server described in claim 5-8 any one, which is characterized in that
The terminal are as follows: computer or cloud platform.
10. a kind of computer readable storage medium, storage is used for the program of electronic data interchange, wherein described program makes
Terminal executes the method provided such as claim 1-4 any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910420066.9A CN110147462A (en) | 2019-05-20 | 2019-05-20 | The verification method and Related product of the short-sighted frequency of religion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910420066.9A CN110147462A (en) | 2019-05-20 | 2019-05-20 | The verification method and Related product of the short-sighted frequency of religion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110147462A true CN110147462A (en) | 2019-08-20 |
Family
ID=67592269
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910420066.9A Withdrawn CN110147462A (en) | 2019-05-20 | 2019-05-20 | The verification method and Related product of the short-sighted frequency of religion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110147462A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113642419A (en) * | 2021-07-23 | 2021-11-12 | 上海亘存科技有限责任公司 | Convolutional neural network for target identification and identification method thereof |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104768029A (en) * | 2015-03-20 | 2015-07-08 | 深圳市同洲电子股份有限公司 | Station caption detection method and digital television terminal |
| CN106488313A (en) * | 2016-10-31 | 2017-03-08 | Tcl集团股份有限公司 | A kind of TV station symbol recognition method and system |
| CN106507188A (en) * | 2016-11-25 | 2017-03-15 | 南京中密信息科技有限公司 | A kind of video TV station symbol recognition device and method of work based on convolutional neural networks |
| CN107330027A (en) * | 2017-06-23 | 2017-11-07 | 中国科学院信息工程研究所 | A kind of Weakly supervised depth station caption detection method |
| CN107767365A (en) * | 2017-09-21 | 2018-03-06 | 华中科技大学鄂州工业技术研究院 | A kind of endoscopic images processing method and system |
| US20180242047A1 (en) * | 2014-06-12 | 2018-08-23 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for identifying television channel information |
-
2019
- 2019-05-20 CN CN201910420066.9A patent/CN110147462A/en not_active Withdrawn
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180242047A1 (en) * | 2014-06-12 | 2018-08-23 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for identifying television channel information |
| CN104768029A (en) * | 2015-03-20 | 2015-07-08 | 深圳市同洲电子股份有限公司 | Station caption detection method and digital television terminal |
| CN106488313A (en) * | 2016-10-31 | 2017-03-08 | Tcl集团股份有限公司 | A kind of TV station symbol recognition method and system |
| CN106507188A (en) * | 2016-11-25 | 2017-03-15 | 南京中密信息科技有限公司 | A kind of video TV station symbol recognition device and method of work based on convolutional neural networks |
| CN107330027A (en) * | 2017-06-23 | 2017-11-07 | 中国科学院信息工程研究所 | A kind of Weakly supervised depth station caption detection method |
| CN107767365A (en) * | 2017-09-21 | 2018-03-06 | 华中科技大学鄂州工业技术研究院 | A kind of endoscopic images processing method and system |
Non-Patent Citations (1)
| Title |
|---|
| 符亚彬: "基于Logo标志检测的暴恐视频识别系统的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113642419A (en) * | 2021-07-23 | 2021-11-12 | 上海亘存科技有限责任公司 | Convolutional neural network for target identification and identification method thereof |
| CN113642419B (en) * | 2021-07-23 | 2024-03-01 | 上海亘存科技有限责任公司 | Convolutional neural network for target recognition and recognition method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108197532B (en) | The method, apparatus and computer installation of recognition of face | |
| CN104883384B (en) | A kind of method and apparatus for the end ability that client is provided for light application | |
| CN107578659A (en) | Generation method, generating means and the terminal of electronics topic | |
| CN110119733A (en) | Page recognition methods and device, terminal device, computer readable storage medium | |
| CN111310724A (en) | In-vivo detection method and device based on deep learning, storage medium and equipment | |
| CN109872362A (en) | A kind of object detection method and device | |
| CN112734498A (en) | Task reward acquisition method, device, terminal and storage medium | |
| CN107506494B (en) | Document handling method, mobile terminal and computer readable storage medium | |
| CN109816543A (en) | A kind of image lookup method and device | |
| CN109658420A (en) | Change face method and the Related product of short-sighted frequency | |
| CN110022397A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN110147462A (en) | The verification method and Related product of the short-sighted frequency of religion | |
| CN110119396A (en) | Data managing method and Related product | |
| CN107741980A (en) | Topic searching method, topic searcher and electric terminal | |
| CN112149570A (en) | Multi-person living body detection method and device, electronic equipment and storage medium | |
| CN109697746A (en) | Self-timer video cartoon head portrait stacking method and Related product | |
| CN110516590A (en) | Operation or work standard prompt system based on scene Recognition | |
| US11288776B2 (en) | Method and apparatus for image processing | |
| CN107133940A (en) | A kind of patterning process and terminal | |
| CN109688452A (en) | Pagination Display stage property stacking method and Related product | |
| CN113850118A (en) | Video processing function verification method and device, electronic equipment and storage medium | |
| CN113094624A (en) | Page generation method and device and electronic equipment | |
| CN109740431A (en) | From the eyebrow processing method and Related product of the head portrait picture to shoot the video | |
| CN109525499A (en) | The flow managing method and Related product of short Video Applications | |
| CN111124579A (en) | Special effect rendering method and device, electronic equipment and storage medium |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190820 |