CN106067006A - For the method and apparatus identifying news program - Google Patents
For the method and apparatus identifying news program Download PDFInfo
- Publication number
- CN106067006A CN106067006A CN201610405071.9A CN201610405071A CN106067006A CN 106067006 A CN106067006 A CN 106067006A CN 201610405071 A CN201610405071 A CN 201610405071A CN 106067006 A CN106067006 A CN 106067006A
- Authority
- CN
- China
- Prior art keywords
- field picture
- image template
- column
- image
- template
- 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
Classifications
-
- 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
- G06V20/43—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of news video content
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of method and apparatus for identifying news program.Described method includes: obtain at least one two field picture from video to be identified;Whether at least one two field picture described in judgement mates with predetermined image template, and described predetermined image template includes that the column icon of described news program, described column icon are in predetermined column icon area;When at least one two field picture described in judging mates with described predetermined image template, determine that described video to be identified is the video in described news program.This way it is not necessary to intercept the head picture of news program, it becomes possible to identify the news program belonging to sub-news that demolition is crossed so that simpler efficiently to the Catalogue Work of news program, improve Consumer's Experience.
Description
Technical field
The present invention relates to Computer Image Processing field, in particular it relates to a kind of method for identifying news program and
Device.
Background technology
Along with popularizing of automatic technology, one of automated cataloging technology necessary technology becoming radio, TV and film industries.For one
Individual news program, news program is one of requisite cataloguing key element.Current recognizer is all by intercepting news column
Purpose head picture is identified.And each news program has usually contained some sub-news, every sub-news is the most independent
Tell about a content.The news program belonging to the sub-news crossed through demolition is gone out by existing method None-identified.
Summary of the invention
It is an object of the invention to provide a kind of simple efficient for the method and apparatus identifying news program.
To achieve these goals, the present invention provides a kind of method for identifying news program.Described method includes: from
Video to be identified obtains at least one two field picture;Whether at least one two field picture described in judgement mates with predetermined image template, institute
State predetermined image template and include that the column icon of described news program, described column icon are in predetermined column icon area
In;When at least one two field picture described in judging mates with described predetermined image template, determine that described video to be identified is described
Video in news program.
Alternatively, the step that whether at least one two field picture described in described judgement mates with predetermined image template includes:
Choosing column identification region in described at least one two field picture, described column identification region includes described column icon area;Judge
Whether the image in described column identification region includes described column icon, and the image in described column identification region includes
During described column icon, it is determined that described at least one two field picture mates with described predetermined image template.
Alternatively, described predetermined image template also includes the television station's station symbol being in predetermined station symbol region, described
When the image in described column identification region includes described column icon, it is determined that described at least one two field picture and described predetermined figure
As the step of template matching includes: when the image in described column identification region includes described column icon, described at least
Choosing TV station symbol recognition region in one two field picture, described TV station symbol recognition region includes described station symbol region;Judge described TV station symbol recognition
Whether the image in region includes described television station station symbol, and the image in described TV station symbol recognition region includes described television station
During station symbol, it is determined that described at least one two field picture mates with described predetermined image template.
Alternatively, the step that whether at least one two field picture described in described judgement mates with predetermined image template includes:
Described at least one two field picture identifies described column icon;At least one two field picture described in judgement identifies described column icon
Whether region and described column icon area be within preset distance, and identifies described column in described at least one two field picture
When figure target area and described column icon area are within described preset distance, it is determined that described at least one two field picture is pre-with described
Fixed image template coupling.
Alternatively, according to one or more in following judge described at least one two field picture whether with predetermined image mould
Plate mates: OCR, image comparison algorithm.
Alternatively, the step that whether at least one two field picture described in described judgement mates with predetermined image template includes following
In any one: whether each two field picture at least one two field picture described in judgement mates with predetermined image template;Judge
Whether at least one two field picture in described at least one two field picture mates with predetermined image template.
Alternatively, described method also includes: set up data base, and in described data base, storage has multiple image template, described
At least one image template in multiple image templates is corresponding with described news program;Choose from described data base with described newly
Hear image template corresponding to column as described predetermined image template.
Alternatively, after the described step obtaining at least one two field picture from video to be identified, described method also includes:
The image template corresponding with described news program is chosen in data base;The image template corresponding with described news program is deposited
When there being the image template identical with the resolution of described at least one two field picture, choose and the resolution of described at least one two field picture
Identical image template is as described predetermined image template;The image template corresponding with described news program does not exist with
During the identical image template of the resolution of described at least one two field picture, choose identical with the length-width ratio of described at least one two field picture
Image template is as described predetermined image template.
The present invention also provides for a kind of for identifying news column destination device.Described device includes: acquisition module, for from treating
Identify in video and obtain at least one two field picture;Judge module, described in judge at least one two field picture whether with predetermined image
Template matching, described predetermined image template includes the column icon of described news program, and described column icon is in predetermined
In column icon area;Determine module, be used for when at least one two field picture described in judging mates with described predetermined image template,
Determine that described video to be identified is the video in described news program.
Pass through technique scheme, it is judged that whether the image in video to be identified mates with image template, determines video
Whether it is the video in a news program.This way it is not necessary to intercept the head picture of news program, it becomes possible to identify demolition mistake
The news program belonging to sub-news so that simpler efficiently to the Catalogue Work of news program, improve Consumer's Experience.
Other features and advantages of the present invention will be described in detail in detailed description of the invention part subsequently.
Accompanying drawing explanation
Accompanying drawing is used to provide a further understanding of the present invention, and constitutes the part of description, with following tool
Body embodiment is used for explaining the present invention together, but is not intended that limitation of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart of the method for identifying news program that an exemplary embodiment provides;
Fig. 2 is the flow chart of the method for identifying news program that another exemplary embodiment provides;
Fig. 3 is the schematic diagram choosing column identification region that an exemplary embodiment provides;
Fig. 4 is the flow chart of the method for identifying news program that further example embodiment provides;
Fig. 5 is the schematic diagram choosing TV station symbol recognition region that an exemplary embodiment provides;
Fig. 6 is the flow chart of the method for identifying news program that further example embodiment provides;
Fig. 7 is the spacing that the judgement that an exemplary embodiment provides identifies column figure target area and column icon area
From schematic diagram;
Fig. 8 is the flow chart of the method for identifying news program that further example embodiment provides;
Fig. 9 is the flow chart of the method for identifying news program that further example embodiment provides;
Figure 10 is the block diagram for identifying news column destination device that an exemplary embodiment provides;
Figure 11 is the block diagram for identifying news column destination device that another exemplary embodiment provides;
Figure 12 is the block diagram for identifying news column destination device that further example embodiment provides;And
Figure 13 is the block diagram for identifying news column destination device that further example embodiment provides.
Detailed description of the invention
Below in conjunction with accompanying drawing, the detailed description of the invention of the present invention is described in detail.It should be appreciated that this place is retouched
The detailed description of the invention stated is merely to illustrate and explains the present invention, is not limited to the present invention.
In the present invention, in the case of illustrating on the contrary, the noun of locality of use such as " upper and lower, left and right " typically refers to
The direction a video for the angle of spectators.
Fig. 1 is the flow chart of the method for identifying news program that an exemplary embodiment provides.As it is shown in figure 1, institute
The method of stating comprises the following steps.
In step s 11, from video to be identified, at least one two field picture is obtained.
In step s 12, it is judged that whether described at least one two field picture mates with predetermined image template.Predetermined image mould
Plate includes the column icon of news program, and column icon is in predetermined column icon area.
In step s 13, when at least one two field picture described in judging mates with predetermined image template, to be identified regarding is determined
Frequency is the video in news program.
Pass through technique scheme, it is judged that whether the image in video to be identified mates with image template, determine and wait to know
Whether other video is the video in news program.Therefore, there is no need to intercept the head picture of news program, it becomes possible to identify and tear open
The news program belonging to sub-news that bar is crossed so that simpler efficiently to the Catalogue Work of news program, improves Consumer's Experience.
Specifically, in step s 11, video to be identified can be the sub-news that a news program is crossed through demolition.Permissible
Such as FFMPEG storehouse of increasing income is utilized to obtain at least one frame (such as, 10 frame) image from video to be identified.In step afterwards,
The news program belonging to this video is identified according to institute's truncated picture.
Step S12 can be implemented in several ways.Fig. 2 be another exemplary embodiment provide for identifying news
The flow chart of the method for column.As in figure 2 it is shown, on the basis of Fig. 1, it is judged that described at least one two field picture whether with predetermined figure
As the step (step S12) of template matching may comprise steps of.
In step S121, choosing column identification region in described at least one two field picture, column identification region includes hurdle
Mesh icon area.
In step S122, it is judged that whether the image in described column identification region includes described column icon, and on hurdle
When the image in mesh identification region includes column icon, it is determined that described at least one two field picture mates with predetermined image template.
Wherein, choose column identification region to seek to the image in this column identification region is identified, it is judged that this hurdle
Whether mesh identification includes column icon in region.Such as, a column icon is arranged on the lower left of screen, then can be from treating
Identify the lower left of the image choosing out in video, choose one piece of region corresponding with column icon (column identification region),
Image in this column identification region is identified.Column identification region can include column icon area.It is, column
Identify that region could be arranged to identical with column icon area, it is also possible to be set greater than column icon area.
Fig. 3 is the schematic diagram choosing column identification region that an exemplary embodiment provides.As it is shown on figure 3, column icon
Region I is arranged on a fixed position in the image lower left corner.Column identification region II can be arranged on the image lower left corner.Further, exist
When image template is identical with the resolution of selected image, column identification region II can ratio column icon in the horizontal direction
Region about I is respectively beyond such as 20 pixels, and in the vertical direction respectively exceeds such as 15 pixels than column icon area I.?
When image template is different from the resolution of selected image, column identification region II can in the horizontal direction with on vertical direction
Than column icon area I respectively beyond the length (such as, the 1/20 of image length) of predetermined ratio.
In this embodiment, by choosing a part of region (column identification region) in selected image, less
Region identifying, image judges whether selected image mates with predetermined image template.So, reduce need identify
Image range, reduce workload, accelerate recognition speed.
Having some news programs only to broadcast in fixing television station, such as, " Lanzhou news " column is only in Lanzhou television station
Broadcast.Therefore, on the basis of being identified according to column icon, it is also possible to by the station symbol information of television station to identify figure
As making further to confirm, to increase the accuracy identified.Fig. 4 be further example embodiment provide for identifying news column
The flow chart of purpose method.In this embodiment, predetermined image template can also include the TV being in predetermined station symbol region
Platform station symbol.As shown in Figure 4, on the basis of Fig. 2, when the image in described column identification region includes column icon, it is determined that
The step (step S122) that described at least one two field picture mates with predetermined image template may comprise steps of.
In step S1221, when the image in column identification region includes described column icon, at described at least one frame
Choosing TV station symbol recognition region in image, TV station symbol recognition region includes station symbol region.
In step S1222, it is judged that whether the image in described TV station symbol recognition region include described television station station symbol, and
When the image in TV station symbol recognition region includes television station's station symbol, it is determined that described at least one two field picture and predetermined image template
Join.
With the embodiment in Fig. 2 similarly, choose TV station symbol recognition region to seek to the image in this TV station symbol recognition region
It is identified, it is judged that whether this TV station symbol recognition region includes television station's station symbol.Such as, television station's station symbol is arranged on screen
Upper left side, then one piece and television station's station symbol pair can be chosen on the upper left side of the image choosing out from video to be identified
The region (TV station symbol recognition region) answered, is identified the image in this TV station symbol recognition region.TV station symbol recognition region can include
Station symbol region.It is, TV station symbol recognition region could be arranged to identical with station symbol region, it is also possible to be set greater than station symbol district
Territory.
Fig. 5 is the schematic diagram choosing TV station symbol recognition region that an exemplary embodiment provides.As it is shown in figure 5, station symbol region
III is arranged on a fixed position in the image upper left corner.TV station symbol recognition region IV can be arranged on the image upper left corner.Further, at figure
As template identical with the resolution of selected image time, TV station symbol recognition region IV can ratio station symbol region in the horizontal direction
About III is respectively beyond such as 20 pixels, and in the vertical direction respectively exceeds such as 15 pixels than station symbol region III.At image
When template is different from the resolution of selected image, TV station symbol recognition region IV can compare platform with on vertical direction in the horizontal direction
Mark region III is respectively beyond the length (such as, the 1/20 of image length) of predetermined ratio.
In this embodiment, on the basis of identifying column icon, by further the station symbol of television station being confirmed,
Confirming the column icon identified further, so that the news program identified is more accurate, reduce erroneous judgement can
Energy.
In another embodiment of the present invention, the region for image recognition can not be delimited in advance, but to whole
Image is identified, when identifying column icon, it is judged that whether the column icon identified is in the usual institute of this column image
Position.
Fig. 6 is the flow chart of the method for identifying news program that further example embodiment provides.As shown in Figure 6,
On the basis of Fig. 1, it is judged that the step (step S12) whether described at least one two field picture mates with predetermined image template is permissible
Comprise the following steps.
In step S123, described at least one two field picture identifies column icon.
In step S124, it is judged that described at least one two field picture identifies described column figure target area and described column
Whether icon area is within preset distance, and identifies column figure target area and column figure in described at least one two field picture
When mark region is within preset distance, it is determined that described at least one two field picture mates with predetermined image template.
Wherein, described preset distance, can be the distance at the center in two regions, or the level side in two regions
The distance between border upwards, or the distance between the border on the vertical direction in two regions.
Fig. 7 is the spacing that the judgement that an exemplary embodiment provides identifies column figure target area and column icon area
From schematic diagram.As it is shown in fig. 7, identify the distance of column figure target area V and column icon area I the two regional center
For OO', according to this distance and preset distance be compared to determine the column icon identified in image whether can confirm that into
Column icon, namely determine described at least one two field picture whether mate (step S12) with predetermined image template.
It is understood that when image template is identical with the resolution of selected image, above-mentioned preset distance is permissible
Calculate with predetermined pixel, such as 20 pixels.When image template is different from the resolution of selected image, above-mentioned predetermined
Distance can calculate with the length of predetermined ratio, such as the 1/20 of image total length.
In this embodiment, whole image identifies column icon, it therefore reduces omit the probability of icon, thus
Decrease erroneous judgement.
Specifically, can according to one or more in following judge described at least one two field picture whether with predetermined figure
As template matching: OCR (Optical Character Recognition, optical character recognition) technology, image comparison algorithm.
Wherein, when column icon only includes character, can use OCR technique, image comparison algorithm (such as, based on
The image comparison algorithm of OpenGL) or the combination of the two judge;When column icon includes character and image, or only wrap
When including figure, it is possible to use only image comparison algorithm judges.
It addition, choose from image is at least one two field picture, when choosing multiple image, at least one frame described in judgement
When whether image mates (step S12) with predetermined image template, each two field picture chosen all can be judged, then
Judged result according to each frame determines whether video to be identified mates with image template.Specifically, it is judged that described at least one frame
The step (step S12) whether image mates with predetermined image template can include following in any one:
Whether each two field picture at least one two field picture described in judgement mates with predetermined image template.It is, work as
When each two field picture in described at least one two field picture all mates with predetermined image template, just by video identification to be identified be with
The news program that image template is corresponding, the accuracy identified in this embodiment is higher;
Whether at least one two field picture at least one two field picture described in judgement mates with predetermined image template.It is,
When described at least one two field picture has a two field picture to mate with image template, it is possible to by video identification to be identified be and image
The news program that template is corresponding, it is also possible to when having a two field picture to mate with image template at least one two field picture described in judging,
Just no longer carry out the judgement of residual image, the speed identified in this embodiment.
Wherein it is possible to according to the accuracy of news program identification and the requirement of recognition speed, select suitably to judge
Method.
Embodiment described above is the identification for specific news program, and predetermined image template is for this news
Column and the image template that arranges.The data base comprising multiple image template can also be pre-build, the when of identification, from this number
Mate according to storehouse is chosen image template.Fig. 8 be further example embodiment provide for identifying news column destination party
The flow chart of method.As shown in Figure 8, described method can also comprise the following steps.
In step S01, setting up data base, in this data base, storage has multiple image template, in multiple image templates
At least one image template is corresponding with described news program.
It is, this data base can store the image template of multiple news program.Each news program can have
One or more image templates are the most corresponding.Such as, each news program can include different resolution, the figure of different length-width ratio
As template.
In step S02, from data base, choose the image template corresponding with described news program as predetermined image
Template.
Mate as predetermined image template, then it is, choose the image template corresponding with described news program
The result of coupling may be used for judging whether video to be identified is the video in described news program.In this embodiment, by building
The vertical data base comprising multiple image template, facilitates user to search required image template.
It is understood that in the embodiment shown in fig. 8, step S01 and step S02 are to perform before step S11
's.In other embodiments, step S01 and step S02 can be after step s 11, or perform with step S11 simultaneously.
Fig. 9 is the flow chart of the method for identifying news program that further example embodiment provides.As it is shown in figure 9,
On the basis of Fig. 1, after the described step (step S11) obtaining at least one two field picture from video to be identified, described side
Method can also comprise the following steps.
In step S03, data base chooses the image template corresponding with described news program.
In step S04, there are in the image template corresponding with described news program and described at least one two field picture
Resolution identical image template time, choose the image template identical with the resolution of described at least one two field picture as described
Predetermined image template.
In step S05, do not exist in the image template corresponding with described news program and described at least one two field picture
Resolution identical image template time, choose the image template identical with the length-width ratio of described at least one two field picture as described
Predetermined image template.
It is, the image template corresponding with multiple news programs can be stored in the data base pre-build.Think
Identify when whether a video belongs to a certain news program, the mould image that this news program is corresponding can be chosen in step S03
Plate.It is identified it is of course also possible to the image template stored in data base is mated successively.
As it has been described above, image template corresponding to each news program can have multiple (such as, different resolution, difference
The image template of length-width ratio).(such as, differentiate when the image chosen in video to be identified is identical with the resolution of image template
Rate is all 1080*976), the identical image template of resolution can be chosen and mate as pre-solid plate.Without dividing
The image template that resolution is identical, then can choose the image template of length-width ratio identical (such as, length-width ratio is all 4:3) and carry out
Join.
Wherein it is possible to the image template preferentially choosing resolution identical in multiple image templates mates, it is possible to
Column identification region, column icon area, station symbol region and TV station symbol recognition region are configured by pixel rank, coupling
Accuracy higher.For example, it is possible to according to pixel choose point (200,760), rect (top, left, right,
Bottom) rectangular area is as column identification region.The image mould identical with the length-width ratio of image to be matched can also be chosen
Plate.Now, above-mentioned regional can be chosen according to the proportionate relationship with image length or width.For example, it is possible to choose figure
As the upper left corner, length, width are respectively a/15, b/15, and its upper left corner is positioned at the rectangular area of (a/40, b/40) as column
Identifying region, wherein, a is image length, and b is picture traverse.
In this embodiment, by setting up data base, and set up the priority orders choosing image template, it is possible to more
Identify the news program belonging to a video comprehensively, exactly, improve Consumer's Experience.
The present invention also provides for a kind of for identifying news column destination device.Figure 10 be one exemplary embodiment provide for
Identify the block diagram of news column destination device.As shown in Figure 10, described for identifying that news column destination device 10 can include obtaining
Module 11, judge module 12 and determine module 13.
Acquisition module 11 is for obtaining at least one two field picture from video to be identified.
Whether judge module 12 at least one two field picture described in judge mates with predetermined image template, described predetermined
Image template includes that the column icon of described news program, described column icon are in predetermined column icon area.
Determine that module 13 is for when at least one two field picture described in judging mates with described predetermined image template, determining institute
Stating video to be identified is the video in described news program.
Figure 11 is the block diagram for identifying news column destination device that another exemplary embodiment provides.As shown in figure 11,
On the basis of Figure 10, described judge module 12 can include that submodule 121 is chosen in column region and column judges submodule
122。
Submodule 121 is chosen for choosing column identification region, described hurdle in described at least one two field picture in column region
Mesh identification region includes described column icon area;
Column judges whether submodule 122 includes described column figure in the image judging described column identification region
Mark, and when the image in described column identification region includes described column icon, it is determined that described at least one two field picture and image
Template matching.
Figure 12 is the block diagram for identifying news column destination device that further example embodiment provides.In this embodiment,
Image template can also include the television station's station symbol being in predetermined station symbol region.As shown in figure 12, on the basis of Figure 11, institute
State column and judge that submodule 122 can also include that submodule 1221 is chosen in station symbol region and station symbol judges submodule 1222.
Submodule 1221 is chosen when the image in described column identification region includes column icon in station symbol region, in institute
Stating and choose TV station symbol recognition region at least one two field picture, described TV station symbol recognition region includes described station symbol region.
Station symbol judges whether submodule 1222 includes described television station in the image judging described TV station symbol recognition region
Station symbol, and when the image in described TV station symbol recognition region includes described television station's station symbol, it is determined that described at least one two field picture with
Image template mates.
Figure 13 is the block diagram for identifying news column destination device that further example embodiment provides.As shown in figure 13,
On the basis of Figure 10, described judge module 12 can include identifying submodule 123 and Distance Judgment submodule 124.
Identify that submodule 123 is for identifying described column icon in described at least one two field picture.
Distance Judgment submodule 124 be used for judging described at least one two field picture identifies described column figure target area with
Whether described column icon area is within preset distance, and identifies described column icon in described at least one two field picture
When region and described column icon area are within preset distance, it is determined that described at least one two field picture mates with image template.
Alternatively, according to one or more in following judge described at least one two field picture whether with described predetermined figure
As template matching: OCR, image comparison algorithm.
Alternatively, described judge module 12 can include following in any one: first judges that submodule and second is sentenced
Disconnected submodule.
First judge each two field picture in submodule at least one two field picture described in judge whether with predetermined image
Template matching.
Second judge at least one two field picture in submodule at least one two field picture described in judge whether with predetermined figure
As template matching.
Alternatively, described device can also include that Database module and template choose module.
Database module is used for setting up data base, and in described data base, storage has multiple image template, the plurality of
At least one image template in image template is corresponding with described news program.
Template chooses module for choosing the image template corresponding with described news program from data base as predetermined
Image template.
Alternatively, described device can also include first choosing module, second choosing module and the 3rd and choose module.
First chooses module for choosing the image template corresponding with described news program in data base.
Second chooses module for there are in the image template corresponding with described news program and described at least one frame
During the identical image template of the resolution of image, choose the image template conduct identical with the resolution of described at least one two field picture
Described predetermined image template.
3rd chooses module for not existing in the image template corresponding with described news program and described at least one frame
During the identical image template of the resolution of image, choose the image template conduct identical with the length-width ratio of described at least one two field picture
Described predetermined image template.
About the device in above-described embodiment, wherein modules performs the concrete mode of operation in relevant the method
Embodiment in be described in detail, explanation will be not set forth in detail herein.
Pass through technique scheme, it is judged that whether the image in video to be identified mates with image template, determines video
Whether it is the video in a news program.This way it is not necessary to intercept the head picture of news program, it becomes possible to identify demolition mistake
The news program belonging to sub-news so that simpler efficiently to the Catalogue Work of news program, improve Consumer's Experience.
The preferred embodiment of the present invention is described in detail above in association with accompanying drawing, but, the present invention is not limited to above-mentioned reality
Execute the detail in mode, in the technology concept of the present invention, technical scheme can be carried out multiple letter
Monotropic type, these simple variant belong to protection scope of the present invention.
It is further to note that each the concrete technical characteristic described in above-mentioned detailed description of the invention, at not lance
In the case of shield, can be combined by any suitable means.In order to avoid unnecessary repetition, the present invention to various can
The compound mode of energy illustrates the most separately.
Additionally, combination in any can also be carried out between the various different embodiment of the present invention, as long as it is without prejudice to this
The thought of invention, it should be considered as content disclosed in this invention equally.
Claims (16)
1. the method being used for identifying news program, it is characterised in that described method includes:
At least one two field picture is obtained from video to be identified;
Whether at least one two field picture described in judgement mates with predetermined image template, described predetermined image template include described newly
Hearing the column icon of column, described column icon is in predetermined column icon area;
When at least one two field picture described in judging mates with described predetermined image template, determine that described video to be identified is described
Video in news program.
Method the most according to claim 1, it is characterised in that whether at least one two field picture described in described judgement is with predetermined
The step of image template coupling includes:
Choosing column identification region in described at least one two field picture, described column identification region includes described column icon area
Territory;
Judge whether the image in described column identification region includes described column icon, and at the figure in described column identification region
During as including described column icon, it is determined that described at least one two field picture mates with described predetermined image template.
Method the most according to claim 2, it is characterised in that described predetermined image template also includes being in predetermined platform
Television station's station symbol in mark region, when the described image in described column identification region includes described column icon, it is determined that described
The step that at least one two field picture mates with described predetermined image template includes:
When the image in described column identification region includes described column icon, in described at least one two field picture, choose station symbol
Identifying region, described TV station symbol recognition region includes described station symbol region;
Judge whether the image in described TV station symbol recognition region includes described television station station symbol, and in described TV station symbol recognition region
When image includes described television station's station symbol, it is determined that described at least one two field picture mates with described predetermined image template.
Method the most according to claim 1, it is characterised in that whether at least one two field picture described in described judgement is with predetermined
The step of image template coupling includes:
Described column icon is identified in described at least one two field picture;
Whether at least one two field picture described in judgement identifies described column figure target area with described column icon area in advance
Within set a distance, and in described at least one two field picture, identify described column figure target area and described column icon area exist
Time within described preset distance, it is determined that described at least one two field picture mates with described predetermined image template.
Method the most according to claim 1, it is characterised in that according to one or more in following judge described at least
Whether one two field picture mates with described predetermined image template: OCR, image comparison algorithm.
Method the most according to claim 1, it is characterised in that whether at least one two field picture described in described judgement is with predetermined
Image template coupling step include following in any one:
Whether each two field picture at least one two field picture described in judgement mates with predetermined image template;
Whether at least one two field picture at least one two field picture described in judgement mates with predetermined image template.
7. according to the method described in any claim in claim 1-6, it is characterised in that described method also includes:
Setting up data base, in described data base, storage has multiple image template, at least one figure in the plurality of image template
As template is corresponding with described news program;
The image template corresponding with described news program is chosen as described predetermined image template from described data base.
8. according to the method described in any claim in claim 1-6, it is characterised in that described from video to be identified
After obtaining the step of at least one two field picture, described method also includes:
The image template corresponding with described news program is chosen in data base;
The figure identical with the resolution of described at least one two field picture is there are in the image template corresponding with described news program
During as template, choose the image template identical with the resolution of described at least one two field picture as described predetermined image template;
The figure identical with the resolution of described at least one two field picture is there is not in the image template corresponding with described news program
During as template, choose the image template identical with the length-width ratio of described at least one two field picture as described predetermined image template.
9. one kind is used for identifying news column destination device, it is characterised in that described device includes:
Acquisition module, for obtaining at least one two field picture from video to be identified;
Judge module, whether at least one two field picture described in judge mates with predetermined image template, described predetermined image
Template includes that the column icon of described news program, described column icon are in predetermined column icon area;
Determine module, for judge described at least one two field picture mate with described predetermined image template time, determine described in treat
Identify that video is the video in described news program.
Device the most according to claim 9, it is characterised in that described judge module includes:
Submodule is chosen in column region, for choosing column identification region, described column identification in described at least one two field picture
Region includes described column icon area;
Column judges submodule, for judging whether the image in described column identification region includes described column icon, and
When the image in described column identification region includes described column icon, it is determined that described at least one two field picture and described predetermined figure
As template matching.
11. devices according to claim 10, it is characterised in that described predetermined image template also includes being in predetermined
Television station's station symbol in station symbol region, described column judges that submodule also includes:
Submodule is chosen in station symbol region, for when the image in described column identification region includes described column icon, in institute
Stating and choose TV station symbol recognition region at least one two field picture, described TV station symbol recognition region includes described station symbol region;
Station symbol judges submodule, whether includes described television station station symbol in the image judging described TV station symbol recognition region, and
When the image in described TV station symbol recognition region includes described television station's station symbol, it is determined that described at least one two field picture is predetermined with described
Image template coupling.
12. devices according to claim 9, it is characterised in that described judge module includes:
Identify submodule, for identifying described column icon in described at least one two field picture;
Distance Judgment submodule, be used for judging described at least one two field picture identifies described column figure target area and described hurdle
Mesh icon area whether within preset distance, and identify in described at least one two field picture described column figure target area with
When described column icon area is within described preset distance, it is determined that described at least one two field picture and described predetermined image template
Coupling.
13. devices according to claim 9, it is characterised in that according to one or more in following judge described in extremely
Whether a few two field picture mates with described predetermined image template: OCR, image comparison algorithm.
14. devices according to claim 9, it is characterised in that described judge module include following in any one:
First judges submodule, each two field picture at least one two field picture described in judge whether with predetermined image template
Coupling;
Second judges submodule, at least one two field picture at least one two field picture described in judge whether with predetermined image mould
Plate mates.
15. according to the device described in any claim in claim 9-14, it is characterised in that described device also includes:
Database module, is used for setting up data base, and in described data base, storage has multiple image template, the plurality of image
At least one image template in template is corresponding with described news program;
Template chooses module, for choosing the image template corresponding with described news program from described data base as described pre-
Fixed image template.
16. according to the device described in any claim in claim 9-14, it is characterised in that described device also includes:
First chooses module, for choosing the image template corresponding with described news program in data base;
Second chooses module, for there are in the image template corresponding with described news program and described at least one two field picture
Resolution identical image template time, choose the image template identical with the resolution of described at least one two field picture as described
Predetermined image template;
3rd chooses module, for not existing in the image template corresponding with described news program and described at least one two field picture
Resolution identical image template time, choose the image template identical with the length-width ratio of described at least one two field picture as described
Predetermined image template.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610405071.9A CN106067006A (en) | 2016-06-07 | 2016-06-07 | For the method and apparatus identifying news program |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610405071.9A CN106067006A (en) | 2016-06-07 | 2016-06-07 | For the method and apparatus identifying news program |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106067006A true CN106067006A (en) | 2016-11-02 |
Family
ID=57420337
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610405071.9A Pending CN106067006A (en) | 2016-06-07 | 2016-06-07 | For the method and apparatus identifying news program |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106067006A (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101536513A (en) * | 2006-06-20 | 2009-09-16 | 尼尔森(美国)有限公司 | Methods and apparatus for detecting on-screen media sources |
CN101706873A (en) * | 2009-11-27 | 2010-05-12 | 东软集团股份有限公司 | Identification method and device of digital-class limitation marking |
CN102426647A (en) * | 2011-10-28 | 2012-04-25 | Tcl集团股份有限公司 | Station identification method and device |
CN102446272A (en) * | 2011-09-05 | 2012-05-09 | Tcl集团股份有限公司 | Method and device for segmenting and recognizing station caption as well as television comprising device |
CN103020650A (en) * | 2012-11-23 | 2013-04-03 | Tcl集团股份有限公司 | Station caption identifying method and device |
CN103336954A (en) * | 2013-07-08 | 2013-10-02 | 北京捷成世纪科技股份有限公司 | Identification method and device of station caption in video |
CN103477349A (en) * | 2011-01-04 | 2013-12-25 | 塔塔咨询服务有限公司 | Logo recognition |
CN103714350A (en) * | 2013-12-13 | 2014-04-09 | 安徽科大讯飞信息科技股份有限公司 | TV commercial detection method and TV commercial detection system based on channel logo position |
CN104023249A (en) * | 2014-06-12 | 2014-09-03 | 腾讯科技(深圳)有限公司 | Method and device of identifying television channel |
CN105100461A (en) * | 2015-07-08 | 2015-11-25 | 惠州Tcl移动通信有限公司 | Mobile terminal and method for realizing automatic answering thereof |
-
2016
- 2016-06-07 CN CN201610405071.9A patent/CN106067006A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101536513A (en) * | 2006-06-20 | 2009-09-16 | 尼尔森(美国)有限公司 | Methods and apparatus for detecting on-screen media sources |
CN101706873A (en) * | 2009-11-27 | 2010-05-12 | 东软集团股份有限公司 | Identification method and device of digital-class limitation marking |
CN103477349A (en) * | 2011-01-04 | 2013-12-25 | 塔塔咨询服务有限公司 | Logo recognition |
CN102446272A (en) * | 2011-09-05 | 2012-05-09 | Tcl集团股份有限公司 | Method and device for segmenting and recognizing station caption as well as television comprising device |
CN102426647A (en) * | 2011-10-28 | 2012-04-25 | Tcl集团股份有限公司 | Station identification method and device |
CN103020650A (en) * | 2012-11-23 | 2013-04-03 | Tcl集团股份有限公司 | Station caption identifying method and device |
CN103336954A (en) * | 2013-07-08 | 2013-10-02 | 北京捷成世纪科技股份有限公司 | Identification method and device of station caption in video |
CN103714350A (en) * | 2013-12-13 | 2014-04-09 | 安徽科大讯飞信息科技股份有限公司 | TV commercial detection method and TV commercial detection system based on channel logo position |
CN104023249A (en) * | 2014-06-12 | 2014-09-03 | 腾讯科技(深圳)有限公司 | Method and device of identifying television channel |
CN105100461A (en) * | 2015-07-08 | 2015-11-25 | 惠州Tcl移动通信有限公司 | Mobile terminal and method for realizing automatic answering thereof |
Non-Patent Citations (2)
Title |
---|
侯胜伟 等: "台标的自动检测与识别", 《四川大学学报(自然科学版)》 * |
张大宝 等: "基于音视频模板匹配的新闻视频识别方法", 《电视技术》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10257481B2 (en) | Method and system for adjusting a projected image, and projection device | |
CN107977659B (en) | Character recognition method and device and electronic equipment | |
KR101758580B1 (en) | Method and apparatus for area identification | |
CN110738602A (en) | Image processing method and device, electronic equipment and readable storage medium | |
KR102462025B1 (en) | Apparatus and method for detecting checkerboard corner point for camera calibration | |
US10027878B2 (en) | Detection of object in digital image | |
CN105869122A (en) | Image processing method and apparatus | |
CN101286230B (en) | Image processing apparatus and method thereof | |
US20190387184A1 (en) | Method and device for displaying target object | |
CN103593120A (en) | Method and device for adhering screenshot box to boundary of region of interest during screenshot | |
CN111833279A (en) | Fusion method of live-action hand-drawn map and electronic map | |
US10623719B2 (en) | Multi-aperture camera system for improving depth accuracy through focusing distance scan | |
CN105657395A (en) | Subtitle playing method and device for 3D (3-Dimensions) video | |
CN112989768B (en) | Method and device for correcting connection questions, electronic equipment and storage medium | |
CN104767926A (en) | Automatic focusing method and device | |
CN110557556A (en) | Multi-object shooting method and device | |
EP2853089B1 (en) | Pattern processing apparatus, pattern processing method, and pattern processing program | |
CN106067006A (en) | For the method and apparatus identifying news program | |
CN105631446A (en) | Method and device for determining interactive corner mark prompt | |
CN106446889A (en) | Local identification method and local identification device for station logo | |
US10383515B2 (en) | Method of detecting pupil center | |
CN107579028B (en) | Method and device for determining edge of incomplete wafer and scribing device | |
JP5983033B2 (en) | Position relationship determination program, position relationship determination method, and position relationship determination device | |
EP3540630A1 (en) | Glint detection method | |
CN109040774B (en) | Program information extraction method, terminal equipment, server and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161102 |