CN107133553A - A kind of method and device for recognizing TV station's icon - Google Patents
A kind of method and device for recognizing TV station's icon Download PDFInfo
- Publication number
- CN107133553A CN107133553A CN201610113690.0A CN201610113690A CN107133553A CN 107133553 A CN107133553 A CN 107133553A CN 201610113690 A CN201610113690 A CN 201610113690A CN 107133553 A CN107133553 A CN 107133553A
- Authority
- CN
- China
- Prior art keywords
- station
- icon
- matching degree
- image
- detected
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The invention discloses a kind of method and device for recognizing TV station's icon.Identification TV station figure calibration method, including：Obtain the n two field pictures of TV station to be detected；Extract the scale invariant feature of each two field picture in the n two field pictures of the TV station to be detected；According to the standard scale invariant features database of default TV station's icon, each two field picture matching degree highest TV station icon in the n two field pictures with the TV station to be detected is analyzed respectively；The occurrence number of TV station's icon described in identical is counted, it is matching TV station icon to determine the most TV station's icon of the occurrence number.The present invention can accurately identify TV station's icon in the picture of TV station to be identified, so as to according to obtaining the information related to TV station icon.
Description
Technical field
The present invention relates to field of image recognition, more particularly to a kind of method and device for recognizing TV station's icon.
Background technology
TV station's icon is one of specific vision content in INVENTIONBroadcast video, contains the platform of the TV station
The important semantic information such as name, type, copyright, is to discriminate between the important mark of broadcast TV channel, Er Qietai
Target identification all has great importance for the program guiding of radio and television, content analysis and retrieval etc..Mesh
Before, in terms of identification TV station icon, it is frequently encountered the background image that TV station's icon appears in complexity
In, and background image can continue change under many circumstances, and background image that is complicated and persistently changing can shadow
Ring the degree of accuracy to identification TV station icon.The quantity of particularly tv stations currently broadcast is very more, according to statistics much
In 300 channels, the similar degree of some of which TV station icon is higher, adds and accurately identifies TV station's figure
Target difficulty.Therefore how to solve the above problems, just become industry problem urgently to be resolved hurrily.
The content of the invention
The present invention provides a kind of method and device for recognizing TV station's icon, and technical scheme passes through figure
The scale invariant feature of picture recognizes TV station's icon, can improve the accuracy of identification TV station icon.
First aspect according to embodiments of the present invention recognizes TV station's figure calibration method there is provided one kind, including：
Obtain the n two field pictures of TV station to be detected；
Extract the scale invariant feature of each two field picture in the n two field pictures of the TV station to be detected；
According to the standard scale invariant features database of default TV station's icon, analyze treated with described respectively
Each two field picture matching degree highest TV station icon in the n two field pictures of the TV station of detection；
The occurrence number of TV station's icon described in identical is counted, the most TV station of the occurrence number is determined
Icon is matching TV station icon.
In one embodiment, each frame figure in the n two field pictures for extracting the TV station to be detected
The scale invariant feature of picture, including：According to default interception area, the TV station to be detected is intercepted
The image in the corresponding interception area of each two field picture in n two field pictures, described image is referred to as interception
Image；
It is default standard size by the size conversion of the interception image, by the interception image after conversion
Referred to as the first image；
Described first image is subjected to gray processing processing, the described first image after gray processing is handled is referred to as
Standard picture；
Coordinate system is set up in the standard picture, the scale invariant feature of the standard picture is extracted, it is described
Scale invariant feature includes corresponding coordinate parameters.
In one embodiment, the standard scale invariant features data according to default TV station's icon
Storehouse, analyzes each two field picture matching degree highest in the n two field pictures with the TV station to be detected respectively
TV station's icon, including：
Calculate the i-th two field picture and the default TV in the n two field pictures of the TV station to be detected
The matching degree of each TV station's image in the standard scale invariant features database of platform icon；
Contrast and the i-th two field picture matching degree highest TV station icon；
Determine first TV station's icon that TV station's icon is i-th two field picture.
In one embodiment, the occurrence number of TV station's icon described in the statistics identical, it is determined that described
The most TV station's icon of occurrence number is matching TV station icon, including：
Count and go out in first TV station icon corresponding to the n two field pictures of the TV station to be detected
The most TV station's icon of occurrence number；
Determine electricity of the most TV station's icon of the occurrence number corresponding to the TV station to be detected
Television stations icon.
In one embodiment, it is described contrast with the i-th two field picture matching degree highest TV station icon,
Including：
Obtain the matching degree numerical value of the matching degree highest TV station icon；
When the matching degree numerical value is more than or equal to default matching degree threshold value, determine that TV station's icon is
TV station's icon of i-th two field picture；
When the matching degree numerical value is less than default matching degree threshold value, determine i-th two field picture default
TV station's icon database in be not present corresponding TV station's icon.
Second aspect according to embodiments of the present invention there is provided a kind of device for recognizing TV station icon, including：
Acquisition module, the n two field pictures of TV station to be detected for obtaining；
Extraction module, the chi of each two field picture in n two field pictures for extracting the TV station to be detected
Spend invariant features；
Analysis module, for the standard scale invariant features database according to default TV station's icon, difference
Analyze each two field picture matching degree highest TV station in the n two field pictures with the TV station to be detected
Icon；
Statistical module, the occurrence number for counting TV station's icon described in identical, it is determined that it is described go out occurrence
The most TV station's icon of number is matching TV station icon.
In one embodiment, the extraction module, including：
Submodule is intercepted, for according to default interception area, intercepting the n frames of the TV station to be detected
The image in the corresponding interception area of each two field picture in image, described image is referred to as interception figure
Picture；
Transform subblock, for being default standard size by the size conversion of the interception image, will be changed
The interception image afterwards is referred to as the first image；
Gray processing submodule, for described first image to be carried out into gray processing processing, after gray processing is handled
Described first image is referred to as standard picture；
Extracting sub-module, for setting up coordinate system in the standard picture, extracts the chi of the standard picture
Invariant features are spent, the scale invariant feature includes corresponding coordinate parameters.
In one embodiment, the analysis module, including：
Calculating sub module, the i-th two field picture in n two field pictures for calculating the TV station to be detected
With each TV station's image in the standard scale invariant features database of default TV station's icon
Matching degree；
Submodule is contrasted, for contrasting and the i-th two field picture matching degree highest TV station icon；
First determination sub-module, for determining first TV of the TV station's icon for i-th two field picture
Platform icon.
In one embodiment, the statistical module, including：
Statistic submodule, for counting described corresponding to the n two field pictures of the TV station to be detected
The most TV station's icon of occurrence number in one TV station's icon；
Second determination sub-module, for determining that the most TV station's icon of the occurrence number is described to be detected
TV station corresponding to TV station's icon.
In one embodiment, the contrast submodule, is additionally operable to obtain the matching degree highest TV station
The matching degree numerical value of icon；When the matching degree numerical value is more than or equal to default matching degree threshold value, institute is determined
State TV station's icon that TV station's icon is i-th two field picture；When the matching degree numerical value is less than default
During matching degree threshold value, determine that correspondence is not present in i-th two field picture in default TV station's icon database
TV station's icon.
Other features and advantages of the present invention will be illustrated in the following description, also, partly from explanation
Become apparent, or understood by implementing the present invention in book.The purpose of the present invention and other advantages can
Realize and obtain by specifically noted structure in the specification, claims and accompanying drawing write
.
Below by drawings and examples, technical scheme is described in further detail.
Brief description of the drawings
Accompanying drawing is used for providing a further understanding of the present invention, and constitutes a part for specification, with this hair
Bright embodiment is used to explain the present invention together, is not construed as limiting the invention.In the accompanying drawings：
Fig. 1 is a kind of flow of identification TV station figure calibration method shown in an exemplary embodiment of the invention
Figure；
The step of Fig. 2 is a kind of identification TV station's figure calibration method shown in an exemplary embodiment of the invention
S12 flow chart；
The step of Fig. 3 is a kind of identification TV station's figure calibration method shown in an exemplary embodiment of the invention
S13 flow chart；
The step of Fig. 4 is a kind of identification TV station's figure calibration method shown in an exemplary embodiment of the invention
S14 flow chart；
The step of Fig. 5 is a kind of identification TV station's figure calibration method shown in another exemplary embodiment of the present invention
S32 flow chart；
Fig. 6 is a kind of block diagram of the device of identification TV station icon shown in an exemplary embodiment of the invention；
Fig. 7 is a kind of extraction mould of the device of identification TV station icon shown in an exemplary embodiment of the invention
The block diagram of block 62；
Fig. 8 is a kind of analysis mould of the device of identification TV station icon shown in an exemplary embodiment of the invention
The block diagram of block 63；
Fig. 9 is a kind of statistics mould of the device of identification TV station icon shown in an exemplary embodiment of the invention
The block diagram of block 64.
Embodiment
The preferred embodiments of the present invention are illustrated below in conjunction with accompanying drawing, it will be appreciated that described herein
Preferred embodiment is merely to illustrate and explain the present invention, and is not intended to limit the present invention.
Fig. 1 is a kind of method flow diagram of identification TV station icon according to an exemplary embodiment, such as
Shown in Fig. 1, the identification TV station figure calibration method comprises the following steps S11-S14：
In step s 11, the n two field pictures of TV station to be detected are obtained；
The continuous n two field pictures of TV station to be detected can be obtained, discrete n frames figure can also be obtained
Picture, the n two field pictures are all from same TV station.In preferred embodiment, n numerical value is more than 25.
In step s 12, the chi of each two field picture in the n two field pictures of the TV station to be detected is extracted
Spend invariant features；
The n two field pictures of TV station to be detected are pre-processed first, pretreated n two field pictures are carried
Take its scale invariant feature.Scale invariant feature conversion (Scale-invariant feature transform, referred to as
SIFT it is) that a kind of algorithm of computer vision is used for detecting and describing the locality characteristic in image, it is in space
Extreme point is found in yardstick, and extracts its position, yardstick, rotational invariants.Scale invariant feature is base
In the point of interest of some local appearances on object, the size of image can be resisted and brought influence is rotated.
In step s 13, according to the standard scale invariant features database of default TV station's icon, respectively
Analyze each two field picture matching degree highest TV station in the n two field pictures with the TV station to be detected
Icon；
Each two field picture and default TV station's icon in the n two field pictures of TV station to be detected by calculating
The matching degree of each TV station's icon in standard scale invariant features database, contrasts highest matching degree
Corresponding TV station's icon.Detailed process is the i-th frame in the n two field pictures for calculate TV station to be detected
Image and each TV station's image in the standard scale invariant features database of default TV station's icon
Matching degree, than go out with the i-th two field picture matching degree highest TV station icon, determine that TV station's icon is
First TV station's icon of the i-th two field picture.
In step S14, statistics identical described in TV station's icon occurrence number, it is determined that it is described go out occurrence
The most TV station's icon of number is matching TV station icon.
Count in first TV station's icon corresponding to the n two field pictures of TV station to be detected occurrence number most
Many TV station's icons, determine that the most TV station's icon of occurrence number is right for the TV station to be detected
The TV station's icon answered.In some cases, it is assumed that the occurrence number of the most TV station's icon of occurrence number
For c, c and n percentages d is calculated, if d gives up threshold value R less than default, it is believed that go out occurrence
The most TV station's icon of number is not preferably to match electric view icon enough, therefore thinks this matching TV
Platform icon is unsuccessful.It is recommended that re-entering the data of the frame of video of TV station to be detected.
In one embodiment, as shown in Fig. 2 step S11 comprises the following steps S21-S24：
In the step s 21, according to default interception area, the n frame figures of the TV station to be detected are intercepted
The image in the corresponding interception area of each two field picture as in, described image is referred to as interception image；
Default interception area is got according to priori, and TV station's icon always occurs from screen
The upper left corner either upper right corner.Judge that some TV station's icon appears in regional location, intercept region position
Put.It might as well assume that TV station's icon appears in the upper left corner, then only intercept the electricity for the TV station
The upper left corner of the image of television stations.And the size of of TV station's icon itself be also it is conditional,
So the size that the interception area needed is can also be fixed, it can so facilitate to all TV stations
Picture makes unified processing.The image intercepted in interception area out is referred to as interception image.
It is default standard size by the size conversion of the interception image, after conversion in step S22
The interception image be referred to as the first image；
Size conversion to capturing picture is unified size, and the size is default standard size.So may be used
To facilitate the processing of follow-up link.
In step S23, described first image is subjected to gray processing processing, described in after gray processing is handled
First image is referred to as standard picture；
In step s 24, coordinate system is set up in the standard picture, the yardstick of the standard picture is extracted
Invariant features, the scale invariant feature includes corresponding coordinate parameters.
In the present embodiment, coordinate system is set up in the standard picture, the origin of coordinate system might as well be set up
In the lower left corner of the standard picture, using horizontal direction as x-axis, using vertical direction as y-axis.Using yardstick
The method of invariant features conversion is extracted after the scale invariant feature of image, marks the scale invariant feature in seat
Transverse and longitudinal coordinate value in mark system.
For example, for the i-th two field picture in the n two field pictures of TV station to be detected, first determining whether in the figure
The position that TV station's icon occurs as in, might as well assume that TV station's icon appears in the upper right corner, then for
The TV station only intercepts the upper right corner of the image frame of the TV station, and the size that interception area is
It is fixed.After standard size operation and gray processing operation is carried out, passing through scale invariant feature method
Its scale invariant feature, and the method by setting up coordinate system are proposed, the horizontal stroke of the scale invariant feature is marked out
Ordinate value.
In one embodiment, as shown in figure 3, step S12 comprises the following steps S31-S33：
In step S31, calculate the i-th two field picture in the n two field pictures of the TV station to be detected with
Each TV station's image in the standard scale invariant features database of default TV station's icon
Matching degree；
All TV station's icons in the standard scale invariant features database of default TV station's icon, its
The Background of TV station's icon is all the Background of uniform pure color and texture-free.Therefore extract TV station's icon
Scale invariant feature is entirely to come from TV station's icon in itself, and its Background will not generate any yardstick
Invariant features.
Scale invariant feature in the i-th two field picture in the n two field pictures of TV station to be detected might as well be assumed
Coordinate set is set A, a certain in the standard scale invariant features database of default TV station's icon
The coordinate set of the scale invariant feature of width TV station icon is set B.It might as well claim set A corresponding figure
As being image x, the corresponding image of set B is image y.Calculate the common factor C of set A and set B.
The number of the element possessed in set A and C set is counted again, and the number for the element that set A possesses is a
It is c with the C numbers for gathering the element possessed.Calculate c divided by a percentages d, the percentage number
Value d is exactly image x and image y matching degree.
In step s 32, contrast and the i-th two field picture matching degree highest TV station icon；
I-th two field picture is calculated in the standard scale invariant features database with default TV station's icon
The matching degree of all TV station's icons, it is m that might as well assume the amount of images in the database.So just can be with
Obtain the matching degree d of the i-th two field picture and all images in the databasei1、di2……dim.Contrast di1、
di2……dimIn maximum, might as well assume the maximum be dimax。
In step S33, determine that the first TV station that TV station's icon is i-th two field picture schemes
Mark.
It is determined that being exactly that matching degree is d with the i-th two field picture matching degree highest TV station iconimaxTV
Platform icon.
In one embodiment, as shown in figure 4, step S14 comprises the following steps S41-S42：
In step S41, described first corresponding to the n two field pictures of the TV station to be detected is counted
The most TV station's icon of occurrence number in TV station's icon；
The standard scale of the n two field pictures of TV station to be detected and default TV station's icon is calculated respectively not
Change characteristic contrasts according to the matching degree in storehouse and draws highest corresponding to the n two field pictures of TV station to be detected
It is d with degree1max、d2max……dnmax, and then the corresponding TV station's icon of each highest matching degree drawn.
Count in the corresponding TV station's icon of each highest matching degree how many variety classes TV station icon and
The number of times that TV station's icon of each species occurs.
In step S42, it is the TV to be detected to determine the most TV station's icon of the occurrence number
TV station's icon corresponding to platform.
The most TV station's icon of the number of times of appearance is exactly TV station's icon corresponding to TV station to be detected.
In some cases, situation arranged side by side can occur for the most TV station's icon of the number of times of appearance, might as well vacation
If it is respectively TV station icon K and TV station icon G to occur in that TV station's icon arranged side by side, TV station is calculated
Icon K average highest matching degree k, calculates the average highest matching degree g of TV station icon G, compare k with
The size of g numerical value.K might as well be assumed>G, then it is to treat TV station to be detected that can confirm TV station icon K
Corresponding TV station's icon.
In one embodiment, as shown in figure 5, step S32 comprises the following steps S51-S53：
In step s 51, the matching degree numerical value of the matching degree highest TV station icon is obtained；
Highest matching degree numerical value corresponding to the n two field pictures of TV station to be detected is obtained, its occurrence is
d1max、d2max……dnmax。
In step S52, when the matching degree numerical value is more than or equal to default matching degree threshold value, institute is determined
State TV station's icon that TV station's icon is i-th two field picture；
It is L that default matching degree threshold value, which might as well be assumed, is respectively compared d1max、d2max……dnmaxWith L number
It is worth size.Work as dimaxDuring more than or equal to L, d is confirmedimaxCorresponding TV station's icon is the i-th two field picture
TV station's icon.
In step S53, when the matching degree numerical value is less than default matching degree threshold value, described the is determined
Corresponding TV station's icon is not present in i two field pictures in default TV station's icon database.
Work as dimaxDuring less than L, d is equivalent toimaxCorresponding TV station's icon and the TV station of the i-th two field picture
The matching degree of icon is not high enough, i.e., similarity degree is relatively low, therefore abandons the dimaxCorresponding TV station's icon.
Think that corresponding TV station's icon is not present in i-th two field picture in default TV station's icon database.
In one embodiment, Fig. 6 is a kind of identification TV station icon according to an exemplary embodiment
Device block diagram.As Fig. 6 shows, the device includes acquisition module 61, extraction module 62, analysis module 63
With statistical module 64.
The acquisition module 61, the n two field pictures of TV station to be detected for obtaining；
The extraction module 62, each two field picture in n two field pictures for extracting the TV station to be detected
Scale invariant feature；
The analysis module 63, for the standard scale invariant features database according to default TV station's icon,
Each two field picture matching degree highest electricity in the n two field pictures with the TV station to be detected is analyzed respectively
Television stations icon；
The statistical module 64, the occurrence number for counting TV station's icon described in identical, it is determined that it is described go out
The most TV station's icon of occurrence number is matching TV station icon.
As shown in fig. 7, the extraction module 62 includes interception submodule 71, transform subblock 72, gray processing
Submodule 73 and extracting sub-module 74.
The interception submodule 71, for according to default interception area, intercepting the TV station to be detected
The image in the corresponding interception area of each two field picture in n two field pictures, described image is referred to as interception
Image；
The transform subblock 72, will for being default standard size by the size conversion of the interception image
The interception image after conversion is referred to as the first image；
The gray processing submodule 73, for described first image to be carried out into gray processing processing, gray processing is handled
Described first image afterwards is referred to as standard picture；
The extracting sub-module 74, for setting up coordinate system in the standard picture, extracts the standard picture
Scale invariant feature, the scale invariant feature include corresponding coordinate parameters.
As shown in figure 8, the analysis module 63 is true including calculating sub module 81, contrast submodule 82 and first
Stator modules 83.
The calculating sub module 81, the i-th frame in n two field pictures for calculating the TV station to be detected
Image and each TV station in the standard scale invariant features database of default TV station's icon
The matching degree of image；
The contrast submodule 82, for contrasting and the i-th two field picture matching degree highest TV station icon；
The contrast submodule 82, is additionally operable to obtain the matching number of degrees of the matching degree highest TV station icon
Value；When the matching degree numerical value is more than or equal to default matching degree threshold value, determine that TV station's icon is
TV station's icon of i-th two field picture；When the matching degree numerical value is less than default matching degree threshold value,
Determine that corresponding TV station's icon is not present in i-th two field picture in default TV station's icon database；
First determination sub-module 83, for determining that TV station's icon is the first of i-th two field picture
TV station's icon.
As shown in figure 9, the statistical module 64 includes the determination sub-module 92 of statistic submodule 91 and second.
The statistic submodule 91, for counting the institute corresponding to the n two field pictures of the TV station to be detected
State the most TV station's icon of occurrence number in first TV station's icon；
Second determination sub-module 92, for determining that the most TV station's icon of the occurrence number is treated to be described
TV station's icon corresponding to the TV station of detection.
It should be understood by those skilled in the art that, embodiments of the invention can be provided as method, system or meter
Calculation machine program product.Therefore, the present invention can be using complete hardware embodiment, complete software embodiment or knot
The form of embodiment in terms of conjunction software and hardware.Wherein wrapped one or more moreover, the present invention can be used
Containing computer usable program code computer-usable storage medium (include but is not limited to magnetic disk storage and
Optical memory etc.) on the form of computer program product implemented.
The present invention is with reference to the production of method according to embodiments of the present invention, equipment (system) and computer program
The flow chart and/or block diagram of product is described.It should be understood that can by computer program instructions implementation process figure and
/ or each flow and/or square frame in block diagram and the flow in flow chart and/or block diagram and/
Or the combination of square frame.These computer program instructions can be provided to all-purpose computer, special-purpose computer, insertion
Formula processor or the processor of other programmable data processing devices are to produce a machine so that pass through and calculate
The instruction of the computing device of machine or other programmable data processing devices is produced for realizing in flow chart one
The device for the function of being specified in individual flow or multiple flows and/or one square frame of block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or the processing of other programmable datas to set
In the standby computer-readable memory worked in a specific way so that be stored in the computer-readable memory
Instruction produce include the manufacture of command device, the command device realization in one flow or multiple of flow chart
The function of being specified in one square frame of flow and/or block diagram or multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices, made
Obtain and perform series of operation steps on computer or other programmable devices to produce computer implemented place
Reason, so that the instruction performed on computer or other programmable devices is provided for realizing in flow chart one
The step of function of being specified in flow or multiple flows and/or one square frame of block diagram or multiple square frames.
Obviously, those skilled in the art can carry out various changes and modification without departing from this to the present invention
The spirit and scope of invention.So, if these modifications and variations of the present invention belong to the claims in the present invention
And its within the scope of equivalent technologies, then the present invention is also intended to comprising including these changes and modification.
Claims (10)
1. one kind identification TV station figure calibration method, it is characterised in that including：
Obtain the n two field pictures of TV station to be detected；
Extract the scale invariant feature of each two field picture in the n two field pictures of the TV station to be detected；
According to the standard scale invariant features database of default TV station's icon, analyze treated with described respectively
Each two field picture matching degree highest TV station icon in the n two field pictures of the TV station of detection；
The occurrence number of TV station's icon described in identical is counted, the most TV station of the occurrence number is determined
Icon is matching TV station icon.
2. according to the method described in claim 1, it is characterised in that described to extract the electricity to be detected
The scale invariant feature of each two field picture in the n two field pictures of television stations, including：
According to default interception area, each frame figure in the n two field pictures of the TV station to be detected is intercepted
As the image in the corresponding interception area, described image is referred to as interception image；
It is default standard size by the size conversion of the interception image, by the interception image after conversion
Referred to as the first image；
Described first image is subjected to gray processing processing, the described first image after gray processing is handled is referred to as
Standard picture；
Coordinate system is set up in the standard picture, the scale invariant feature of the standard picture is extracted, it is described
Scale invariant feature includes corresponding coordinate parameters.
3. method according to claim 2, it is characterised in that described to be schemed according to default TV station
Target standard scale invariant features database, analyzes the n two field pictures with the TV station to be detected respectively
In each two field picture matching degree highest TV station icon, including：
Calculate the i-th two field picture and the default TV in the n two field pictures of the TV station to be detected
The matching degree of each TV station's image in the standard scale invariant features database of platform icon；
Contrast and the i-th two field picture matching degree highest TV station icon；
Determine first TV station's icon that TV station's icon is i-th two field picture.
4. method according to claim 3, it is characterised in that TV described in the statistics identical
The occurrence number of platform icon, it is matching TV station icon to determine the most TV station's icon of the occurrence number,
Including：
Count and go out in first TV station icon corresponding to the n two field pictures of the TV station to be detected
The most TV station's icon of occurrence number；
Determine electricity of the most TV station's icon of the occurrence number corresponding to the TV station to be detected
Television stations icon.
5. method according to claim 3, it is characterised in that described to contrast and the i-th frame figure
As matching degree highest TV station icon, including：
Obtain the matching degree numerical value of the matching degree highest TV station icon；
When the matching degree numerical value is more than or equal to default matching degree threshold value, determine that TV station's icon is
TV station's icon of i-th two field picture；
When the matching degree numerical value is less than default matching degree threshold value, determine i-th two field picture default
TV station's icon database in be not present corresponding TV station's icon.
6. a kind of device for recognizing TV station's icon, it is characterised in that including：
Acquisition module, the n two field pictures of TV station to be detected for obtaining；
Extraction module, the chi of each two field picture in n two field pictures for extracting the TV station to be detected
Spend invariant features；
Analysis module, for the standard scale invariant features database according to default TV station's icon, difference
Analyze each two field picture matching degree highest TV station in the n two field pictures with the TV station to be detected
Icon；
Statistical module, the occurrence number for counting TV station's icon described in identical, it is determined that it is described go out occurrence
The most TV station's icon of number is matching TV station icon.
7. device according to claim 6, it is characterised in that the extraction module, including：
Submodule is intercepted, for according to default interception area, intercepting the n frames of the TV station to be detected
The image in the corresponding interception area of each two field picture in image, described image is referred to as interception figure
Picture；
Transform subblock, for being default standard size by the size conversion of the interception image, will be changed
The interception image afterwards is referred to as the first image；
Gray processing submodule, for described first image to be carried out into gray processing processing, after gray processing is handled
Described first image is referred to as standard picture；
Extracting sub-module, for setting up coordinate system in the standard picture, extracts the chi of the standard picture
Invariant features are spent, the scale invariant feature includes corresponding coordinate parameters.
8. device according to claim 7, it is characterised in that the analysis module, including：
Calculating sub module, the i-th two field picture in n two field pictures for calculating the TV station to be detected
With each TV station's image in the standard scale invariant features database of default TV station's icon
Matching degree；
Submodule is contrasted, for contrasting and the i-th two field picture matching degree highest TV station icon；
First determination sub-module, for determining first TV of the TV station's icon for i-th two field picture
Platform icon.
9. device according to claim 8, it is characterised in that the statistical module, including：
Statistic submodule, for counting described corresponding to the n two field pictures of the TV station to be detected
The most TV station's icon of occurrence number in one TV station's icon；
Second determination sub-module, for determining that the most TV station's icon of the occurrence number is described to be detected
TV station corresponding to TV station's icon.
10. device according to claim 8, it is characterised in that
The contrast submodule, is additionally operable to obtain the matching number of degrees of the matching degree highest TV station icon
Value；When the matching degree numerical value is more than or equal to default matching degree threshold value, determine that TV station's icon is
TV station's icon of i-th two field picture；When the matching degree numerical value is less than default matching degree threshold value,
Determine that corresponding TV station's icon is not present in i-th two field picture in default TV station's icon database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610113690.0A CN107133553A (en) | 2016-02-29 | 2016-02-29 | A kind of method and device for recognizing TV station's icon |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610113690.0A CN107133553A (en) | 2016-02-29 | 2016-02-29 | A kind of method and device for recognizing TV station's icon |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107133553A true CN107133553A (en) | 2017-09-05 |
Family
ID=59721099
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610113690.0A Pending CN107133553A (en) | 2016-02-29 | 2016-02-29 | A kind of method and device for recognizing TV station's icon |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107133553A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390162A (en) * | 2013-07-08 | 2013-11-13 | 中国科学院计算技术研究所 | Detection method for station captions |
| CN103413149A (en) * | 2013-09-06 | 2013-11-27 | 上海美琦浦悦通讯科技有限公司 | Method for detecting and identifying static target in complicated background |
| CN103473551A (en) * | 2013-09-16 | 2013-12-25 | 中国传媒大学 | Station logo recognition method and system based on SIFT operators |
| CN103955713A (en) * | 2014-04-24 | 2014-07-30 | 海信集团有限公司 | Icon recognition method and device |
| CN104537376A (en) * | 2014-11-25 | 2015-04-22 | 深圳创维数字技术有限公司 | A method, a relevant device, and a system for identifying a station caption |
-
2016
- 2016-02-29 CN CN201610113690.0A patent/CN107133553A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390162A (en) * | 2013-07-08 | 2013-11-13 | 中国科学院计算技术研究所 | Detection method for station captions |
| CN103413149A (en) * | 2013-09-06 | 2013-11-27 | 上海美琦浦悦通讯科技有限公司 | Method for detecting and identifying static target in complicated background |
| CN103473551A (en) * | 2013-09-16 | 2013-12-25 | 中国传媒大学 | Station logo recognition method and system based on SIFT operators |
| CN103955713A (en) * | 2014-04-24 | 2014-07-30 | 海信集团有限公司 | Icon recognition method and device |
| CN104537376A (en) * | 2014-11-25 | 2015-04-22 | 深圳创维数字技术有限公司 | A method, a relevant device, and a system for identifying a station caption |
Non-Patent Citations (1)
| Title |
|---|
| 金阳: "电视台标检测与识别技术研究", 《中国硕士学位论文全文数据库信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104023249B (en) | Television channel recognition methods and device | |
| CN109753953B (en) | Method and device for positioning text in image, electronic equipment and storage medium | |
| CN103336954B (en) | A kind of TV station symbol recognition method and apparatus in video | |
| Goyal et al. | Sign language recognition system for deaf and dumb people | |
| CN102426647B (en) | Station identification method and device | |
| CN103020650B (en) | Station caption identifying method and device | |
| US11699283B2 (en) | System and method for finding and classifying lines in an image with a vision system | |
| CN111144366A (en) | Strange face clustering method based on joint face quality assessment | |
| CN105631486A (en) | image character recognition method and device | |
| CN106875408B (en) | Screenshot method and device and terminal equipment | |
| CN102436575A (en) | Method for automatically detecting and classifying station captions | |
| CN103295009B (en) | Based on the license plate character recognition method of Stroke decomposition | |
| CN109947273B (en) | Point reading positioning method and device | |
| CN109255802B (en) | Pedestrian tracking method, device, computer equipment and storage medium | |
| JP2014041486A (en) | Signal processing method and signal processing apparatus | |
| CN103198311A (en) | Method and apparatus for recognizing a character based on a photographed image | |
| US11881015B2 (en) | High-precision identification method and system for substations | |
| US20240078801A1 (en) | System and method for finding and classifying lines in an image with a vision system | |
| US9117132B2 (en) | System and method facilitating designing of classifier while recognizing characters in a video | |
| CN110555349A (en) | working time length statistical method and device | |
| KR20240058827A (en) | System and method for finding and classifying lines in an image with a vision system | |
| CN112052702A (en) | Method and device for identifying two-dimensional code | |
| CN113012189B (en) | Image recognition method, device, computer equipment and storage medium | |
| CN112907206B (en) | Business auditing method, device and equipment based on video object identification | |
| CN104598289A (en) | Recognition method and electronic device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170905 |
|
| RJ01 | Rejection of invention patent application after publication |