CN104751159B - Video coloured silk field detection method and device - Google Patents
Video coloured silk field detection method and device Download PDFInfo
- Publication number
- CN104751159B CN104751159B CN201510013131.8A CN201510013131A CN104751159B CN 104751159 B CN104751159 B CN 104751159B CN 201510013131 A CN201510013131 A CN 201510013131A CN 104751159 B CN104751159 B CN 104751159B
- Authority
- CN
- China
- Prior art keywords
- array
- value
- image
- characteristic
- color field
- 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.)
- Active
Links
Landscapes
- Facsimile Image Signal Circuits (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of video coloured silk field detection method and device, wherein, methods described comprises the following steps：Its gray-scale map is extracted from video image to be detected；Grey level histogram calculating is carried out to the gray-scale map, generates intensity histogram diagram data；According to color field characteristic parameter, Regularization calculating is carried out to the intensity histogram diagram data；According to the intensity histogram diagram data after regular and color field characteristic parameter, signature search is carried out；Characteristic according to searching judges whether the video image is color field.Described device includes gray-scale map extraction module, histogram generation module, characteristic extracting module, color field determining module and database, the present invention and effectively reduces data amount of calculation, improves calculating performance, accuracy rate is higher.
Description
Technical field
The invention belongs to field of video image processing, more particularly to a kind of video coloured silk field detection method and device.
Background technology
Color field in TV programme, refer generally to entire image and only include some pixel value, it is it to be presented as entire image
The solid-color image of middle a certain color, such as：Black field refers to the image that entire image is black, and Red Square refers to that entire image is red
The image of color.It may be used to such picture frame typically during program making, such as：Blueness used in video keying
Background, green background etc..
When formal program broadcasts, it is impossible to color field picture as appearance, therefore when formal program broadcasts, it is necessary to broadcasting
The video content gone out is detected, and avoids the broadcast of color field picture.Video coloured silk field detection method is many in the prior art, substantially all
It is the method using signal colour fidelity analysis.Although signal colour fidelity analysis mode is flexible, be capable of detecting when be what color color field,
But data is computationally intensive, so efficiency is very low.
The content of the invention
The technical problem to be solved in the present invention is, there is provided a kind of video coloured silk field detection method and device, is ensureing video
While the accuracy rate of color field detection, amount of calculation is reduced, improves detection efficiency.
According to an aspect of the present invention, the present invention provides a kind of video coloured silk field detection method, wherein, including following step
Suddenly：
Its gray-scale map is extracted from video image to be detected；
Grey level histogram calculating is carried out to the gray-scale map, generates intensity histogram diagram data；
According to color field characteristic parameter, Regularization calculating is carried out to the intensity histogram diagram data；
According to the intensity histogram diagram data after regular and color field characteristic parameter, signature search is carried out；
Characteristic according to searching judges whether the video image is color field.
Preferably, in above-mentioned video coloured silk field detection method, grey level histogram calculating, generation ash are carried out to the gray-scale map
The detailed process for spending histogram data is as follows：
The pixel value of gray-scale map is subjected to distribution calculating according to 0 to 255 gray level, formed one 0 to 255 one-dimensional the
One array, the value of each array element are the number that the element corresponding grey scale level occurs in gray level image.
Preferably, in above-mentioned video coloured silk field detection method, according to color field characteristic parameter, to the intensity histogram diagram data
The detailed process for carrying out Regularization calculating is as follows：
The value of each array element of the first array and the size of given parameters value are respectively compared, will be greater than given parameters value
Array element form the second array；
Each element value for being respectively compared in the second array falls with predetermined grey level range interior element value in the first array
Poor ratio；
Value of the drop in the range of this than all array elements less than predetermined value is superimposed together, forms the 3rd array,
The array element value being applied is set to 0.
Preferably, in above-mentioned video coloured silk field detection method, the span of the given parameters value for image it is wide × figure
Image height/2~image is wide × and image is high.
Preferably, in above-mentioned video coloured silk field detection method, the predetermined grey level range is 6.
Preferably, in above-mentioned video coloured silk field detection method, according to the intensity histogram diagram data after regular and color field feature
Parameter, signature search is carried out, is comprised the following steps：
Binary conversion treatment is carried out to the element of the 3rd array, the array element higher than given threshold value is characterized data,
And the element value of characteristic is calculated relative to the accounting of entire image pixel.
Preferably, in above-mentioned video coloured silk field detection method, judge that the video image is according to the characteristic searched
No is that color field is specific as follows：
Whether the quantity for judging the characteristic is one, if one, judge the characteristic accounting whether
In the range of given color field feature threshold values, if described image to be detected is color field picture；If the quantity of characteristic
Be not one, or characteristic accounting not in the range of given color field feature threshold values, then described image to be detected is not color field
Image.
Preferably, in above-mentioned video coloured silk field detection method, when carrying out binary conversion treatment, the scope of the given threshold value
Be image it is wide × image height × 0.8~image is wide × image is high；
When whether the accounting of the characteristic is in the range of given color field feature threshold values, the color field feature
Threshold range is 0.99-1.
According to another aspect of the present invention, the present invention provides a kind of video coloured silk field detection means for preceding method, its
In, including：
Gray-scale map extraction module, for extracting gray-scale map from color video frequency image；
Histogram generation module, the gray-scale map that the gray-scale map extraction module is sent is received, the gray-scale map is calculated,
Generate intensity histogram diagram data；
Characteristic extracting module, the intensity histogram diagram data is received, and based on the intensity histogram diagram data, successively
By regular, binary conversion treatment and signature search, characteristic is obtained；
Color field determining module, using the color field feature threshold values range parameter in database and obtained characteristic, judge
Whether the image is color field, and
Database, for storing characteristic parameter.
Preferably, in foregoing video coloured silk field detection means, the intensity histogram diagram data is one-dimensional the of 0 to 255
One array, the value of each array element are the number that the element corresponding grey scale level occurs in gray level image；
The characteristic extracting module also includes：
Regular submodule, carried out to receiving the element value in the first array and the given parameters value obtained from database
Compare, the element that will be greater than given parameters value forms the second array；
Submodule is superimposed, in each element value being respectively compared in the second array and the first array in predetermined grey level range
The drop ratio of element value；Value of the drop in the range of this than all array elements less than predetermined value is superimposed together, forms the
Three arrays, the array element value being applied are set to 0；
Characteristic element searches for submodule, binary conversion treatment is carried out to the element of the 3rd array, higher than given threshold value
Array element is characterized data..
By the invention described above provide specific embodiment it can be seen from just because of will to the color field of entire image detect
Calculate the detection being transformed to the image grey level histogram to calculate, effectively reduce the amount of calculation of data, greatly improve calculating
Performance.Distribution characteristics according to the constitutive characteristic and color field pixel of color field picture on the histogram simultaneously, by color field feature
It is amplified, filters, retrieves, the histogram element data for making to meet color field feature becomes apparent from, special finally by these are calculated
Data are levied to judge whether the image is color field picture so that accuracy rate also improves a lot.
Brief description of the drawings
By the description to the embodiment of the present invention referring to the drawings, above-mentioned and other purposes of the invention, feature and
Advantage will be apparent from, in the accompanying drawings：
Fig. 1 illustrates for normal picture grey level histogram；
Fig. 2 is that the grey level histogram of color field picture is illustrated；
Fig. 3 is video coloured silk field detection method flow chart provided by the invention；
Fig. 4 is video coloured silk field detection means principle schematic provided by the invention.
Embodiment
Various embodiments of the present invention are more fully described hereinafter with reference to accompanying drawing.In various figures, identical element
Represented using same or similar reference.For the sake of clarity, the various pieces in accompanying drawing are not necessarily to scale.
Fig. 1 illustrates for normal picture grey level histogram, and Fig. 2 is that the grey level histogram of color field picture is illustrated, and compares the two
Schematic diagram understands that the grey level histogram of color field picture and the grey level histogram of normal picture are entirely different in distribution, and feature shows
Write.The present invention is exactly that make use of the feature, there is provided a kind of video coloured silk field detection method and device.
Embodiment one
As shown in figure 3, it is video coloured silk field detection method flow chart.Including：
Step S101：A width video image is received from upper layer application, such as the wide of the image is 720 pixels, height is 576 pictures
Element, extract the gray-scale map of the image.
Step S102：Grey level histogram calculating is carried out to the gray-scale map of described image, generates intensity histogram diagram data.It is described
Intensity histogram diagram data for 0-255 one-dimension array.
The calculating of grey level histogram is specially：
The pixel value of gray-scale map is subjected to distribution calculating according to 0 to 255 gray level, forms a dimension of one 0 to 255
Group, to show the difference with other following arrays, the first array is named as herein.In first array, the member in each array
Element includes two parameters of element value and index number, and index number represents the element corresponding gray level, element in gray-scale map
It is worth the number occurred for the gray level in gray level image.
The one-dimension array example of grey level histogram is as shown in table 1 below：
Table 1.
| 4146060 | 01 | 222 | 03 | 584 | 05 | 06 | 347 | 08 | 09 | ... | ... | 025 5 |
In the array of the above first：Subscript 0-255 represents totally 256 gray levels from 0 to 255, and the value in square frame is the gray scale
The number that level occurs in gray level image, such as：0 gray level occurs 414606 times, and 1 gray level occurs 0 time.
Step S103：Regularization calculating is carried out to the intensity histogram diagram data using color field characteristic parameter.
The effect of Regularization in this step is the pixel element for filtering out high frequency distribution, in order to increase the accurate of judgement
Property, by strengthening the intensity of these pixel elements, make its advantageously embodiment in color field feature.Regularization process is specially：
First in intensity histogram diagram data, according to given parameters, (it is a color field characteristic parameter, represents certain pixel elements
The number that element occurs in the images), it is respectively compared the element value of each element of the array of the above first and the given parameters
The size of value, the array element that will be greater than given parameters value form the second array.When time that certain element occurs in piece image
When number is higher than given parameters, the image is possible to as color field, the element of a number of high frequency distribution for meeting the parameter of searching.
Wherein, the span of the given parameters value be image it is wide × image height/2-image is wide × image height.Such as with
Exemplified by image 720 × 576, foregoing given parameters value is between (720 × 576)/2 to 720 × 576, then be exactly 207360 to
Between 414720.
By taking above-mentioned table 1 as an example, when given parameters are 207360, the second array obtained more afterwards is as shown in table 2 below：
Table 2.
| 4146060 |
By the contrast of table 1 and table 2, after to histogram data Regularization, the number of array element is only remaining
One., may be multiple in other embodiment, but quantity will greatly reduce.
Then, in order to strengthen the feature of element, it is interior with predetermined grey level range (such as 6 gray levels) that the element is calculated first
The drop ratio of element value, determine that than the element less than some threshold values, the element value of element of the element value with obtaining is folded for drop
Add.So, a characteristic element array is obtained.
For example, given range is set into 6 gray levels, drop is set to 50 than threshold values, in table 1, by the element of 0 gray level
The element value of value 414606 and adjacent 6 gray levels：The 0 of first gray level, the 22 of the second gray level, the 0 of the 3rd gray level,
The 58 of 4th gray level, the 0 of the 5th gray level, the 0 of the 6th gray level compares, and comparative result is respectively 414606,412584,
414606,414548,414606 and 414606, wherein, all comparative results are both greater than drop than threshold values 50, thus need not
It is overlapped.
Wherein, drop is a changing value than threshold values, can artificially be adjusted according to factors such as image sizes.
When carrying out drop than calculating, given range is set to 6 gray levels.Where calculative second array element
When gray level is 0, then, it is necessary to which the array range for superposition is 1,2,3,4,5,6 in the first array；If when 1, then
0,2,3,4,5,6；If when 2, then 0,1,3,4,5,6；If when 3, then 0,1,2,4,5,6；If when 255, then
254,253,252,251,250,249；If when 254, then 255,253,252,251,250,249；If when 253, then
255,254,252,251,250,249；If when 252, then 255,254,253,251,250,249；If other gray scales
The element of level, if representing gray level where the second array element with x, then, it is necessary to number for superposition in the first array
Group scope is then x-3, x-2, x-1, x+1, x+2, x+3.
Step S104：Using color field characteristic parameter, searched in the regular result of grey level histogram (array i.e. shown in table 2)
Meet the characteristic of color field feature.Specially：
The histogram element less than given threshold value is filtered out first with binary conversion treatment, to the element higher than the threshold values,
Accounting of its value relative to entire image pixel is calculated, when the ratio is more than some threshold values, it is believed that this feature element data is
One color field characteristic.Wherein, the scope of given threshold value described here can × image wide from image it is high × 0.8 wide to image
× image is high.In the present embodiment, 720 × 576 × 0.8=331776 is taken.
When given threshold value is 331776, the element in the regular result of grey level histogram is compared with 331776 respectively,
The element that element value is less than 331776 is got rid of, therefore, after two-value is handled, obtains characteristic array.In the present embodiment
In, only have an element in table 2, and it is 331776 that its value 414606, which is more than given threshold value,.Therefore, the element is characteristic
According to.
Next, using color field characteristic parameter and searching out the color field characteristic come, judge whether the image is color field
Image.
Step S105：Judge whether the quantity for searching out the characteristic element come is equal to one, if it is not, then in step
S109 determines that the image is not color field picture.
If the quantity of characteristic element is equal to one, in step S106, the accounting of the element, i.e. characteristic element value/figure are calculated
Image width × image is high.In the present embodiment, accounting is 414606/720 × 576 ≈ 0.9997.
Step S107, judges whether accounting is more than 0.99, if greater than 0.99, then determines that the image is color in step S108
Field picture.If no more than 0.99, i.e., less than 0.99, then determine that the image is not color field picture in step S109.
In the present embodiment, an only characteristic element, and its accounting is about 0.9997, more than 0.99, thus can sentence
The disconnected image is color field picture.
By the above method, the detection being transformed to the image grey level histogram will be calculated to the detection of the color field of entire image
Calculate, calculating data volume is effectively reduced, so as to greatly improve calculating performance.The present invention is simultaneously according to the composition of color field picture
Feature and these distribution characteristics of color field pixel on the histogram, by being amplified, filtering, retrieving to color field feature, make symbol
The histogram element data for closing color field feature becomes apparent from, and determines whether color field finally by these characteristics are calculated,
So that accuracy rate also accordingly improves.
Embodiment two
Present invention also offers a kind of color field detection means, as shown in figure 4, including：Gray-scale map extraction module 10, histogram
Generation module 20, characteristic extracting module 30, color field determining module 40 and database 50.Whether video image is detected by the device
In the presence of color field picture.
Gray-scale map extraction module 10 extracts the gray-scale map of the image from the video image received.Wherein, the video
The wide of image is 1920 pixels, and height is 1080 pixels.
The gray-scale map that histogram generation module 20 obtains to foregoing gray-scale map extraction module calculates, and generates intensity histogram
Diagram data.The first array i.e. shown in table 3.
Table 3：
| 00 | ... | 0122 | 1078000123 | 990300124 | 0125 | 5300126 | 0127 | 08 | ... | 0255 |
Characteristic extracting module 30 also includes regular submodule 301, superposition submodule 302 and characteristic element search submodule
303.After histogram generation module 20 generates intensity histogram diagram data, first, regular submodule 301 is to grey level histogram number
According to Regularization calculating is carried out, detailed process is as follows.
Regular submodule 301 takes a given parameters from database 50, is set as 1920 × 1080/ according to the size of image
2=1036800.By the element value of the first array in table 3 compared with the value.By comparing, only the 123rd gray level
Element value is more than the setup parameter, so as to obtain the second array, i.e. table 4.
Table 4：
| 1078000123 |
Element of the submodule 302 in table 4 is superimposed, calculates the drop ratio of 6 elements near it.According to embodiment one
Middle offer is used to determine method of the progress drop than the element of calculating, i.e., gray level where representing the second array element with x, needs
The array range for being used to be superimposed is then x-3, x-2, x-1, x+1, x+2, x+3.In the present embodiment, x=123, it is therefore desirable to
It is 120 grades, 121 grades, 122 grades, 124 grades, 125 grades and 126 grades that drop, which is carried out, than the element of calculating.When by the 123rd grade of element
When value is compared with the element value of these gray levels, respectively obtain：1078000、1078000、1078000、87700、
1078000、1072700。
Superposition submodule 302 takes out drop from database 50, and than threshold value 200000, (it is artificial for the size according to image
The value of setting), and by above-mentioned numerical value compared with drop is than threshold value 200000.By comparing, only 124 grades of comparative result
Less than the threshold value, therefore, this grade of element value is added to 123 grades up, obtains the 3rd array, be i.e. table 3 is changed into table 5：
Table 5：
| 00 | ... | 0122 | 2068300123 | 0124 | 0125 | 5300126 | 0127 | 08 | ... | 0255 |
Table 4 is changed into table 6：
Table 6：
| 2068300123 |
When obtaining the 3rd array, i.e., after table 6, characteristic element search module 303 enters the element in table 6 with binary-state threshold
Row compare, binary-state threshold be image it is wide × image height × 0.8=1920 × 1080 × 0.8=1658880.In the present embodiment
In, it is clear that 2068300 are more than 1658880, thus determine that the element is characterized element.
The characteristic element that color field determining module 40 is obtained by judging characteristic element search module 303 usually determines that the image is
No is color field picture.
Whether the number for determining characteristic element first is one.When for one when, then calculate the accounting of the element.This implementation
In example, there was only an element in table 6, its accounting is 2068300/2073600 ≈ 0.9974.The accounting is more than 0.99, therefore, really
The fixed image is color field.
Embodiment three
In the present embodiment, the device shown in embodiment two and the method shown in embodiment one are taken, video image is entered
Row detection.Due to having been carried out describing in detail to described device and method in embodiment one and two, simplify in the present embodiment and say
It is bright.
A width of 704 pixel of video image, a height of 576 pixel.The gray-scale map of the image is extracted first, then carries out Nogata
Figure calculates.It is as shown in table 7 to obtain one-dimension array：
Table 7：
| 121000 | 80201 | 200002 | 03 | 160504 | 42005 | 1602406 | ... | 82200255 |
Then by above element value compared with 704 × 576/2=202752 of given parameters, none of element
Value is more than the given parameters, therefore, without qualified element.Due to can not find qualified element, it is not necessary to carry out
Drop is than calculating, without the calculating of binary conversion treatment and accounting.Due to not being equal to 1 element, it is possible to determine the figure
As being not color field picture.
According to embodiments of the invention as described above, these embodiments do not have all details of detailed descriptionthe, not yet
It is only described specific embodiment to limit the invention.Obviously, as described above, can make many modifications and variations.This explanation
Book is chosen and specifically describes these embodiments, is in order to preferably explain the principle and practical application of the present invention, so that affiliated
Technical field technical staff can be used using modification of the invention and on the basis of the present invention well.The protection model of the present invention
Enclosing should be defined by the scope that the claims in the present invention are defined.
Claims (7)
1. a kind of video coloured silk field detection method, wherein, comprise the following steps：
Its gray-scale map is extracted from video image to be detected；
Grey level histogram calculating is carried out to the gray-scale map, generates intensity histogram diagram data；
According to color field characteristic parameter, Regularization calculating is carried out to the intensity histogram diagram data；
According to the intensity histogram diagram data after regular and color field characteristic parameter, signature search is carried out；
Characteristic according to searching judges whether the video image is color field,
Wherein, grey level histogram calculating is carried out to the gray-scale map, the detailed process for generating intensity histogram diagram data is as follows：
The pixel value of gray-scale map is subjected to distribution calculating according to 0 to 255 gray level, forms one-dimensional first number of one 0 to 255
Group, the value of each array element are the number that the element corresponding grey scale level occurs in gray level image；
According to color field characteristic parameter, the process that Regularization calculating is carried out to the intensity histogram diagram data is specific as follows：
The value of each array element of the first array and the size of given parameters value are respectively compared, will be greater than the number of given parameters value
Constituent element element the second array of composition；
The drop ratio of predetermined grey level range interior element value in each element value being respectively compared in the second array and the first array；
Value of the drop in the range of this than all array elements less than predetermined value is superimposed together, the 3rd array is formed, is folded
The array element value added is set to 0.
2. video coloured silk field detection method as claimed in claim 1, wherein, the span of the given parameters value is wide for image
× image height/2~image is wide × and image is high.
3. video coloured silk field detection method as claimed in claim 1, wherein, the predetermined grey level range is 6.
4. video coloured silk field detection method as claimed in claim 1, wherein, according to the intensity histogram diagram data after regular and color field
Characteristic parameter, signature search is carried out, is comprised the following steps：
Binary conversion treatment is carried out to the element of the 3rd array, the array element higher than given threshold value is characterized data, and counts
The element value of characteristic is calculated relative to the accounting of entire image pixel.
5. video coloured silk field detection method as claimed in claim 4, wherein, the video figure is judged according to the characteristic searched
Seem it is no for color field it is specific as follows：
Judge the quantity and accounting of the characteristic, if quantity is one, and accounting is in given color field feature threshold range
Interior, described image to be detected is color field picture；If the quantity of characteristic is not one, or the accounting of characteristic is not giving
Color field feature threshold values in the range of, then described image to be detected is not color field picture.
6. video coloured silk field detection method as claimed in claim 4, wherein, when carrying out binary conversion treatment, the given threshold value
Scope be image it is wide × image height × 0.8~image is wide × image is high；
When whether the accounting of the characteristic is in the range of given color field feature threshold values, the color field feature threshold values
Scope is 0.99-1.
7. a kind of video coloured silk field detection means for being used to realize any methods describeds of claim 1-6, wherein, including：
Gray-scale map extraction module, for extracting gray-scale map from color video frequency image；
Histogram generation module, the gray-scale map that the gray-scale map extraction module is sent is received, the gray-scale map is calculated, generation
Intensity histogram diagram data；
Characteristic extracting module, the intensity histogram diagram data is received, and based on the intensity histogram diagram data, passed through successively
Regular, binary conversion treatment and signature search, obtain characteristic；
Color field determining module, using the color field feature threshold values range parameter in database and obtained characteristic, judge the figure
Seem it is no be color field picture, and
Database, for storing characteristic parameter,
Wherein, the intensity histogram diagram data is 0 to 255 one-dimensional first array, and the value of each array element is the element pair
Answer the number that gray level occurs in gray level image；
The characteristic extracting module also includes：
Regular submodule, the given parameters value for receiving the element value in the first array and being obtained from database is compared
Compared with the element that will be greater than given parameters value forms the second array；
Submodule is superimposed, predetermined grey level range interior element in each element value being respectively compared in the second array and the first array
The drop ratio of value；Value of the drop in the range of this than all array elements less than predetermined value is superimposed together, forms the 3rd number
Group, the array element value being applied are set to 0；
Characteristic element searches for submodule, binary conversion treatment is carried out to the element of the 3rd array, higher than the array of given threshold value
Element is characterized data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510013131.8A CN104751159B (en) | 2015-01-09 | 2015-01-09 | Video coloured silk field detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510013131.8A CN104751159B (en) | 2015-01-09 | 2015-01-09 | Video coloured silk field detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104751159A CN104751159A (en) | 2015-07-01 |
| CN104751159B true CN104751159B (en) | 2018-03-13 |
Family
ID=53590815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510013131.8A Active CN104751159B (en) | 2015-01-09 | 2015-01-09 | Video coloured silk field detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104751159B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113378633A (en) * | 2021-04-30 | 2021-09-10 | 成都东方盛行电子有限责任公司 | Method and system for detecting quality of streaming media signal |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101500177A (en) * | 2009-02-20 | 2009-08-05 | 重庆市计量质量检测研究院 | Video monitoring system detection method and apparatus thereof |
| CN101815222A (en) * | 2009-02-25 | 2010-08-25 | 北大方正集团有限公司 | Video color bar detecting method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009147730A (en) * | 2007-12-14 | 2009-07-02 | Fujifilm Corp | Moving image generating apparatus, moving image shooting apparatus, moving image generating method, and program |
-
2015
- 2015-01-09 CN CN201510013131.8A patent/CN104751159B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101500177A (en) * | 2009-02-20 | 2009-08-05 | 重庆市计量质量检测研究院 | Video monitoring system detection method and apparatus thereof |
| CN101815222A (en) * | 2009-02-25 | 2010-08-25 | 北大方正集团有限公司 | Video color bar detecting method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104751159A (en) | 2015-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104966085B (en) | A kind of remote sensing images region of interest area detecting method based on the fusion of more notable features | |
| CN111274865A (en) | Remote sensing image cloud detection method and device based on full convolution neural network | |
| CN103778636B (en) | A kind of feature construction method for non-reference picture quality appraisement | |
| CN106548169B (en) | Fuzzy literal Enhancement Method and device based on deep neural network | |
| Pei et al. | The improved wavelet transform based image fusion algorithm and the quality assessment | |
| Jin et al. | Perceptual image quality assessment using block-based multi-metric fusion (BMMF) | |
| CN111597933B (en) | Face recognition method and device | |
| CN106203454A (en) | The method and device that certificate format is analyzed | |
| CN105374047B (en) | SAR image change detection based on improved bilateral filtering with cluster | |
| CN113160239B (en) | Illegal land detection method and device | |
| CN113538603B (en) | Optical detection method and system based on array product and readable storage medium | |
| CN108038839A (en) | Twisted-pair feeder lay real-time detection method on a kind of flow production line | |
| CN104021567B (en) | Based on the fuzzy altering detecting method of image Gauss of first numeral law | |
| CN106780446A (en) | It is a kind of to mix distorted image quality evaluating method without reference | |
| CN106934770A (en) | A kind of method and apparatus for evaluating haze image defog effect | |
| CN106327531A (en) | Panorama video identification method and device, and video playing method and device | |
| CN106331848A (en) | Panoramic video identification method and device, and video playing method and device | |
| CN106683074B (en) | A kind of distorted image detection method based on haze characteristic | |
| CN107665347A (en) | Vision significance object detection method based on filtering optimization | |
| CN109461136B (en) | Method for detecting fiber distribution condition in mixed fiber product | |
| CN104751159B (en) | Video coloured silk field detection method and device | |
| CN111738310B (en) | Material classification method, device, electronic equipment and storage medium | |
| CN105868680A (en) | Channel logo classification method and apparatus | |
| CN114005020B (en) | Designated moving target detection method based on M3-YOLOv5 | |
| Zhang et al. | The modified gradient edge detection method for the color filter array image of the CMOS image sensor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |