CN107274456A - A kind of recognition methods of picture format and device - Google Patents
A kind of recognition methods of picture format and device Download PDFInfo
- Publication number
- CN107274456A CN107274456A CN201710317564.1A CN201710317564A CN107274456A CN 107274456 A CN107274456 A CN 107274456A CN 201710317564 A CN201710317564 A CN 201710317564A CN 107274456 A CN107274456 A CN 107274456A
- Authority
- CN
- China
- Prior art keywords
- pixel
- gathering line
- image
- value
- region
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000009466 transformation Effects 0.000 claims abstract description 34
- 238000005070 sampling Methods 0.000 claims abstract description 15
- 238000006243 chemical reaction Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 9
- 230000008859 change Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G06T3/08—
Abstract
The embodiment of the invention discloses a kind of recognition methods of picture format and device.Wherein method includes:Images to be recognized is obtained, wherein the images to be recognized includes the first image-region and the second image-region;The pixel gathering line of predetermined number is determined in each image-region according to default sampling rule, the pixel gathering line in described first image region and the pixel gathering line of second image-region meet the predeterminated position rule of correspondence;According to the pixel information of correspondence position pixel gathering line in each image-region, determine whether the images to be recognized meets three-dimensional format transformation;If so, the images to be recognized then is carried out into three-dimensional conversion process.The embodiment of the present invention is solved needs the problem of user is by naked eyes identification picture format in the prior art, realizes automatic identification picture format, improves picture format recognition accuracy, reduces user's operation, improve Consumer's Experience.
Description
Technical field
The present embodiments relate to recognition methods and the device of image recognition technology, more particularly to a kind of picture format.
Background technology
With the gradually development of 3D (Three Dimensions, three-dimensional) imaging technique, virtual reality device or bore hole
3D equipment etc. is just gradual to be entered in the life and work of people.
Two images that are similar and differing of the same object obtained from two different visual angles, above-mentioned two image or so
Or it is setting up and down, SBS (Side-By-Side) format-pattern is formed, by the left and right of SBS format-patterns or up and down two figures
Three-dimensional stereo effect can be formed as overlapping., can be automatically by labeled as the image file of SBS forms in current bore hole 3D equipment
Or video file is converted to 3D stereo-pictures or video.
But, for unmarked image file or video file, tray is determined usually in the following way
Formula:User identifies whether to be SBS forms by naked eyes, and is manually operated conversion three-dimensional stereo effect.Manual identified increase
Extra operation, reduces Consumer's Experience.
The content of the invention
The present invention provides recognition methods and the device of a kind of picture format, to realize that highly accurately fast automatic identification is schemed
As form.
In a first aspect, the embodiments of the invention provide a kind of recognition methods of picture format, this method includes:
Images to be recognized is obtained, wherein the images to be recognized includes the first image-region and the second image-region;
The pixel gathering line of predetermined number, described first image area are determined in each image-region according to default sampling rule
The pixel gathering line in domain and the pixel gathering line of second image-region meet the predeterminated position rule of correspondence;
According to the pixel information of correspondence position pixel gathering line in each image-region, the images to be recognized is determined
Whether three-dimensional format transformation is met;
If so, the images to be recognized then is carried out into three-dimensional conversion process.
Further, the pixel gathering line of predetermined number is determined in each image-region according to default sampling rule, including:
The pixel gathering line is determined according to the predetermined number of the type of the pixel gathering line and the pixel gathering line
Position, the type of the pixel gathering line includes row gathering line and row gathering line, and each pixel gathering line is uniformly distributed in
In each image-region.
Further, the pixel gathering line is one of position row pixel or row pixel in each image-region
Half.
Further, the pixel information in correspondence position pixel gathering line in each image-region, determines institute
State whether images to be recognized meets three-dimensional format transformation, including:
Obtain the average brightness value of each pixel in correspondence position pixel gathering line in each image-region;
Determine the similar value of the average brightness value of correspondence position pixel gathering line in each image-region;
The similar levels of the correspondence position pixel gathering line are determined to presetting similar threshold values according to the similar value;
Determine whether the images to be recognized meets three-dimensional format transformation according to the similar levels of each pixel gathering line.
Further, the similar levels of the pixel gathering line, bag are determined to presetting similar threshold values according to the similar value
Include:
If the similar value is more than the maximum for presetting similar threshold values, it is determined that the correspondence position pixel gathering line
Similar levels be the first similar levels, and labeled as the first numerical value;
If the similar value is preset in similar threshold values described, it is determined that the correspondence position pixel gathering line it is similar etc.
Level is the second similar levels, and labeled as second value;
If the similar value is less than the minimum value for presetting similar threshold values, it is determined that the correspondence position pixel gathering line
Similar levels for third phase like grade, and be labeled as third value;
Wherein, first similar levels, second similar levels and the third phase are reduced successively like grade, described
First numerical value, the second value and the third value are sequentially reduced.
Further, determine whether the images to be recognized meets three-dimensional according to the similar levels of each pixel gathering line
Format transformation, including:
Determine the corresponding tag value of the similar levels and value of correspondence position pixel gathering line in each image-region;
Described and value and predetermined threshold value are compared, determine whether the images to be recognized meets three according to comparison result
Tie up format transformation.
Second aspect, the embodiment of the present invention additionally provides a kind of identifying device of picture format, and the device includes:
Image acquiring device, for obtaining images to be recognized, wherein the images to be recognized include the first image-region and
Second image-region;
Pixel gathering line determining module, the picture for determining predetermined number in each image-region according to default sampling rule
The pixel gathering line of plain gathering line, the pixel gathering line in described first image region and second image-region meets default position
Put the rule of correspondence;
Image judge module, for the pixel information according to correspondence position pixel gathering line in each image-region,
Determine whether the images to be recognized meets three-dimensional format transformation;
Image processing module, if three-dimensional format transformation is met for the images to be recognized, by the images to be recognized
Carry out three-dimensional conversion process.
Further, the pixel gathering line determining module specifically for:
The pixel gathering line is determined according to the predetermined number of the type of the pixel gathering line and the pixel gathering line
Position, the type of the pixel gathering line includes row gathering line and row gathering line, and each pixel gathering line is uniformly distributed in
In each image-region.
Further, the pixel gathering line is one of position row pixel or row pixel in each image-region
Half.
Further, described image judge module includes:
Brightness value determining unit, for obtaining in each image-region each pixel in correspondence position pixel gathering line
Average brightness value;
Similar value determining unit, for determining the described average bright of correspondence position pixel gathering line in each image-region
The similar value of angle value;
Similar levels determining unit, for determining the correspondence position pixel to presetting similar threshold values according to the similar value
The similar levels of gathering line;
Image judging unit, for whether determining the images to be recognized according to the similar levels of each pixel gathering line
Meet three-dimensional format transformation.
Further, the similar levels determining unit specifically for:
If the similar value is more than the maximum for presetting similar threshold values, it is determined that the correspondence position pixel gathering line
Similar levels be the first similar levels, and labeled as the first numerical value;If the similar value is preset in similar threshold values described,
The similar levels for determining the correspondence position pixel gathering line are the second similar levels, and labeled as second value;If the phase
It is less than the minimum value for presetting similar threshold values like value, it is determined that the similar levels of the correspondence position pixel gathering line are the 3rd
Similar levels, and labeled as third value;Wherein, first similar levels, second similar levels and the third phase
Reduced successively like grade, first numerical value, the second value and the third value are sequentially reduced.
Further, described image judging unit specifically for:
Determine the corresponding tag value of the similar levels and value of correspondence position pixel gathering line in each image-region;
Described and value and predetermined threshold value are compared, determine whether the images to be recognized meets three-dimensional conversion lattice according to comparison result
Formula.
The embodiment of the present invention in each image-region according to default sampling rule by determining that the pixel of predetermined number is gathered
Line, and according to the pixel information of correspondence position pixel gathering line in each image-region, determine whether images to be recognized meets three
Format transformation is tieed up, the situation for needing user to recognize picture format by naked eyes in the prior art is solved, realizes automatic identification
Picture format, improves picture format recognition accuracy, reduces user's operation, improves Consumer's Experience.
Brief description of the drawings
Fig. 1 is a kind of flow chart of the recognition methods for picture format that the embodiment of the present invention one is provided;
Fig. 2 is the schematic diagram of the pixel gathering line for the images to be recognized that the embodiment of the present invention one is provided;
Fig. 3 is the schematic diagram of the images to be recognized for the left-right format distribution that the embodiment of the present invention one is provided;
Fig. 4 is a kind of flow chart of the recognition methods for picture format that the embodiment of the present invention two is provided;
Fig. 5 is a kind of structural representation of the identifying device for picture format that the embodiment of the present invention three is provided.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that, in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 is a kind of flow chart of the recognition methods for picture format that the embodiment of the present invention one is provided, and the present embodiment can be fitted
For quickly recognizing whether image meets three-dimensional format transformation situation, this method can be by image pane provided in an embodiment of the present invention
The identifying device of formula is performed, and the device can be realized by the way of software and/or hardware, and the device can be integrated in three-dimensional
In the terminal of imaging function, terminal is such as can be the smart mobile phone with 3D functions, computer or DTV.Referring to figure
1, this method is specifically included:
S110, acquisition images to be recognized, wherein images to be recognized include the first image-region and the second image-region.
In the present embodiment, images to be recognized be in the image comprising two image-regions, each image-region independently
Piece image is shown, wherein the first image-region and the second image-region can be left-right format distribution or lattice up and down
Formula is distributed.Optionally, images to be recognized can be still image, can be the two field picture intercepted in video.
S120, the pixel gathering line according to default sampling rule determination predetermined number in each image-region, the first image
The pixel gathering line in region meets the predeterminated position rule of correspondence with the pixel gathering line of the second image-region.
In the present embodiment, according to it is default sampling rule collection pixel be located at predetermined number straight line on, each by
The straight line of pixel composition is referred to as pixel gathering line, and wherein predetermined number can be default fixed qty, such as predetermined number
Can be 3, predetermined number can also be that the resolution ratio of the image according to each image-region is determined, exemplary, can be with
It is that images to be recognized is divided into by different images grade according to image resolution ratio, resolution ratio is higher, and image gradation is higher, and pixel is adopted
The quantity of line concentration is bigger, it is to avoid when resolution ratio increases, and the quantity of pixel gathering line is too small to be caused to detect accuracy reduction
Problem.
In the present embodiment, the first image-region is identical with the pixel gathering line quantity of the second image-region, and meets default
The position rule of correspondence, wherein the predeterminated position rule of correspondence can be row pixel to the first image-region and the second image-region and
Row pixel sets numbering, and the first image-region pixel gathering line corresponding with the second image-region is located at respectively has identical compile
Number row pixel or row pixel on.
Optionally, the position of pixel gathering line is determined according to the predetermined number of the type of pixel gathering line and pixel gathering line
Put, the type of pixel gathering line includes row gathering line and row gathering line, and each pixel gathering line is uniformly distributed in each image-region.
Optionally, pixel gathering line can be entire row of pixels or column of pixels, according to user's request and/or can also treat
Identification image type entire row of pixels or column of pixels are intercepted, it is exemplary, pixel gathering line can be pixel or
1/3,2/3,1/2 etc. of person's column of pixels.In the present embodiment, the default regular type referred to according to pixel gathering line of sampling,
The predetermined number of pixel gathering line determines to be uniformly distributed in the pixel gathering line of each image-region.Exemplary, referring to Fig. 2, Fig. 2
It is the schematic diagram of the pixel gathering line for the images to be recognized that the embodiment of the present invention one is provided.If the type of gathering line gathers for row
Line, the quantity of pixel gathering line is 3, and the row pixel quantity that each image-region is included is 1024, then can determine that each image-region
Pixel gathering line is located in the row pixel that numbering is 256,512 and 768.
It is preferred that, if each image-region is distributed for left-right format, pixel gathering line type is row gathering line, if each image
Region is distributed for top-down format, then pixel gathering line type is row gathering line.In the present embodiment, the figure shown in each image-region
Situation as there may be local display, exemplary, referring to Fig. 3, Fig. 3 is the left-right format point that the embodiment of the present invention one is provided
Each image-region is distributed for left-right format in the schematic diagram of the images to be recognized of cloth, Fig. 3, and display image is not filled in each image-region
Be present background in full image-region, the top and the bottom of display image, if pixel gathering line is row gathering line, wrapped in pixel gathering line
Containing a large amount of background pixel points, cause the effective pixel points quantity of the display image included in each pixel gathering line to reduce, reduce picture
The degree of accuracy of plain gathering line.If pixel gathering line is row gathering line, the number of effective pixel points in each pixel gathering line can be improved
Amount.Similarly, if each image-region is distributed for top-down format, pixel gathering line type is that row gathering line can improve each pixel collection
The quantity of effective pixel points in line.
S130, the pixel information according to correspondence position pixel gathering line in each image-region, determine that images to be recognized is
It is no to meet three-dimensional format transformation.
In the present embodiment, pixel information can be gray value or brightness value of pixel etc..Meet three-dimensional conversion lattice
The image of formula refers to that two images included are the same subject images obtained by two viewpoints, and exemplary, two regard
The distance between point can distance be identical between people's eyes, and two image-regions have higher similarity, and not exclusively
It is identical.
In the present embodiment, by the pixel information for detecting the display image in the first image-region and the second image-region
Determine whether images to be recognized meets three-dimensional format transformation.
In the present embodiment, image to be detected is probably the X-Y scheme that there is fine difference and be unsatisfactory for three-dimensional format transformation
Picture, the similarity of each image-region is detected by the pixel gathering line of predetermined number, it is to avoid adopted by the excessive pixel of quantity
Line concentration, or even whole row pixel or row pixel, when judging two image-region similarities, difference pixel is in whole pixels
In to occupy ratio smaller, cause two image-region similarities too high, produce the situation of detection error.Pass through predetermined number simultaneously
Pixel gathering line detect the similarity of each image-region, reduce amount of calculation, improve the recognition efficiency of picture format
And the degree of accuracy.
In the present embodiment, the pixel gathering line in each image-region is uniformly distributed, and is gathered in each several part of image-region
The pixel of equal proportion, improve the distributive law of the pixel of collection, it is to avoid the random acquisition pixel in each image-region
The situation of block, randomly selected pixel block limitation is big, is easily caused larger detection error.In the image area, have
There is the pixel gathering line of same pixel point quantity compared with pixel block, the image range involved by pixel gathering line is wide, across
Degree is big.Exemplary, referring to Fig. 3, the difference pixel quantity that pixel gathering line is included is more than what is included in pixel block
Difference pixel quantity, detects that images to be recognized form can improve accuracy in detection by pixel gathering line, reduces amount of calculation, carry
High detection efficiency.
If S140, images to be recognized meet three-dimensional format transformation, images to be recognized is subjected to three-dimensional conversion process.
In the present embodiment, if by detecting that the similarity of two image-regions in images to be recognized determines that images to be recognized expires
Foot three-dimensional format transformation, then carry out three-dimensional conversion process by two image-regions, generate three-dimensional image, show user;
If images to be recognized is unsatisfactory for three-dimensional format transformation, two image-regions are showed into user in two dimensional image form.
The technical scheme of the present embodiment, by the picture for determining predetermined number in each image-region according to default sampling rule
Plain gathering line, and according to the pixel information of correspondence position pixel gathering line in each image-region, whether determine images to be recognized
Three-dimensional format transformation is met, solve needs the problem of user is by naked eyes identification picture format in the prior art, realizes certainly
Dynamic identification picture format, improves picture format recognition accuracy, reduces user's operation, improves Consumer's Experience.
On the basis of above-described embodiment, pixel gathering line is position row pixel or row pixel in each image-region
Half.
In the picture or video of daily shooting, there are a large amount of symmetric graph pictures, such as one piece copper coin or one are bloomed
Flower etc., when each image-region in images to be recognized shows Symmetrical Two-dimentional image, collection full line or column of pixels point
The similarity of obtained pixel gathering line is calculated, the pixel gathering line obtained more than collection hemistich or the calculating of half row pixel
Similarity, is also easy to produce detection error.It is preferred that, if pixel gathering line is row pixel, pixel gathering line is be expert at pixel
Left hemistich pixel or right hemistich pixel;If pixel gathering line be row pixel, pixel gathering line for be expert at pixel upper half
Row pixel or lower half row pixel.
In the present embodiment, by obtaining the pixel gathering line of hemistich or half row according to default collection rule, it can exclude pair
Claim two dimensional image, improve the degree of accuracy of picture format identification.
Embodiment two
Fig. 4 is a kind of flow chart of the recognition methods for picture format that the embodiment of the present invention two is provided, in above-described embodiment
On the basis of, it is further to provide the pixel information in correspondence position pixel gathering line in each image-region, it is determined that
The method whether images to be recognized meets three-dimensional format transformation.Accordingly, referring to Fig. 2, this method is specifically included:
S210, acquisition images to be recognized, wherein images to be recognized include the first image-region and the second image-region.
S220, the pixel gathering line according to default sampling rule determination predetermined number in each image-region, the first image
The pixel gathering line in region meets the predeterminated position rule of correspondence with the pixel gathering line of the second image-region.
S230, the average brightness value for obtaining each pixel in correspondence position pixel gathering line in each image-region.
Wherein, the average brightness value of each pixel gathering line brightness value of each pixel in pixel gathering line is determined, specifically
, the brightness value of each pixel can determine that the brightness value of such as pixel can be each picture according to the detection demand of image
The calculation such as the average of red, green, blue triple channel brightness value, weighted average or triple channel brightness maxima appoints in vegetarian refreshments
Meaning is a kind of.
Optionally, step S230, which can also be, obtains in each image-region each pixel in correspondence position pixel gathering line
Average gray value.
In the present embodiment, the brightness value or gray value extracting mode of each pixel are simple, and amount of calculation is small, reduces image
The difficulty of the recognizer of form, improves detection efficiency.
S240, the similar value for determining the average brightness value of correspondence position pixel gathering line in each image-region.
In the present embodiment, determined by the similar value of the pixel gathering line average brightness value of correspondence position in each image-region
The similarity of the pixel gathering line of each correspondence position.Exemplary, referring to Fig. 2, pixel gathering line 101 and 201, pixel gathering line
102 and 202 and pixel gathering line that pixel gathering line 103 and 203 is correspondence position, obtain the average bright of each pixel gathering line
Angle value, determines the similar value of the average brightness value of the pixel gathering line of correspondence position.In the present embodiment, pixel gathering line is average bright
The similar value of angle value can be determined by the difference of pixel gathering line average brightness value, for example, can be that difference is bigger, similar value
It is smaller;Difference is smaller, and similar value is bigger.This pair is for example determined according to the difference of the average brightness value of pixel gathering line 101 and 201
Answer the similar value of the pixel gathering line of position.
S250, the similar levels of correspondence position pixel gathering line to presetting similar threshold values are determined according to similar value.
Wherein, similar threshold values is preset to be determined according to history image format-detected result.
Optionally, if similar value is more than the maximum for presetting similar threshold values, it is determined that the phase of correspondence position pixel gathering line
It is the first similar levels like grade, and labeled as the first numerical value;
If similar value is being preset in similar threshold values, it is determined that the similar levels of correspondence position pixel gathering line are second similar
Grade, and labeled as second value;
If similar value is less than the minimum value for presetting similar threshold values, it is determined that the similar levels of correspondence position pixel gathering line are
Third phase is labeled as third value like grade;
Wherein, the first similar levels, the second similar levels and third phase are reduced successively like grade, the first numerical value, the second number
Value and third value are sequentially reduced.
Exemplary, it can be 0.9-0.95 to preset similar threshold values, and similar value is that 0 two brightness values of expression are entirely different;
Similar value is that 1 two brightness values of expression are identical.If the similar value of the average brightness value of correspondence position pixel gathering line is more than
0.95, it is determined that the similar levels of the correspondence position pixel gathering line are the first similar levels, and labeled as the first numerical value;If right
The similar value of the average brightness value of position pixel gathering line is answered to be less than or equal to 0.95, and more than or equal to 0.9, it is determined that the correspondence position
The similar levels for putting pixel gathering line are the second similar levels, and labeled as second value;If correspondence position pixel gathering line
The similar value of average brightness value be less than 0.9, it is determined that the similar levels of the correspondence position pixel gathering line be third phase like grade,
And labeled as third value.Wherein the first numerical value, second value and third value can be determined according to history testing result, exemplary
, the first numerical value, second value and third value can be -1,0 and 1 respectively.
S260, according to the similar levels of each pixel gathering line determine whether images to be recognized meets three-dimensional format transformation, if
It is then to perform step S270, if it is not, then performing step S280.
In the present embodiment, the determination planned as a whole by the similar levels of pixel gathering line all in each image-region is to be identified
The form of image, it is to avoid the pixel gathering line similar levels of a certain correspondence position are abnormal, or pass through single group correspondence position
When the similar levels of pixel gathering line determine picture format, the problem of accuracy in detection is low.
Optionally, step S260 includes:
Determine the corresponding tag value of the similar levels and value of correspondence position pixel gathering line in each image-region;
It will be compared with value with predetermined threshold value, and determine whether images to be recognized will meet three-dimensional conversion lattice according to comparison result
Formula.
In the present embodiment, the similar levels of each correspondence position pixel gathering line are subjected to data by corresponding flag data
Change, by the corresponding tag value of similar levels and value calculating, realize the quantization system of each pixel gathering line similar levels
Raise, improve the accuracy in detection of the form of image.
Wherein, predetermined threshold value is determined according to the first numerical value, second value and third value, exemplary, if the first numerical value,
Second value and third value can be -1,0 and 1 respectively, then predetermined threshold value can be 2.Exemplary, if each correspondence position
The similar levels of pixel gathering line and value be more than or equal to 2, it is determined that images to be recognized meets three-dimensional format transformation, if respectively
The similar levels of the pixel gathering line of correspondence position and value be less than 2, it is determined that images to be recognized is unsatisfactory for three-dimensional format transformation.
S270, images to be recognized is subjected to three-dimensional conversion process.
S280, images to be recognized is subjected to two-dimentional display.
The technical scheme of the present embodiment, determines that the pixel of predetermined number is adopted according to default sampling rule in each image-region
Line concentration, and the average brightness value of each pixel gathering line is obtained, according to the phase of the average brightness value of the pixel gathering line of correspondence position
The similar levels of the pixel gathering line of correspondence position are determined like value, plans as a whole ground and is gathered according to the pixel of the correspondence position of predetermined number
The similar levels of line determine images to be recognized form, and solve needs user to recognize picture format by naked eyes in the prior art
Situation, realizes automatic identification picture format, improves picture format recognition accuracy.
Embodiment three
Fig. 5 is a kind of structural representation of the identifying device for picture format that the embodiment of the present invention three is provided, device tool
Body can include:
Image acquiring device 310, for obtaining images to be recognized, wherein images to be recognized includes the first image-region and the
Two image-regions;
Pixel gathering line determining module 320, for determining predetermined number in each image-region according to default sampling rule
Pixel gathering line, the pixel gathering line of the first image-region and the pixel gathering line of the second image-region meet predeterminated position pair
Should rule;
Image judge module 330, for the pixel information according to correspondence position pixel gathering line in each image-region, really
Determine whether images to be recognized meets three-dimensional format transformation;
Image processing module 340, if meeting three-dimensional format transformation for images to be recognized, three are carried out by images to be recognized
Tie up conversion process.
Optionally, pixel gathering line determining module 320 specifically for:
The position of pixel gathering line is determined according to the predetermined number of the type of pixel gathering line and pixel gathering line, pixel is adopted
The type of line concentration includes row gathering line and row gathering line, and each pixel gathering line is uniformly distributed in each image-region.
Optionally, pixel gathering line is the half of position row pixel or row pixel in each image-region.
Optionally, image judge module 330 includes:
Brightness value determining unit, for obtaining in each image-region being averaged for each pixel in correspondence position pixel gathering line
Brightness value;
Similar value determining unit, the phase for determining the average brightness value of correspondence position pixel gathering line in each image-region
Like value;
Similar levels determining unit, for determining correspondence position pixel gathering line to presetting similar threshold values according to similar value
Similar levels;
Image judging unit, for determining whether images to be recognized meets three-dimensional according to the similar levels of each pixel gathering line
Format transformation.
Optionally, similar levels determining unit specifically for:
If similar value is more than the maximum for presetting similar threshold values, it is determined that the similar levels of correspondence position pixel gathering line are
First similar levels, and labeled as the first numerical value;If similar value is being preset in similar threshold values, it is determined that correspondence position pixel is gathered
The similar levels of line are the second similar levels, and labeled as second value;If similar value is less than the minimum value for presetting similar threshold values,
Then determine correspondence position pixel gathering line similar levels for third phase like grade, and be labeled as third value;Wherein, the first phase
Reduced successively like grade like grade, the second similar levels and third phase, the first numerical value, second value and third value subtract successively
It is small.
Optionally, image judging unit specifically for:
Determine the corresponding tag value of the similar levels and value of correspondence position pixel gathering line in each image-region;Will be with
Value is compared with predetermined threshold value, determines whether images to be recognized meets three-dimensional format transformation according to comparison result.
A kind of identifying device of picture format provided in an embodiment of the present invention can perform any embodiment of the present invention and be provided
A kind of picture format recognition methods, possess a kind of corresponding functional module of the recognition methods of picture format of execution method and
Beneficial effect.
Note, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art it is various it is obvious change,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although the present invention is carried out by above example
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (12)
1. a kind of recognition methods of picture format, it is characterised in that including:
Images to be recognized is obtained, wherein the images to be recognized includes the first image-region and the second image-region;
The pixel gathering line of predetermined number is determined in each image-region according to default sampling rule, described first image region
Pixel gathering line and the pixel gathering line of second image-region meet the predeterminated position rule of correspondence;
According to the pixel information of correspondence position pixel gathering line in each image-region, whether the images to be recognized is determined
Meet three-dimensional format transformation;
If so, the images to be recognized then is carried out into three-dimensional conversion process.
2. according to the method described in claim 1, it is characterised in that determined according to default sampling rule in each image-region pre-
If the pixel gathering line of quantity, including:
The position of the pixel gathering line is determined according to the predetermined number of the type of the pixel gathering line and the pixel gathering line
Put, the type of the pixel gathering line includes row gathering line and row gathering line, and each pixel gathering line is uniformly distributed in described
In each image-region.
3. method according to claim 1 or 2, it is characterised in that the pixel gathering line is in each image-region
The half of position row pixel or row pixel.
4. according to the method described in claim 1, it is characterised in that gathered according to correspondence position pixel in each image-region
Pixel information in line, determines whether the images to be recognized meets three-dimensional format transformation, including:
Obtain the average brightness value of each pixel in correspondence position pixel gathering line in each image-region;
Determine the similar value of the average brightness value of correspondence position pixel gathering line in each image-region;
The similar levels of the correspondence position pixel gathering line are determined to presetting similar threshold values according to the similar value;
Determine whether the images to be recognized meets three-dimensional format transformation according to the similar levels of each pixel gathering line.
5. method according to claim 4, it is characterised in that according to the similar value is determined to default similar threshold values
The similar levels of pixel gathering line, including:
If the similar value is more than the maximum for presetting similar threshold values, it is determined that the phase of the correspondence position pixel gathering line
It is the first similar levels like grade, and labeled as the first numerical value;
If the similar value is preset in similar threshold values described, it is determined that the similar levels of the correspondence position pixel gathering line are
Second similar levels, and labeled as second value;
If the similar value is less than the minimum value for presetting similar threshold values, it is determined that the phase of the correspondence position pixel gathering line
Like grade be third phase like grade, and be labeled as third value;
Wherein, first similar levels, second similar levels and the third phase are reduced successively like grade, and described first
Numerical value, the second value and the third value are sequentially reduced.
6. method according to claim 5, it is characterised in that determine institute according to the similar levels of each pixel gathering line
State whether images to be recognized meets three-dimensional format transformation, including:
Determine the corresponding tag value of the similar levels and value of correspondence position pixel gathering line in each image-region;
Described and value and predetermined threshold value are compared, determine whether the images to be recognized meets three-dimensional turn according to comparison result
Change form.
7. a kind of identifying device of picture format, it is characterised in that including:
Image acquiring device, for obtaining images to be recognized, wherein the images to be recognized includes the first image-region and second
Image-region;
Pixel gathering line determining module, for determining that the pixel of predetermined number is adopted in each image-region according to default sampling rule
Line concentration, the pixel gathering line in described first image region and the pixel gathering line of second image-region meet predeterminated position pair
Should rule;
Image judge module, for the pixel information according to correspondence position pixel gathering line in each image-region, it is determined that
Whether the images to be recognized meets three-dimensional format transformation;
Image processing module, if meeting three-dimensional format transformation for the images to be recognized, the images to be recognized is carried out
Three-dimensional conversion process.
8. device according to claim 7, it is characterised in that the pixel gathering line determining module specifically for:
The position of the pixel gathering line is determined according to the predetermined number of the type of the pixel gathering line and the pixel gathering line
Put, the type of the pixel gathering line includes row gathering line and row gathering line, and each pixel gathering line is uniformly distributed in described
In each image-region.
9. the device according to claim 7 or 8, it is characterised in that the pixel gathering line is in each image-region
The half of position row pixel or row pixel.
10. device according to claim 7, it is characterised in that described image judge module includes:
Brightness value determining unit, for obtaining in each image-region being averaged for each pixel in correspondence position pixel gathering line
Brightness value;
Similar value determining unit, the average brightness value for determining correspondence position pixel gathering line in each image-region
Similar value;
Similar levels determining unit, for determining that the correspondence position pixel is gathered to presetting similar threshold values according to the similar value
The similar levels of line;
Image judging unit, for determining whether the images to be recognized meets according to the similar levels of each pixel gathering line
Three-dimensional format transformation.
11. device according to claim 10, it is characterised in that the similar levels determining unit specifically for:
If the similar value is more than the maximum for presetting similar threshold values, it is determined that the phase of the correspondence position pixel gathering line
It is the first similar levels like grade, and labeled as the first numerical value;If the similar value is preset in similar threshold values described, it is determined that
The similar levels of the correspondence position pixel gathering line are the second similar levels, and labeled as second value;If the similar value
Less than it is described preset similar threshold values minimum value, it is determined that the similar levels of the correspondence position pixel gathering line be third phase seemingly
Grade, and labeled as third value;Wherein, first similar levels, second similar levels and the third phase like etc.
Level is reduced successively, and first numerical value, the second value and the third value are sequentially reduced.
12. device according to claim 11, it is characterised in that described image judging unit specifically for:
Determine the corresponding tag value of the similar levels and value of correspondence position pixel gathering line in each image-region;By institute
State and value is compared with predetermined threshold value, determine whether the images to be recognized meets three-dimensional format transformation according to comparison result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710317564.1A CN107274456A (en) | 2017-05-08 | 2017-05-08 | A kind of recognition methods of picture format and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710317564.1A CN107274456A (en) | 2017-05-08 | 2017-05-08 | A kind of recognition methods of picture format and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107274456A true CN107274456A (en) | 2017-10-20 |
Family
ID=60074345
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710317564.1A Pending CN107274456A (en) | 2017-05-08 | 2017-05-08 | A kind of recognition methods of picture format and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107274456A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111325804A (en) * | 2018-12-14 | 2020-06-23 | 中移(杭州)信息技术有限公司 | Method and device for determining YUV image display parameters |
CN114584673A (en) * | 2020-12-01 | 2022-06-03 | 京东方科技集团股份有限公司 | Image processing method and device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080310717A1 (en) * | 2006-02-01 | 2008-12-18 | Motorola, Inc. | Apparatus and Method for Image Labeling |
CN103593837A (en) * | 2012-08-15 | 2014-02-19 | 联咏科技股份有限公司 | Method for automatically detecting image format and related device |
CN104994374A (en) * | 2015-07-03 | 2015-10-21 | 宁波易维视显示技术有限公司 | Method for automatically detecting three-dimensional format of video |
-
2017
- 2017-05-08 CN CN201710317564.1A patent/CN107274456A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080310717A1 (en) * | 2006-02-01 | 2008-12-18 | Motorola, Inc. | Apparatus and Method for Image Labeling |
CN103593837A (en) * | 2012-08-15 | 2014-02-19 | 联咏科技股份有限公司 | Method for automatically detecting image format and related device |
CN104994374A (en) * | 2015-07-03 | 2015-10-21 | 宁波易维视显示技术有限公司 | Method for automatically detecting three-dimensional format of video |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111325804A (en) * | 2018-12-14 | 2020-06-23 | 中移(杭州)信息技术有限公司 | Method and device for determining YUV image display parameters |
CN111325804B (en) * | 2018-12-14 | 2023-11-03 | 中移(杭州)信息技术有限公司 | Method and device for determining YUV image display parameters |
CN114584673A (en) * | 2020-12-01 | 2022-06-03 | 京东方科技集团股份有限公司 | Image processing method and device |
CN114584673B (en) * | 2020-12-01 | 2024-01-09 | 京东方科技集团股份有限公司 | Image processing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111028213B (en) | Image defect detection method, device, electronic equipment and storage medium | |
CN104574366B (en) | A kind of extracting method in the vision significance region based on monocular depth figure | |
WO2007052191A2 (en) | Filling in depth results | |
CN105389541B (en) | The recognition methods of fingerprint image and device | |
CN109190617B (en) | Image rectangle detection method and device and storage medium | |
CN106067177A (en) | HDR scene method for detecting and device | |
CN105279473B (en) | Face image correction method and device and face recognition method and system | |
CN106815587A (en) | Image processing method and device | |
CN109903283A (en) | A kind of mask graph edge defect detection algorithm based on image normal vector | |
CN104281850A (en) | Character area identification method and device | |
CN107274456A (en) | A kind of recognition methods of picture format and device | |
CN110188640B (en) | Face recognition method, face recognition device, server and computer readable medium | |
CN107025633B (en) | Image processing method and device | |
CN113177941B (en) | Steel coil edge crack identification method, system, medium and terminal | |
CN105631868A (en) | Depth information extraction method based on image classification | |
CN111161291A (en) | Contour detection method based on target depth of field information | |
CN115840550A (en) | Angle-adaptive display screen display method, device and medium | |
CN116579968A (en) | Identification method and device for food material image, steaming and baking equipment and storage medium | |
CN112070081B (en) | Intelligent license plate recognition method based on high-definition video | |
CN112991294A (en) | Foreign matter detection method, apparatus and computer readable medium | |
CN106251468B (en) | A kind of paper money discrimination method and apparatus | |
CN107452039B (en) | Method and device for compressing RGB color space | |
CN102194203B (en) | A kind of method and apparatus reducing Face datection memory space | |
CN116185544B (en) | Display image fusion method and device based on image feature recognition and storage medium | |
KR20030076904A (en) | Method for Reconstructing Intermediate View Image using Adaptive Disparity Estimation |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200407 Address after: 215634 north side of Chengang road and west side of Ganghua Road, Jiangsu environmental protection new material industrial park, Zhangjiagang City, Suzhou City, Jiangsu Province Applicant after: ZHANGJIAGANG KANGDE XIN OPTRONICS MATERIAL Co.,Ltd. Address before: 201203, room 5, building 690, No. 202 blue wave road, Zhangjiang hi tech park, Shanghai, Pudong New Area Applicant before: WZ TECHNOLOGY Inc. |
|
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171020 |