CN106454096A - Image processing method and terminal thereof - Google Patents
Image processing method and terminal thereof Download PDFInfo
- Publication number
- CN106454096A CN106454096A CN201610923647.0A CN201610923647A CN106454096A CN 106454096 A CN106454096 A CN 106454096A CN 201610923647 A CN201610923647 A CN 201610923647A CN 106454096 A CN106454096 A CN 106454096A
- Authority
- CN
- China
- Prior art keywords
- histogram
- curve
- optimum
- axis
- original
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims description 25
- 238000010801 machine learning Methods 0.000 claims description 18
- 230000015572 biosynthetic process Effects 0.000 claims description 13
- 238000003786 synthesis reaction Methods 0.000 claims description 13
- 238000013139 quantization Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000009877 rendering Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000275 quality assurance Methods 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/698—Control of cameras or camera modules for achieving an enlarged field of view, e.g. panoramic image capture
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/73—Circuitry for compensating brightness variation in the scene by influencing the exposure time
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
- Facsimile Image Signal Circuits (AREA)
- Image Processing (AREA)
Abstract
Embodiments of the invention disclose an image processing method and a terminal thereof. The method comprises the following steps of acquiring a plurality of current photographs shot by a panorama camera, wherein the panorama camera includes at least cameras with different directions and each current photograph is shot by each camera of the panorama camera; acquiring a target histogram curve; and according to the target histogram curve, carrying out exposure adjusting on the current photographs. In the embodiments of the invention, the current photographs shot by the panorama camera are acquired firstly, and then the target histogram curve is acquired too; according to the target histogram curve, the exposure adjusting is performed on the current photographs so that a problem that exposure degrees of the photographs shot by the cameras (such as phototropic face and shady face cameras) which are located at different shooting angles in the panorama camera are inconsistent is solved and panorama photograph quality is increased.
Description
Technical field
The present invention relates to technical field of image processing, more particularly, to a kind of image processing method and terminal.
Background technology
Panorama camera generally includes at least two cameras with different shooting angles.Complete being shot using panorama camera
During scape photo, because camera has different shooting angle, the camera for example having is located at phototropic face, some cameras but position
In shady face, thus leading to captured distant view photograph to occur in that the situation that depth of exposure differs, have impact on clapped distant view photograph
Effect.
Content of the invention
The embodiment of the present invention provides a kind of image processing method and its terminal, with to being in different shooting angles in panorama camera
The photo captured by camera of degree is exposed adjusting, thus improving distant view photograph quality.
Embodiments provide a kind of image processing method, including：
Obtain multiple current photos captured by panorama camera, panorama camera includes the shooting of at least two different directions
Head, every current photo is captured by each camera of panorama camera；
Obtain goal histogram curve；
Current photo is exposed adjust according to goal histogram curve.
Embodiments provide a kind of terminal, including：
Acquiring unit, for obtaining multiple current photos and the goal histogram curve captured by panorama camera, this panorama
Camera includes the camera of at least two different directions, and every current photo is captured by each camera of panorama camera；
Adjustment unit, for being exposed to described current photo adjusting according to goal histogram curve.
The embodiment of the present invention first obtains the current photo captured by panorama camera, then obtains goal histogram curve, finally
Current photo is exposed adjust according to goal histogram curve, thus solve being in different shooting angles in panorama camera
The problem that differs of camera (as the camera lens of phototropic face and shady face) depth of exposure of taking a picture, and then improve distant view photograph
Quality.
Brief description
In order to be illustrated more clearly that embodiment of the present invention technical scheme, required use in embodiment being described below
Accompanying drawing be briefly described it should be apparent that, drawings in the following description are some embodiments of the present invention, general for this area
For logical technical staff, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is the schematic flow diagram of the image processing method that first embodiment of the invention provides；
Fig. 2 is the schematic flow diagram of the image processing method that second embodiment of the invention provides；
Fig. 3 is the original histogram before adjustment；
Fig. 4 is the histogram curve schematic diagram before adjustment；
Fig. 5 is the original histogram after adjustment；
Fig. 6 is the histogram curve schematic diagram after adjustment；
Fig. 7 is the dark portion of RGB and GL four dimensions, ash portion, highlights schematic diagram；
Fig. 8 is optimum dark portion curve under GL dimension, ash portion curve and highlights curve synoptic diagram；
Fig. 9 is the fitting function figure under GL dimension；
Figure 10 is the schematic flow diagram of third embodiment of the invention image processing method；
Figure 11 is the structural representation of the terminal that first embodiment of the invention provides；
Figure 12 is the structural representation of the terminal that second embodiment of the invention provides；
Figure 13 is the structural representation of the terminal that third embodiment of the invention provides；
Figure 14 is the structural representation of the terminal providing in fourth embodiment of the invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation description is it is clear that described embodiment a part of embodiment that is the present invention, rather than whole embodiments.Based on this
Embodiment in bright, the every other enforcement that those of ordinary skill in the art are obtained under the premise of not making creative work
Example, broadly falls into the scope of protection of the invention.
It should be appreciated that when using in this specification and in the appended claims, term " inclusion " and "comprising" indicate
The presence of described feature, entirety, step, operation, element and/or assembly, but it is not precluded from one or more of the other feature, whole
Body, step, operation, the presence of element, assembly and/or its set or interpolation.
It is also understood that the term used in this description of the invention is merely for the sake of the mesh describing specific embodiment
And be not intended to limit the present invention.As used in description of the invention and appended claims, unless on
Hereafter clearly indicate other situations, otherwise " one " of singulative, " one " and " being somebody's turn to do " are intended to including plural form.
It will be further appreciated that, used in description of the invention and appended claims, term "and/or" is
Refer to any combinations of one or more of the associated item listed and be possible to combine, and include these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determining " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if [described condition or event] is detected " can be interpreted to mean according to context " once it is determined that " or " in response to true
Fixed " or " once [described condition or event] is detected " or " in response to [described condition or event] is detected ".
In implementing, the terminal described in the embodiment of the present invention including but not limited to such as has touch sensitive surface
Other of the mobile phone of (for example, touch-screen display and/or touch pad), laptop computer or tablet PC etc is just
Portable device.It is to be further understood that in certain embodiments, described equipment not portable communication device, but have tactile
Touch the desktop computer of sensing surface (for example, touch-screen display and/or touch pad).
In discussion below, describe the terminal including display and touch sensitive surface.It is, however, to be understood that
It is that terminal can include one or more of the other physical user-interface device of such as physical keyboard, mouse and/or control bar.
Refer to Fig. 1, be that first embodiment of the invention provides a kind of schematic flow diagram of image processing method, as schemed institute
Show, the method may include following steps：
S101, obtains multiple current photos captured by panorama camera, and this panorama camera includes at least two different directions
Camera, every current photo is captured by each camera of panorama camera.Panorama camera, such as virtual reality
(Virtual Reality, VR) panorama camera, is used for the photo that pans, and it generally includes more than 2 cameras, and each
Camera all has different shooting angle, and the camera for example having is located at phototropic face, and some cameras are located at shady face.Cause
This, the exposure of the photo captured by each camera differs, and the camera of such as phototropic face may be over-exposed, and shady face
Camera then probably due to dark and under-exposed.In one embodiment, panorama camera can be that 360 degree of shootings set
Standby, by 360 picture pick-up devices in current time 16:15 shooting N open current photo, are designated as photo 1, photo 2, photo 3......
Photo n.Wherein, photo 1 is captured by the camera of X1 angle, and photo 2 is captured by the camera of X2 angle, the like,
Photo n is captured by the camera of Xn angle.Understandably, the panorama camera described in the embodiment of the present invention, it shoots
Angle can be 360 degree it is also possible to more than 360 degree or be less than 360 degree, specifically and the structure of panorama camera, camera quantity, take the photograph
As the set-up mode of head and the factor of other impact pan-shot angular range are related, the present invention is not construed as limiting to this.
S102, obtains goal histogram curve.Specifically, goal histogram curve is by the history captured by panorama camera
Photo is analyzed gained, and the detailed process of this part will be described in detail in next embodiment.Understandably, except can be to going through
History photo is analyzed to obtain goal histogram extra curvature, also in advance this goal histogram curve can be stored in this reality of execution
Apply in the terminal of a method.Or, after the terminal executing the present embodiment method obtains multiple current photos, can be adjusted by network
Mode obtains the goal histogram curve being stored on other-end.
S103, is exposed to current photo adjusting according to goal histogram curve.Specifically, current photo is carried out directly
Square map analysis and Luminance Analysis etc., thus obtaining the optimum histogram curve of current photo, afterwards, according to goal histogram curve
Optimum histogram curve is adjusted so that this optimum histogram curve is as far as possible consistent with goal histogram curve, thus real
Show the exposure adjustment to current photo.
Specifically, 15:45 moment have taken N by 360 picture pick-up devices and open historical photograph, and this historical photograph is carried out directly
Square map analysis and Luminance Analysis, to obtain optimum histogram curve, carry out numerical value collection and machine to this optimum histogram curve afterwards
Device study can get goal histogram curve.So far, adjustment can be exposed to current photo memory according to this optimum histogram curve,
So that the exposure base of the current photo captured by phototropic face camera and the current photo captured by shady face camera
This is consistent, thus providing quality assurance for follow-up synthesis distant view photograph.
The embodiment of the present invention first obtains the current photo captured by panorama camera, then obtains goal histogram curve, finally
Current photo is exposed adjust according to goal histogram curve, thus solve being in different shooting angles in panorama camera
The problem that differs of camera (as the camera lens of phototropic face and shady face) depth of exposure of taking a picture, and then improve distant view photograph
Quality.
Refer to Fig. 2, be that second embodiment of the invention provides a kind of schematic flow diagram of image processing method, as schemed institute
Show, the method may include following steps：
S201, obtains multiple historical photographs captured by panorama camera.Specifically, by 360 picture pick-up devices in the moment 15:
45 shooting N open current photo, are designated as photo 1, photo 2, photo 3......Photo n.Wherein, photo 1 is the camera of X1 angle
Captured, photo 2 is captured by the camera of X2 angle, the like, photo n is captured by the camera of Xn angle.
Multiple historical photographs are entered column hisgram and extract to obtain multiple original histograms by S202.Specifically, every history
Photo all includes RGB and GL four dimensions, and wherein, R represents Red redness, and G represents Green green, and B represents Blue blueness, GL
Represent Gray Level gray scale.According to this four dimensions, every historical photograph can be obtained with 4 histograms, for example, to photo 1,
Obtain Nogata Fig. 3 of Nogata Fig. 2, B dimension of Nogata Fig. 1, G dimension and Nogata Fig. 4 of GL dimension of R dimension.Now, to photo
1 enter column hisgram extraction process obtained by original histogram 1 it should be the Nogata of Nogata Fig. 1, G dimension containing R dimension
Nogata Fig. 3 of Fig. 2, B dimension and Nogata Fig. 4 of GL dimension, this original histogram 1 is as shown in Figure 3.In the same manner, to remaining photo
Do same treatment, because there being N to open photo, finally obtaining N and open Nogata Fig. 1, N of R dimension and opening Nogata Fig. 2, N of G dimension and open B
Nogata Fig. 3 and N of dimension opens Nogata Fig. 4 of GL dimension.Accordingly, also obtain N and open original histogram 2 and open original Nogata to N
Figure n, and original histogram 2 all includes RGB and GL four dimensions to original histogram n.
S203, generates a plurality of histogram curve according to multiple original histograms.Specifically, taking original histogram 1 as a example, can
To generate a histogram curve 1 on the distributed areas that x-axis and y-axis are constituted, as shown in figure 4, wherein, x-axis represents photo
In black, grey and white, y-axis represents black, the grey and white accounting in photo.In the same manner, to original histogram 2 to
Original histogram n does same process, can generate histogram curve 2 to n, thus having obtained a plurality of histogram curve.
S204, each histogram curve of adjustment is so that each original histogram is equably extended to whole distributed area
Domain, wherein, distributed areas are the region in x-axis and y-axis.Taking histogram curve 1 as a example, it corresponds to original histogram 1, from figure
3, as can be seen that the distribution in the original histogram 1 of photo 1 is very uneven, therefore, are adjusted to histogram curve 1, example
Curve as shown in by Fig. 4 is adjusted to straight line as shown in Figure 6.Through such adjustment, original histogram is equably extended
Arrive whole distributed areas, refer to Fig. 5, the effect of the original histogram 1 after adjustment is substantially unadjusted original straight than in Fig. 3
Square figure is well a lot.In the same manner, same process is done to histogram curve 2 to n, original histogram 2 can be made all by equably to n
It has been extended to whole distributed areas.
Multiple original histograms after extending are carried out brightness contrast and analyze to obtain optimum histogram curve by S205.Tool
Body ground, photo includes RGB and GL four dimensions, and therefore, original histogram herein also includes RGB and GL four dimensions.
If split original histogram 1 coming, wherein should the histogram containing 1 R dimension, the histogram of 1 G dimension, 1 B dimension
Histogram and 1 GL dimension histogram.In the same manner, original histogram is opened for n and can get that N opens the histogram of R dimension, N opens G
The histogram of dimension, N open the histogram of B dimension and N opens the histogram of GL dimension.Here, the dull gray being comprised according to picture is bright
Three dimensions split to each original histogram, that is, each histogram all include dark portion as shown in Figure 7, ash portion and
Highlights, the dark portion photo such that it is able to obtain includes N and opens GL dimension, R dimension, G dimension and B dimension, and grey portion photo includes N and opens GL
Dimension, R dimension, G dimension and B dimension, highlights photo includes N and opens GL dimension, R dimension, G dimension and B dimension.With GL dimension it is first
Example, the dark portion photo that N is opened with GL dimension compares, and can obtain under GL dimension, N opens dark portion histogram, in the same manner, permissible
Obtain under GL dimension, N opens grey portion histogram and highlights histogram.Open dark portion histogram to the N under GL dimension to be analyzed,
Such that it is able to obtain the optimum dark portion histogram under GL dimension.In the same manner, can obtain optimal grey portion histogram under GL dimension and
Optimum highlights histogram.Equally, under GL dimension, straight according to optimum dark portion histogram, optimal grey portion histogram and optimum highlights
Side's figure generates optimum dark portion curve, optimal grey portion curve and optimum highlights curve.By this optimum dark portion curve, optimal grey portion curve
And optimum highlights curve carries out splicing synthesis, just obtain the optimum histogram curve under GL dimension, as can be seen from figures 8 and 9.From
In figure can be seen that optimum histogram curve under GL dimension by optimum dark portion curve, optimum grey portion curve and optimum
Highlights curve is constituted.Further, to RGB dimension repeat the above steps, can get the optimum histogram curve under RGB dimension.
Finally, optimum for four under GL and RGB dimension histogram curve is synthesized, finally can obtain comprising tetra- dimensions of GL and RGB
The optimum histogram curve of degree.
S206, carries out numerical value collection and machine learning to obtain goal histogram curve to optimum histogram curve.Specifically
Ground, the quantization that optimum histogram curve is carried out with x-axis and y-axis to obtain x-axis numerical value and y-axis numerical value, further according to x-axis numerical value and y
Axis values draw matched curve, finally matched curve are carried out with machine learning to obtain goal histogram curve (GL as shown in Figure 9
Goal histogram curve under dimension).Further, a reference axis can be set up, wherein transverse axis is x-axis, and the longitudinal axis is y-axis.Transverse axis
Represent from black to white from left to right, by transverse axis is divided into 256 ranks, be black in photo, grey and white；The longitudinal axis
Then represent black, the grey and white accounting in a photo, i.e. relative populations.After setting up this reference axis, with GL dimension
As a example, the quantization that optimum histogram curve is carried out with x-axis and y-axis to obtain x-axis numerical value and y-axis numerical value, further according to x-axis numerical value and
Y-axis numeric renderings matched curve, finally carries out machine learning and can simulate similar one section of sin cos functionses in Fig. 9 to matched curve
Curve, i.e. goal histogram curve.In the same manner, to RGB dimension repeat the above steps, can get the target Nogata under RGB dimension
Figure curve.Finally, four target histogram curve under GL and RGB dimension are synthesized, finally can obtain comprising GL and RGB
The goal histogram curve of four dimensions.It should be noted that being to be entered according to RGB the and GL four dimensions of photo in the present embodiment
Row analysis, to obtain goal histogram curve it will be appreciated that ground, can directly be analyzed to view picture photo to obtain goal histogram
Curve.
S207, receives multiple current photos captured by panorama camera.For example, 16:In 15 moment, panorama camera have taken
N opens the current photo of different shooting angles.
S208, is exposed to current photo adjusting according to goal histogram curve.Specifically, before current photo being carried out
The histogram analysis stated and Luminance Analysis etc., thus obtaining the optimum histogram curve of current photo, as shown in Figure 9 is optimum straight
Square figure curve, afterwards, according to goal histogram curve as shown in Figure 9, optimum histogram curve is adjusted so that this
Excellent histogram curve is tried one's best consistent with goal histogram curve, it is achieved thereby that the exposure to current photo adjusts.
The embodiment of the present invention first passes through panorama camera and shoots multiple historical photographs, enters column hisgram to multiple historical photographs and divides
Analysis and Luminance Analysis to obtain optimum histogram curve, and this optimum histogram curve is carried out numerical value collection and machine learning with
Obtain goal histogram curve.When shooting next photo again by panorama camera, can be according to above-mentioned goal histogram curve
Current photo is exposed adjust.Due to having taken into full account in panorama camera during obtaining goal histogram curve
It is in the problem that camera (as the camera lens of the phototropic face and shady face) depth of exposure of taking a picture of different shooting angles differs, should
In goal histogram curve, involved dark portion, ash portion and highlights part are optimum, therefore according to this goal histogram curve
Current photo is exposed adjust, so that the exposure that the camera being in different angles is taken a picture is basically identical,
Thus providing quality assurance for the synthesis of follow-up distant view photograph.
Refer to Figure 10, be that third embodiment of the invention provides a kind of schematic flow diagram of image processing method, as schemed institute
Show, the method may include following steps：
S301, obtains multiple historical photographs captured by panorama camera.Specifically, by 360 picture pick-up devices in the moment 15:
45 shooting N open current photo, are designated as photo 1, photo 2, photo 3......Photo n.Wherein, photo 1 is the camera of X1 angle
Captured, photo 2 is captured by the camera of X2 angle, the like, photo n is captured by the camera of Xn angle.
Multiple historical photographs are entered column hisgram and extract to obtain multiple original histograms by S302.Specifically, every history
Photo all includes RGB and GL four dimensions, and wherein, R represents Red redness, and G represents Green green, and B represents Blue blueness, GL
Represent Gray Level gray scale.According to this four dimensions, every historical photograph can be obtained with 4 histograms, for example, to photo 1,
Obtain Nogata Fig. 3 of Nogata Fig. 2, B dimension of Nogata Fig. 1, G dimension and Nogata Fig. 4 of GL dimension of R dimension.Now, to photo
1 enter column hisgram extraction process obtained by original histogram 1 should be Nogata Fig. 1, G dimension containing R dimension Nogata
Nogata Fig. 4 of Nogata Fig. 3 level GL dimension of Fig. 2, B dimension.In the same manner, same treatment is done to remaining photo, because there being N to open photograph
Piece, thus finally obtain N open R dimension Nogata Fig. 1, N open G dimension Nogata Fig. 2, N open B dimension Nogata Fig. 3 and N open GL dimension
Nogata Fig. 4 of degree.Accordingly, also obtain N and open original histogram 2 and open original histogram n to N, and original histogram 2 is to original
Histogram n all includes RGB and GL four dimensions.
S303, generates a plurality of histogram curve according to multiple original histograms.Specifically, taking original histogram 1 as a example, can
So that a histogram curve 1 to be generated on the distributed areas that x-axis and y-axis are constituted, as shown in Figure 4.In the same manner, to original histogram
2 to original histogram n does same process, can generate histogram curve 2 to n, thus having obtained a plurality of histogram curve.
S304, each histogram curve of adjustment is so that each original histogram is equably extended to whole distributed area
Domain, wherein, distributed areas are the region in x-axis and y-axis.Taking histogram curve 1 as a example, it corresponds to original histogram 1, from figure
3, as can be seen that the distribution in the original histogram 1 of photo 1 is very uneven, therefore, are adjusted to histogram curve 1, example
Curve as shown in by Fig. 4 is adjusted to straight line as shown in Figure 6.Through such adjustment, original histogram is equably extended
Arrive whole distributed areas, refer to Fig. 5, the effect of the original histogram 1 after adjustment is substantially unadjusted original straight than in Fig. 3
Square figure is well a lot.In the same manner, same process is done to histogram curve 2 to n, original histogram 2 can be made all by equably to n
It has been extended to whole distributed areas.
Multiple original histograms after extending are carried out brightness contrast and analyze to obtain optimum histogram curve by S305.Tool
Body ground, first carries out Luminance Analysis to obtain multiple dark portion histograms, ash portion histogram to each original histogram after extending
And highlights histogram, then it is straight to obtain optimum dark portion to contrast multiple described dark portion histograms, ash portion histogram and highlights histogram
Fang Tu, optimal grey portion histogram and optimum highlights histogram, generate optimum dark portion curve, root then according to optimum dark portion histogram
Generate optimum highlights curve according to optimal grey portion histogram generation optimal grey portion curve and according to optimum highlights histogram, finally according to
Optimum dark portion curve, optimal grey portion curve and optimum highlights curve generate optimum histogram curve.Further, this part is more
Detailed process refer to previous embodiment.
S306, carries out numerical value collection and machine learning to obtain goal histogram curve to optimum histogram curve.Specifically
Ground, the quantization that optimum histogram curve is carried out with x-axis and y-axis to obtain x-axis numerical value and y-axis numerical value, further according to x-axis numerical value and y
Axis values draw matched curve, finally matched curve are carried out with machine learning to obtain goal histogram curve (GL as shown in Figure 9
Goal histogram curve under dimension).Further, this partly more detailed process refer to previous embodiment.
S307, receives multiple current photos captured by panorama camera.For example, 16:In 15 moment, panorama camera have taken
N opens the current photo of different shooting angles.
S308, is exposed to current photo adjusting according to goal histogram curve.Specifically, before current photo being carried out
The histogram analysis stated and Luminance Analysis etc., thus obtaining the optimum histogram curve of current photo, as shown in Figure 9 is optimum straight
Square figure curve, afterwards, according to goal histogram curve as shown in Figure 9, optimum histogram curve is adjusted so that this
Excellent histogram curve is tried one's best consistent with goal histogram curve, it is achieved thereby that the exposure to current photo adjusts.
S309, multiple current photos after synthesis exposure adjustment are to obtain distant view photograph.According to goal histogram curve pair
It is exposed after adjustment positioned at the current photo captured by camera of different angles, it is synthesized to obtain panorama photograph
Piece.Due to have passed through aforesaid exposure adjustment, therefore, the exposure of each several part in finally obtained distant view photograph before synthesis
Degree is not in notable difference, and this exposure is basically identical, thus having obtained high-quality distant view photograph.
The embodiment of the present invention first passes through panorama camera and shoots multiple historical photographs, enters column hisgram to multiple historical photographs and divides
Analysis and Luminance Analysis to obtain optimum histogram curve, and this optimum histogram curve is carried out numerical value collection and machine learning with
Obtain goal histogram curve.When shooting next photo again by panorama camera, can be according to above-mentioned goal histogram curve
Current photo is exposed adjust, again the photo after adjustment is synthesized to obtain distant view photograph afterwards.Due to obtaining
Take into full account during goal histogram curve in panorama camera and be in the camera of different shooting angles (as phototropic face
Camera lens with shady face) problem that differs of taken a picture depth of exposure, involved dark portion, ash portion in this goal histogram curve
And highlights part is optimum, therefore current photo is exposed adjust according to this goal histogram curve, so that place
The exposure taken a picture in the camera of different angles is basically identical, thus improve the matter through synthesizing the distant view photograph obtaining
Amount.
Refer to Figure 11 again, be a kind of structural representation of image processing terminal that first embodiment of the invention provides, such as
Shown in figure, this terminal includes：
Acquiring unit 10, for obtaining multiple current photos captured by panorama camera, historical photograph and goal histogram
Curve, this panorama camera includes the camera of at least two different directions, and every current photo is by each shooting of panorama camera
Head is captured；Wherein, as it was previously stated, goal histogram curve can be analyzed institute by the historical photograph captured by panorama camera
, may also be and in advance this goal histogram curve is stored in the terminal of execution the present embodiment method；Or, when this reality of execution
Apply a method terminal obtain multiple current photos after, the mesh being stored on other-end can be obtained by way of network call
Mark histogram curve；
Adjustment unit 11, for being exposed to current photo adjusting according to goal histogram curve.
The embodiment of the present invention first passes through the current photo captured by acquiring unit 10 acquisition panorama camera, then it is straight to obtain target
Square figure curve, is exposed to current photo adjusting according to goal histogram curve finally by adjustment unit 11, thus solving
It is in camera (as the camera lens of the phototropic face and shady face) depth of exposure of taking a picture of different shooting angles in panorama camera
The problem differing, and then improve distant view photograph quality.
Refer to Figure 12 again, be a kind of structural representation of image processing terminal that second embodiment of the invention provides,
On the basis of terminal shown in Figure 11, as illustrated, this terminal also includes：
Extraction unit 22, extracts for multiple historical photographs are entered with column hisgram to obtain multiple original histograms；
Signal generating unit 23, for generating a plurality of original histogram curve according to multiple original histograms；
Extension unit 24, for adjusting each original histogram curve so that each original histogram equably extends
To whole distributed areas, wherein, distributed areas are the region in x-axis and y-axis, and x-axis represents black in photo, grey and white
Color, y-axis represents black, the grey and white accounting in photo；
Analytic unit 25, analyzes for carrying out brightness contrast to multiple original histograms after extending to obtain optimum Nogata
Figure curve；
Collection unit 26 is straight to obtain target for carrying out numerical value collection and machine learning to optimum histogram curve
Square figure curve.
Further, analytic unit 25 operates specifically for execution is following：
Luminance Analysis are carried out to obtain multiple dark portion histograms, ash portion histogram to each original histogram after extending
And highlights histogram；
Contrast multiple dark portion histograms, ash portion histogram and highlights histogram to obtain optimum dark portion histogram, optimal grey
Portion's histogram and optimum highlights histogram；
Generate optimal grey portion curve according to the optimum dark portion curve of optimum dark portion histogram generation, according to optimal grey portion histogram
And optimum highlights curve is generated according to optimum highlights histogram；
Optimum histogram curve is generated according to optimum dark portion curve, optimal grey portion curve and optimum highlights curve.
Further, collection unit 26 operates specifically for execution is following：
The quantization that optimum histogram curve is carried out with x-axis and y-axis is to obtain x-axis numerical value and y-axis numerical value；
According to x-axis numerical value and y-axis numeric renderings matched curve；
Matched curve is carried out with machine learning to obtain goal histogram curve.
It should be noted that acquiring unit 10 in acquiring unit 20 in the present embodiment and adjustment unit 21 and Figure 11 and
Adjustment unit 11 is similar to, therefore will not be described here.
The embodiment of the present invention first passes through acquiring unit 20 and obtains panorama camera multiple historical photographs captured, to multiple history
Photo carries out histogram analysis and Luminance Analysis to obtain optimum histogram curve, and carries out numerical value to this optimum histogram curve
Collection and machine learning are to obtain goal histogram curve.Shoot next photograph when obtaining panorama camera again by acquiring unit 20
During piece, current photo can be exposed adjust according to above-mentioned goal histogram curve by adjustment unit 21.Due to obtaining
Take into full account during goal histogram curve in panorama camera and be in the camera of different shooting angles (as phototropic face
Camera lens with shady face) problem that differs of taken a picture depth of exposure, involved dark portion, ash portion in this goal histogram curve
And highlights part is optimum, therefore current photo is exposed adjust according to this goal histogram curve, so that place
The exposure taken a picture in the camera of different angles is basically identical, thus providing quality for the synthesis of follow-up distant view photograph
Ensure.
Refer to Figure 13 again, be a kind of structural representation of image processing terminal that third embodiment of the invention provides,
On the basis of terminal shown in Figure 12, as illustrated, this terminal also includes：
Synthesis unit 37, for multiple current photos after synthesis exposure adjustment to obtain distant view photograph.
It should be noted that acquiring unit 30 in the present embodiment, adjustment unit 31, extraction unit 32, signal generating unit 33,
Acquiring unit 20 in extension unit 34, analytic unit 35 and collection unit 36 and Figure 12, adjustment unit 21, extraction unit
22nd, signal generating unit 23, extension unit 24, analytic unit 25 and collection unit 26 are similar to, therefore will not be described here.
Need further exist for illustrating, the specific workflow of terminal shown in Figure 11 to Figure 13 is in aforesaid method napex
Divide and have been described in detail, therefore will not be described here.
The embodiment of the present invention first passes through multiple historical photographs captured by acquiring unit 30 acquisition panorama camera, and multiple are gone through
History photo carries out histogram analysis and Luminance Analysis to obtain optimum histogram curve, and enters line number to this optimum histogram curve
Value collection and machine learning are to obtain goal histogram curve.When shooting next photo again by panorama camera, can pass through
Adjustment unit 31 is exposed to current photo adjusting according to above-mentioned goal histogram curve, passes through synthesis unit 37 afterwards more right
Photo after adjustment is synthesized to obtain distant view photograph.Due to taking into full account during obtaining goal histogram curve
It is in camera (as the camera lens of the phototropic face and shady face) depth of exposure of taking a picture of different shooting angles in panorama camera
The problem differing, in this goal histogram curve, involved dark portion, ash portion and highlights part are optimum, therefore according to this mesh
Mark histogram curve is exposed to current photo adjusting, so that the exposure that the camera being in different angles is taken a picture
Degree is basically identical, thus improve the quality through synthesizing the distant view photograph obtaining.
Figure 14 is a kind of structural representation of the terminal providing in the embodiment of the present invention, as illustrated, this terminal includes：Extremely
A few processor 401, such as CPU (Central Processing Unit, central processing unit), at least one user interface
403, memory 404, at least one communication bus 402.Wherein, communication bus 402 is used for realizing the connection between these assemblies
Communication.Wherein, user interface 403 can include display screen (Display), keyboard (Keyboard), and optional user interface 403 is also
Wireline interface, the wave point of standard can be included.Memory 404 can be high-speed RAM memory (Ramdom Access
Memory, effumability random access memory) or non-labile memory (non-volatile memory),
For example, at least one magnetic disc store.Memory 404 optionally can also be that at least one is located remotely from aforementioned processor 401
Storage device.Wherein processor 401 can in conjunction with Figure 11 to 13 described by terminal, in memory 404 store batch processing generation
Code, and processor 401 calls the program code of storage in memory 404, for executing following operation：
Obtain multiple current photos captured by panorama camera, panorama camera includes the shooting of at least two different directions
Head, every current photo is captured by each camera of described panorama camera；
Obtain goal histogram curve；
Current photo is exposed adjust according to goal histogram curve.
Further, processor 401 is also operated with execution is following：
Obtain multiple historical photographs captured by panorama camera；
Multiple historical photographs are entered with column hisgram extract to obtain multiple original histograms；
A plurality of original histogram curve is generated according to multiple original histograms；
Adjust each original histogram curve so that each original histogram is equably extended to whole distributed areas,
Wherein, distributed areas are the region in x-axis and y-axis, and x-axis represents black in photo, grey and white, and y-axis represents black, ash
The color and white accounting in photo；
Carry out brightness contrast to multiple original histograms after extending to analyze to obtain optimum histogram curve；
Optimum histogram curve is carried out with numerical value collection and machine learning to obtain goal histogram curve.
Specifically, processor 401 operates specifically for execution is following：
Luminance Analysis are carried out to obtain multiple dark portion histograms, ash portion histogram to each original histogram after extending
And highlights histogram；
Contrast multiple dark portion histograms, ash portion histogram and highlights histogram to obtain optimum dark portion histogram, optimal grey
Portion's histogram and optimum highlights histogram；
Generate optimal grey portion curve according to the optimum dark portion curve of optimum dark portion histogram generation, according to optimal grey portion histogram
And optimum highlights curve is generated according to optimum highlights histogram；
Optimum histogram curve is generated according to optimum dark portion curve, optimal grey portion curve and optimum highlights curve.
Specifically, processor 401 operates specifically for execution is following：
The quantization that optimum histogram curve is carried out with x-axis and y-axis is to obtain x-axis numerical value and y-axis numerical value；
According to x-axis numerical value and y-axis numeric renderings matched curve；
Matched curve is carried out with machine learning to obtain goal histogram curve.
Further, processor 401 is additionally operable to execute following operation：
Multiple current photos after synthesis exposure adjustment are to obtain distant view photograph.
Those of ordinary skill in the art are it is to be appreciated that combine the list of each example of the embodiments described herein description
Unit and algorithm steps, can be with electronic hardware, computer software or the two be implemented in combination in, in order to clearly demonstrate hardware
With the interchangeability of software, generally describe composition and the step of each example in the above description according to function.This
A little functions to be executed with hardware or software mode actually, the application-specific depending on technical scheme and design constraint.Specially
Industry technical staff can use different methods to each specific application realize described function, but this realization is not
It is considered as beyond the scope of this invention.
Additionally, it should be understood that disclosed, terminal and method in several embodiments provided herein, permissible
Realize by another way.For example, device embodiment described above is only schematically, for example, described unit
Divide, only a kind of division of logic function, actual can have other dividing mode when realizing, for example multiple units or assembly
Can in conjunction with or be desirably integrated into another system, or some features can be ignored, or does not execute.In addition, it is shown or beg for
By coupling each other or direct-coupling or communication connection can be INDIRECT COUPLING by some interfaces, device or unit
Or communication connection or electricity, machinery or other forms connect.
The described unit illustrating as separating component can be or may not be physically separate, show as unit
The part showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected according to the actual needs to realize embodiment of the present invention scheme
Purpose.
In addition, can be integrated in a processing unit in each functional unit in each embodiment of the present invention it is also possible to
It is that unit is individually physically present or two or more units are integrated in a unit.Above-mentioned integrated
Unit both can be to be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
Step in present invention method can carry out order according to actual needs and adjust, merges and delete.
Unit in embodiment of the present invention terminal can merge according to actual needs, divides and delete.
The above, the only specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, and any
Those familiar with the art the invention discloses technical scope in, various equivalent modifications can be readily occurred in or replace
Change, these modifications or replacement all should be included within the scope of the present invention.Therefore, protection scope of the present invention should be with right
The protection domain requiring is defined.
Claims (10)
1. a kind of image processing method is it is characterised in that include：
Obtain multiple current photos captured by panorama camera, described panorama camera includes the shooting of at least two different directions
Head, every described current photo is captured by each described camera of described panorama camera；
Obtain goal histogram curve；
Described current photo is exposed adjust according to described goal histogram curve.
2. the method for claim 1 specifically includes it is characterised in that obtaining goal histogram curve：
Obtain multiple the described historical photographs captured by described panorama camera；
Historical photograph multiple described is entered with column hisgram extract to obtain multiple original histograms；
Generate a plurality of original histogram curve according to multiple described original histograms；
Each described original histogram curve of adjustment is so that each Zhang Suoshu original histogram is equably extended to whole distribution
Region, wherein, described distributed areas are the region in x-axis and y-axis, and x-axis represents black in photo, grey and white, y-axis table
Show black, the grey and white accounting in photo；
Multiple described original histograms after extending are carried out with brightness contrast analysis to obtain described optimum histogram curve；
Numerical value collection and machine learning are carried out to obtain described goal histogram curve to described optimum histogram curve.
3. method as claimed in claim 2 is it is characterised in that carry out brightness pair to multiple the described original histograms after extending
Specifically included with obtaining described optimum histogram curve than analysis：
Luminance Analysis are carried out to obtain multiple dark portion histograms, ash portion histogram to each Zhang Suoshu original histogram after extending
And highlights histogram；
Contrast multiple described dark portion histograms, ash portion histogram and highlights histogram to obtain optimum dark portion histogram, optimal grey
Portion's histogram and optimum highlights histogram；
Generate optimal grey portion according to the optimum dark portion curve of described optimum dark portion histogram generation, according to described optimal grey portion histogram
Curve and optimum highlights curve is generated according to described optimum highlights histogram；
Described optimum histogram curve is generated according to described optimum dark portion curve, optimal grey portion curve and optimum highlights curve.
4. method as claimed in claim 3, carries out numerical value collection and machine learning to obtain to described optimum histogram curve
Described goal histogram curve specifically includes：
The quantization of x-axis and y-axis is carried out to obtain x-axis numerical value and y-axis numerical value to described optimum histogram curve；
According to described x-axis numerical value and y-axis numeric renderings matched curve；
Described matched curve is carried out with machine learning to obtain described goal histogram curve.
5. the method as described in any one of claim 1-4 is it is characterised in that also include：
Multiple described current photos after synthesis exposure adjustment are to obtain distant view photograph.
6. a kind of terminal is it is characterised in that include：
Acquiring unit, for obtaining multiple current photos and the goal histogram curve captured by panorama camera, described panorama phase
Machine includes the camera of at least two different directions, and every described current photo is by each described camera of described panorama camera
Captured；
Adjustment unit, for being exposed to described current photo adjusting according to described goal histogram curve.
7. terminal as claimed in claim 6 is it is characterised in that described acquiring unit is additionally operable to obtain described panorama camera and is clapped
Multiple the described historical photographs taken the photograph, described terminal also includes：
Extraction unit, extracts for historical photograph multiple described is entered with column hisgram to obtain multiple original histograms；
Signal generating unit, for generating a plurality of original histogram curve according to multiple described original histograms；
Extension unit, for adjusting each described original histogram curve so that each Zhang Suoshu original histogram equably prolongs
Open up whole distributed areas, wherein, described distributed areas are the region in x-axis and y-axis, and x-axis represents black in photo, grey
And white, y-axis represents black, the grey and white accounting in photo；
Analytic unit is described optimum straight to obtain for multiple the described original histograms after extending are carried out with brightness contrast analysis
Square figure curve；
Collection unit, for carrying out numerical value collection and machine learning to obtain described target to described optimum histogram curve
Histogram curve.
8. terminal as claimed in claim 7 is it is characterised in that described analytic unit is used for：
Luminance Analysis are carried out to obtain multiple dark portion histograms, ash portion histogram to each Zhang Suoshu original histogram after extending
And highlights histogram；
Contrast multiple described dark portion histograms, ash portion histogram and highlights histogram to obtain optimum dark portion histogram, optimal grey
Portion's histogram and optimum highlights histogram；
Generate optimal grey portion according to the optimum dark portion curve of described optimum dark portion histogram generation, according to described optimal grey portion histogram
Curve and optimum highlights curve is generated according to described optimum highlights histogram；
Described optimum histogram curve is generated according to described optimum dark portion curve, optimal grey portion curve and optimum highlights curve.
9. terminal as claimed in claim 8 is it is characterised in that described collection unit is used for described optimum histogram song
Line carries out the quantization of x-axis and y-axis to obtain x-axis numerical value and y-axis numerical value, bent according to described x-axis numerical value and y-axis numeric renderings matching
Line and described matched curve is carried out with machine learning to obtain described goal histogram curve.
10. the terminal as described in any one of claim 6-9 is it is characterised in that described terminal also includes：
Synthesis unit, for multiple the described current photos after synthesis exposure adjustment to obtain distant view photograph.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610923647.0A CN106454096A (en) | 2016-10-29 | 2016-10-29 | Image processing method and terminal thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610923647.0A CN106454096A (en) | 2016-10-29 | 2016-10-29 | Image processing method and terminal thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106454096A true CN106454096A (en) | 2017-02-22 |
Family
ID=58175830
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610923647.0A Withdrawn CN106454096A (en) | 2016-10-29 | 2016-10-29 | Image processing method and terminal thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106454096A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610045A (en) * | 2017-09-20 | 2018-01-19 | 北京维境视讯信息技术有限公司 | Luminance compensation method, device, equipment and storage medium in the splicing of flake picture |
| CN108924525A (en) * | 2018-06-06 | 2018-11-30 | 平安科技（深圳）有限公司 | Brightness of image method of adjustment, device, computer equipment and storage medium |
| WO2019061020A1 (en) * | 2017-09-26 | 2019-04-04 | 深圳市大疆创新科技有限公司 | Image generation method, image generation device, and machine readable storage medium |
| CN110475072A (en) * | 2017-11-13 | 2019-11-19 | Oppo广东移动通信有限公司 | Shoot method, apparatus, terminal and the storage medium of image |
| CN111083356A (en) * | 2019-12-05 | 2020-04-28 | 河北汉光重工有限责任公司 | Method for adjusting light in panoramic image shooting process |
| CN111741228A (en) * | 2020-06-30 | 2020-10-02 | 浙江大华技术股份有限公司 | Exposure adjusting method and device for panoramic image |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102694981A (en) * | 2012-05-11 | 2012-09-26 | 中国科学院西安光学精密机械研究所 | Automatic exposure method for histogram equalization based on adaptive threshold segmentation |
| CN104065863A (en) * | 2013-03-19 | 2014-09-24 | 腾讯科技（深圳）有限公司 | Image processing method and processing device |
| CN105827995A (en) * | 2016-03-30 | 2016-08-03 | 金三立视频科技（深圳）有限公司 | Automatic exposure method and system based on histogram |
| CN105915811A (en) * | 2016-04-08 | 2016-08-31 | 深圳英飞拓科技股份有限公司 | Image strong light inhibition adaptation control method and device |
| CN105981360A (en) * | 2014-02-13 | 2016-09-28 | 株式会社理光 | Image processing apparatus, image processing system, image processing method and recording medium |
| CN106034210A (en) * | 2015-03-09 | 2016-10-19 | 华为技术有限公司 | Image editing method and image editing device |
-
2016
- 2016-10-29 CN CN201610923647.0A patent/CN106454096A/en not_active Withdrawn
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102694981A (en) * | 2012-05-11 | 2012-09-26 | 中国科学院西安光学精密机械研究所 | Automatic exposure method for histogram equalization based on adaptive threshold segmentation |
| CN104065863A (en) * | 2013-03-19 | 2014-09-24 | 腾讯科技（深圳）有限公司 | Image processing method and processing device |
| CN105981360A (en) * | 2014-02-13 | 2016-09-28 | 株式会社理光 | Image processing apparatus, image processing system, image processing method and recording medium |
| CN106034210A (en) * | 2015-03-09 | 2016-10-19 | 华为技术有限公司 | Image editing method and image editing device |
| CN105827995A (en) * | 2016-03-30 | 2016-08-03 | 金三立视频科技（深圳）有限公司 | Automatic exposure method and system based on histogram |
| CN105915811A (en) * | 2016-04-08 | 2016-08-31 | 深圳英飞拓科技股份有限公司 | Image strong light inhibition adaptation control method and device |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610045A (en) * | 2017-09-20 | 2018-01-19 | 北京维境视讯信息技术有限公司 | Luminance compensation method, device, equipment and storage medium in the splicing of flake picture |
| CN107610045B (en) * | 2017-09-20 | 2021-02-05 | 北京字节跳动网络技术有限公司 | Brightness compensation method, device and equipment in fisheye picture splicing and storage medium |
| WO2019061020A1 (en) * | 2017-09-26 | 2019-04-04 | 深圳市大疆创新科技有限公司 | Image generation method, image generation device, and machine readable storage medium |
| CN110475072A (en) * | 2017-11-13 | 2019-11-19 | Oppo广东移动通信有限公司 | Shoot method, apparatus, terminal and the storage medium of image |
| CN110475072B (en) * | 2017-11-13 | 2021-03-09 | Oppo广东移动通信有限公司 | Method, device, terminal and storage medium for shooting image |
| US11412153B2 (en) | 2017-11-13 | 2022-08-09 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Model-based method for capturing images, terminal, and storage medium |
| CN108924525A (en) * | 2018-06-06 | 2018-11-30 | 平安科技（深圳）有限公司 | Brightness of image method of adjustment, device, computer equipment and storage medium |
| CN108924525B (en) * | 2018-06-06 | 2021-07-06 | 平安科技（深圳）有限公司 | Image brightness adjusting method and device, computer equipment and storage medium |
| CN111083356A (en) * | 2019-12-05 | 2020-04-28 | 河北汉光重工有限责任公司 | Method for adjusting light in panoramic image shooting process |
| CN111741228A (en) * | 2020-06-30 | 2020-10-02 | 浙江大华技术股份有限公司 | Exposure adjusting method and device for panoramic image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106454096A (en) | Image processing method and terminal thereof | |
| US10841551B2 (en) | User feedback for real-time checking and improving quality of scanned image | |
| CN103414844B (en) | Video jitter modification method and device | |
| US10532271B2 (en) | Data processing method for reactive augmented reality card game and reactive augmented reality card game play device, by checking collision between virtual objects | |
| EP2843625B1 (en) | Method for synthesizing images and electronic device thereof | |
| US20180041692A1 (en) | Automatic Camera Adjustment Method and Electronic Device | |
| EP2696573A2 (en) | Method for generating a panoramic image, user terminal device, and computer-readable recording medium | |
| CN107464266B (en) | Method, device and equipment for correcting camera calibration parameters and storage medium | |
| EP1895469A2 (en) | Image display apparatus, image display method, and image display program | |
| US20170332009A1 (en) | Devices, systems, and methods for a virtual reality camera simulator | |
| US9058655B2 (en) | Region of interest based image registration | |
| JP2022541977A (en) | Image labeling method, device, electronic device and storage medium | |
| CN107395958A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN104580883B (en) | Image processing apparatus, image processing method and recording medium | |
| US11483463B2 (en) | Adaptive glare removal and/or color correction | |
| CN104915971A (en) | Method and terminal for obtaining color values | |
| EP3327662B1 (en) | Image processing device, image processing method, and program | |
| JP2004362443A (en) | Parameter determination system | |
| Xiong et al. | Color correction for mobile panorama imaging | |
| CN105893578A (en) | Method and device for selecting photos | |
| CN116017129A (en) | Method, device, system, equipment and medium for adjusting angle of light supplementing lamp | |
| CN115529405A (en) | Image display method and device of front camera | |
| CN108702441A (en) | Image processing equipment, image processing system and program | |
| CN108432229A (en) | It is a kind of to realize that other people take pictures the method and photographing device of effect by self-timer | |
| JP5887384B2 (en) | Line image drawing method and apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170222 |
|
| WW01 | Invention patent application withdrawn after publication |