CN105893578A - Method and device for selecting photos - Google Patents
Method and device for selecting photos Download PDFInfo
- Publication number
- CN105893578A CN105893578A CN201610203626.1A CN201610203626A CN105893578A CN 105893578 A CN105893578 A CN 105893578A CN 201610203626 A CN201610203626 A CN 201610203626A CN 105893578 A CN105893578 A CN 105893578A
- Authority
- CN
- China
- Prior art keywords
- photo
- smart machine
- eigenvalue
- value
- opened
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Landscapes
- Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a method and a device for selecting photos. According to the method and the device, the problems that after smart equipment continuously takes photos, a user needs to look up multiple continuously-captured photos one by one to select required photos are solved. The method comprises the following steps that the smart equipment continuously captures through dual cameras on the smart equipment to obtain N photos; for each photo in the N photos, the smart equipment determines a characteristic value of the photo according to a span value corresponding to a field depth of each photo and a brightness value of pixel points contained in the photo; the smart equipment selects at least one photo from the N photos according to the determined characteristic values, and displays the at least one photo on a screen of the smart equipment. After the smart equipment continuously captures multiple photos, the smart equipment can recommend photos for the user from the multiple captured photos according to the characteristic values of the shoot multiple photos, thereby saving the time of selecting the photos by the user, and improving the user experience.
Description
Technical field
The present invention relates to smart machine field, particularly relate to the method and device that a kind of photo selects.
Background technology
Along with the development of camera function in smart machine, smart machine is mounted with dual camera, and intelligence
Equipment can realize being continuously shot multiple pictures.
In the prior art, when, after smart machine continuous photo, user needs multiple continuous photos of leafing through one by one
Select the photo that user needs, waste the time of user, reduce Consumer's Experience.
Summary of the invention
It is an object of the invention to provide the method and device that a kind of photo selects, to solve when smart machine continuous shooting
After photo, user needs to leaf through multiple continuous photos one by one to the problem selecting the photo of needs.
It is an object of the invention to be achieved through the following technical solutions:
A kind of method that photo selects, described method includes:
Smart machine is continuously shot, by the dual camera on described smart machine, the N obtained and opens photo;
Described N is opened to every photo in photo, smart machine according to the depth of field of described photo corresponding across
The brightness value of the pixel comprised in angle value and described photo, determines the eigenvalue of described photo;
Described smart machine, according to the eigenvalue determined, is opened photo from described N, selects at least one photograph
Sheet, and at least one photo described in display on the screen of described smart machine.
Optionally, described N being opened to every photo in photo, smart machine is according to the depth of field of described photo
The brightness value of the pixel comprised in corresponding span value and described photo, determines the eigenvalue of described photo,
Including:
Described smart machine opens in photo the brightness value of the pixel that every photo comprises according to described N, by institute
State N to open photo and be ranked up, determine that every photo opens, at described N, the row that sorting position in photo is corresponding
Sequence value;
Described N being opened to every photo in photo, described smart machine is corresponding according to the depth of field of described photo
The span value ranking value corresponding with described photo, determine described eigenvalue.
Optionally, described N being opened to every photo in photo, described smart machine is according to described photo
The ranking value that span value corresponding to the depth of field is corresponding with described photo, determines described eigenvalue, including:
Described N being opened to every photo in photo, described smart machine is by corresponding for the depth of field of described photo
The ranking value sum that span value is corresponding with described photo, is defined as described eigenvalue;Or
Described N being opened to every photo in photo, described smart machine is by corresponding for the depth of field of described photo
The span value ranking value corresponding with described photo is long-pending, is defined as described eigenvalue.
Optionally, described smart machine opens in photo the bright of pixel that every photo comprises according to described N
Angle value, opens photo by described N and is ranked up, and determines that every photo opens sequence position in photo at described N
Put the ranking value of correspondence, including:
Described smart machine, according to the brightness value of the pixel comprised in described photo, is determined for characterizing
The rectangular histogram of the brightness of pixel;
Described smart machine, according to described rectangular histogram, determines the normal state of the brightness of the pixel of described photo
The variance of distribution;
Described smart machine determines the difference of described variance and the variance of standard normal distribution;
Described N is opened photo and is ranked up, really according to described difference order from big to small by described smart machine
Make every photo and open, at described N, the ranking value that sorting position in photo is corresponding.
Optionally, described smart machine, according to the eigenvalue determined, is opened photo from described N, selects extremely
A few photo, described method includes:
Described smart machine, according to the eigenvalue determined, is opened photo from described N, is selected eigenvalue
Maximum photo;Or
Described smart machine, according to the eigenvalue determined, is opened photo from described N, is selected eigenvalue
Minimum photo.
Based on the inventive concept as method, embodiments provide the device that a kind of photo selects,
Including:
Acquisition module, opens photo for being continuously shot, by the dual camera on smart machine, the N obtained;
Determine module, for opening every photo in photo for described N, according to the depth of field pair of described photo
The brightness value of the pixel comprised in the span value answered and described photo, determines the eigenvalue of described photo;
Select module, for according to the eigenvalue determined, opening photo from described N, select at least one
Photo, and at least one photo described in display on the screen of smart machine.
Optionally, described determine module specifically for:
Open in photo the brightness value of the pixel that every photo comprises according to described N, described N is opened photo
It is ranked up, determines that every photo opens, at described N, the ranking value that sorting position in photo is corresponding;
Described N is opened to every photo in photo, the span value corresponding according to the depth of field of described photo and institute
State the ranking value that photo is corresponding, determine described eigenvalue.
Optionally, described determine module specifically for:
Described N is opened to every photo in photo, by span value corresponding for the depth of field of described photo and described
The ranking value sum that photo is corresponding, is defined as described eigenvalue;Or
Described N is opened to every photo in photo, by span value corresponding for the depth of field of described photo and described
The ranking value that photo is corresponding is long-pending, is defined as described eigenvalue.
Optionally, described determine that module is specifically additionally operable to:
According to the brightness value of the pixel comprised in described photo, determine brightness for characterizing pixel
Rectangular histogram;
According to described rectangular histogram, determine the variance of the normal distribution of the brightness of the pixel of described photo;
Determine the difference of described variance and the variance of standard normal distribution;
Described N opens photo be ranked up according to described difference order from big to small, determine every photo
The ranking value that sorting position in photo is corresponding is opened at described N.
Optionally, described selection module specifically for:
According to the eigenvalue determined, open photo from described N, select the photo that eigenvalue is maximum;
Or
According to the eigenvalue determined, open photo from described N, select the photo that eigenvalue is minimum.
In the method and apparatus that the embodiment of the present invention provides, smart machine is taken the photograph by double on described smart machine
Photo is opened as head is continuously shot the N obtained;Described N is opened to every photo in photo, smart machine
The brightness value of the pixel comprised in span value that the depth of field according to described photo is corresponding and described photo, determines
The eigenvalue of described photo;Described smart machine, according to the eigenvalue determined, is opened photo from described N,
Select at least one photo, and at least one photo described in display on the screen of described smart machine.Work as intelligence
After energy equipment continuous shooting multiple pictures, smart machine can be according to the eigenvalue of captured multiple pictures, from institute
In the multiple pictures of shooting, recommend photo for user, thus saved user and selected the time of photo, improve
Consumer's Experience.
Accompanying drawing explanation
The method flow diagram that a kind of photo that Fig. 1 provides for the embodiment of the present invention selects;
The rectangular histogram of a kind of photo that Fig. 2 provides for the embodiment of the present invention;
A kind of standard normal distribution figure that Fig. 3 provides for the embodiment of the present invention;
The method flow diagram that the another kind of photo that Fig. 4 provides for the embodiment of the present invention selects;
The device schematic diagram that a kind of photo that Fig. 5 provides for the embodiment of the present invention selects.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the present invention
Accompanying drawing in embodiment, is clearly and completely described the technical scheme in the embodiment of the present invention, it is clear that
Described embodiment is a part of embodiment of the present invention rather than whole embodiments.Based in the present invention
Embodiment, those of ordinary skill in the art obtained under not making creative work premise all its
His embodiment, broadly falls into the scope of protection of the invention.
Below in conjunction with accompanying drawing, the technical scheme providing the embodiment of the present invention is described in detail.
Embodiments provide a kind of method that photo selects, as it is shown in figure 1, include operating as follows:
Step 100, smart machine are continuously shot, by the dual camera on described smart machine, the N obtained and open
Photo.
Wherein, described N is the positive integer more than 1.
Step 110, described N being opened to every photo in photo, smart machine is according to the scape of described photo
The brightness value of the pixel comprised in deep corresponding span value and described photo, determines the feature of described photo
Value.
Wherein, when the depth of field of described photo refers to shoot described photo in dual camera before the focus of main photographic head
After can the scope of blur-free imaging, the span value that the depth of field of described photo is corresponding is maxima and minima in the depth of field
Difference, the difference of the maxima and minima in the most described scope.Such as, the depth of field of photo is [7,300],
Then span value is 300-7=293.
Step 120, described smart machine, according to the eigenvalue determined, are opened photo from described N, select
At least one photo, and at least one photo described in display on the screen of described smart machine.
Wherein, on the screen of described smart machine described in display during at least one photo, choosing can only be shown
The thumbnail of the photo selected out;Can also show that described N opens the thumbnail of photo, and the photo that will select
Before being arranged in, to how showing that the photo selected does not limits in the embodiment of the present invention.
In the embodiment of the present invention, smart machine is continuously shot by the dual camera on described smart machine and obtains
N open photo;Described N being opened to every photo in photo, smart machine is according to the scape of described photo
The brightness value of the pixel comprised in deep corresponding span value and described photo, determines the feature of described photo
Value;Described smart machine, according to the eigenvalue determined, is opened photo from described N, selects at least one photograph
Sheet, and at least one photo described in display on the screen of described smart machine.When smart machine continuous shooting multiple
After photo, smart machine can be according to the eigenvalue of captured multiple pictures, from captured multiple pictures
In, recommend photo for user, thus saved user and selected the time of photo, improve Consumer's Experience.
Certainly can also the saturation of pixel by comprising in described photo, tone in the embodiment of the present invention
Deng the span value corresponding with the depth of field of described photo, determine described eigenvalue;The embodiment of the present invention is to it not
Limit.
In a kind of possible implementation, described smart machine is according to span value corresponding to the depth of field of described photo
With the brightness value of the pixel comprised in described photo, determine described eigenvalue, including:
Described smart machine opens in photo the brightness value of the pixel that every photo comprises according to described N, by institute
State N to open photo and be ranked up, determine that every photo opens, at described N, the row that sorting position in photo is corresponding
Sequence value;
Described N being opened to every photo in photo, described smart machine is corresponding according to the depth of field of described photo
The span value ranking value corresponding with described photo, determine described eigenvalue.
In the embodiment of the present invention, described smart machine is according to span value corresponding to the depth of field of described photo and described
Ranking value, determines described eigenvalue, can realize by the way of following two is possible:
Mode one, described N being opened to every photo in photo, described smart machine is by the scape of described photo
The ranking value sum that deep corresponding span value is corresponding with described photo, is defined as the eigenvalue of described photo;Close
It is that expression formula is as follows:
Ti=Di+Pi;
Wherein, TiRepresent the eigenvalue of i-th photo, DiRepresent the span that the depth of field of i-th photo is corresponding
Value, PiThe ranking value of i-th photo of expression, i=1 ..., N.
Mode two, described N being opened to every photo in photo, described smart machine is by the scape of described photo
The ranking value that the span value of deep correspondence is corresponding with described photo is long-pending, is defined as described eigenvalue;Relationship expression
Formula is as follows:
Ti=Di*Pi;
Wherein, TiRepresent the eigenvalue of i-th photo, DiRepresent the span that the depth of field of i-th photo is corresponding
Value, PiThe ranking value of i-th photo of expression, i=1 ..., N.
In a kind of optional embodiment, described smart machine is opened every photo in photo according to described N and is comprised
The brightness value of pixel, described N is opened photo and is ranked up, determine that every photo is opened at described N
The ranking value that in photo, sorting position is corresponding, including:
Described smart machine, according to the brightness value of the pixel comprised in described photo, is determined for characterizing picture
The rectangular histogram of the brightness of vegetarian refreshments;
Described smart machine, according to described rectangular histogram, determines that the normal state of the brightness of the pixel of described photo is divided
The variance of cloth;
Described smart machine determines the difference of described variance and the variance of standard normal distribution;
Described N is opened photo and is ranked up, really according to described difference order from big to small by described smart machine
Make every photo and open, at described N, the ranking value that sorting position in photo is corresponding.
Illustrate: described photo characterizes the rectangular histogram of the brightness of pixel as in figure 2 it is shown, in Fig. 2, horizontal
Axle represents the brightness value in photo, and brightness value is in the range of [0,255], from left to right, represent from completely black by
Gradual transition is to complete white;The longitudinal axis represents the relative populations of the pixel being in this brightness range in photo.
The normal distribution that described photo is corresponding is determined according to the rectangular histogram shown in Fig. 2, as a example by 5 photos,
Obtain Parameters of Normal Distribution, it is assumed that the variance obtaining 5 photos is respectively 90,100,130,110 and 140.
Standard normal distribution is as shown in Figure 3: N (128,128), wherein mean μ=128, variances sigma ^2=128.
Described 5 photos are respectively 38,28,18,2 and 12 with the difference of standard normal distribution variance, root
It is ranked up according to variance order from big to small, obtains the ranking value of every photo, wherein, the row of photo 1
Sequence value P1Be 1, ranking value P of photo 22Be 2, ranking value P of photo 33Be 3, the sequence of photo 4
Value P4It is 5, ranking value P of photo 55It is 4.
In the embodiment of the present invention, described smart machine, according to the eigenvalue determined, is opened photo from described N,
Select at least one photo, including the optional implementation of the following two kinds:
Mode 1, described smart machine, according to the eigenvalue determined, are opened photo from described N, are selected
The photo that eigenvalue is maximum.
Concrete, brightness and the definition of the photo that eigenvalue is maximum are good.
Under which, specifically include:
Described smart machine is directly opened photo from described N, selects the photo that eigenvalue is maximum;Or
Described smart machine is when receiving the first selection instruction, according to the eigenvalue determined, from described N
Opening in photo, select the photo that eigenvalue is maximum, wherein, described first selects instruction to be used for indicating selection special
The photo that value indicative is maximum.
The instruction that smart machine sends according to user, recommends photo to user, more preferably meets the demand of user,
Improve Consumer's Experience.
Mode 2, described smart machine, according to the eigenvalue determined, are opened photo from described N, are selected
The photo that eigenvalue is minimum.
Concrete, background blurring in the photo that eigenvalue is minimum, when user needs background blurring photo,
Select the photo that eigenvalue is minimum.
Under which, specifically include:
Described smart machine is directly opened photo from described N, selects the photo that eigenvalue is minimum;Or
Described smart machine is when receiving the second selection instruction, according to the eigenvalue determined, from described N
Opening in photo, select the photo that eigenvalue is minimum, wherein, described second selects instruction to be used for indicating selection special
The photo that value indicative is minimum.
The instruction that smart machine sends according to user, recommends photo to user, more preferably meets the demand of user,
Improve Consumer's Experience.
In the embodiment of the present invention, being not limited to both the above situation, smart machine can also select by other means
Selecting photo, such as, smart machine, according to the eigenvalue determined, is opened photo from described N, selects feature
The photo that value is maximum and eigenvalue is minimum;Or smart machine is when receiving the 3rd selection instruction, according to really
The eigenvalue made, opens photo from described N, selects the photo that eigenvalue is maximum and eigenvalue is minimum.
And for example, smart machine according to the eigenvalue determined, described N is opened photo according to eigenvalue from greatly to
Little order is ranked up, and before selecting, M opens photo;Or smart machine is receiving the 3rd selection instruction
Time, according to the eigenvalue determined, described N is opened photo and arranges according to eigenvalue order from big to small
Sequence, before selecting, M opens photo, and wherein, M is the positive integer more than 1.
For another example, smart machine according to the eigenvalue determined, described N is opened photo according to eigenvalue according to from
Being ranked up to little order greatly, after selection, Q opens photo;Or smart machine refers to receiving the 3rd selection
When making, according to the eigenvalue determined, described N is opened photo according to eigenvalue according to order from big to small
Being ranked up, after selection, Q opens photo, and wherein, Q is the positive integer more than 1.
Below by a specific embodiment, the method that a kind of photo providing the embodiment of the present invention selects is entered
Row describes in detail, as shown in Figure 4, and including:
Step 410, smart machine are continuously shot 5 photos.
Step 420, smart machine, according to the brightness of pixel in described 5 photos, determine every photo
Brightness histogram.
According to the brightness histogram of every photo, step 430, smart machine determine that the normal state of every photo is divided
Cloth, determines the variance of every photo normal distribution, it is assumed that the variance of described 5 photos is respectively 90,100,
130,110 and 140.
Step 440, smart machine determine variance and the mark of every photo according to the variance of described 5 photos
The difference of the variance of quasi normal distribution, it is assumed that the variance of standard normal distribution is 128, described 5 photos with
The variance of the difference of standard normal distribution variance respectively photo 1 is 38, the variance of photo 2 is 28, shines
The variance of sheet 3 is 2, the variance of photo 4 is 18 and the variance of photo 5 is 12.
Step 450, smart machine are ranked up according to variance order from big to small, obtain every photo
Ranking value, wherein, ranking value P of photo 11Be 1, ranking value P of photo 22Be 2, the row of photo 3
Sequence value P3Be 5, ranking value P of photo 44Be 3, ranking value P of photo 55It is 4.
Step 460, smart machine determine the span value that the depth of field of every photo in 5 photos is corresponding,
Span value D that the depth of field of photo 1 is corresponding1Be 200, span value D corresponding to the depth of field of photo 22Be 135,
Span value D that the depth of field of photo 3 is corresponding3Be 157, span value D corresponding to the depth of field of photo 44Be 123,
Span value D that the depth of field of photo 5 is corresponding5It is 164.
Step 470, smart machine determine the eigenvalue of 5 photos, the eigenvalue T of photo 11
=P1+D1=201, the eigenvalue T of photo 22=P2+D2=137, the eigenvalue T of photo 33=P3+D3=162,
The eigenvalue T of photo 44=P4+D4=126, the eigenvalue T of photo 55=P5+D5=168.
Step 480, smart machine determine that the photo 1 of eigenvalue maximum shows on screen.
Based on the inventive concept as method, embodiments provide the device that a kind of photo selects,
As it is shown in figure 5, include:
Acquisition module 501, opens photo for being continuously shot, by the dual camera on smart machine, the N obtained;
Determine module 502, for opening every photo in photo for described N, according to the scape of described photo
The brightness value of the pixel comprised in deep corresponding span value and described photo, determines the feature of described photo
Value;
Select module 503, for according to the eigenvalue determined, opening photo from described N, select at least
One photo, and at least one photo described in display on the screen of smart machine.
The device that a kind of photo that the embodiment of the present invention provides selects, including: smart machine is by described intelligence
Dual camera on equipment is continuously shot the N obtained and opens photo;Described N is opened to every photograph in photo
Sheet, smart machine is according to the pixel comprised in span value corresponding to the depth of field of described photo and described photo
Brightness value, determines the eigenvalue of described photo;Described smart machine is according to the eigenvalue determined, from described
N opens in photo, selects at least one photo, and on the screen of described smart machine described in display at least one
Open photo.When, after smart machine continuous shooting multiple pictures, smart machine can be according to captured multiple pictures
Eigenvalue, from captured multiple pictures, recommends photo for user, thus has saved user and selected photo
Time, improve Consumer's Experience.
Optionally, described determine module specifically for:
Open in photo the brightness value of the pixel that every photo comprises according to described N, described N is opened photo
It is ranked up, determines that every photo opens, at described N, the ranking value that sorting position in photo is corresponding;
Described N is opened to every photo in photo, the span value corresponding according to the depth of field of described photo and institute
State the ranking value that photo is corresponding, determine described eigenvalue.
Optionally, described determine module specifically for:
Described N is opened to every photo in photo, by span value corresponding for the depth of field of described photo and described
The ranking value sum that photo is corresponding, is defined as described eigenvalue;Or
Described N is opened to every photo in photo, by span value corresponding for the depth of field of described photo and described
The ranking value that photo is corresponding is long-pending, is defined as described eigenvalue.
Optionally, described determine that module is specifically additionally operable to:
According to the brightness value of the pixel comprised in described photo, determine brightness for characterizing pixel
Rectangular histogram;
According to described rectangular histogram, determine the variance of the normal distribution of the brightness of the pixel of described photo;
Determine the difference of described variance and the variance of standard normal distribution;
Described N opens photo be ranked up according to described difference order from big to small, determine every photo
The ranking value that sorting position in photo is corresponding is opened at described N.
Optionally, described selection module specifically for:
According to the eigenvalue determined, open photo from described N, select the photo that eigenvalue is maximum;
Or
According to the eigenvalue determined, open photo from described N, select the photo that eigenvalue is minimum.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or meter
Calculation machine program product.Therefore, the present invention can use complete hardware embodiment, complete software implementation or knot
The form of the embodiment in terms of conjunction software and hardware.And, the present invention can use and wherein wrap one or more
Computer-usable storage medium containing computer usable program code (include but not limited to disk memory,
CD-ROM, optical memory etc.) form of the upper computer program implemented.
The present invention is with reference to method, equipment (system) and computer program product according to embodiments of the present invention
The flow chart of product and/or block diagram describe.It should be understood that can by computer program instructions flowchart and
/ or block diagram in each flow process and/or flow process in square frame and flow chart and/or block diagram and/
Or the combination of square frame.These computer program instructions can be provided to general purpose computer, special-purpose computer, embedding
The processor of formula datatron or other programmable data processing device is to produce a machine so that by calculating
The instruction that the processor of machine or other programmable data processing device performs produces for realizing at flow chart one
The device of the function specified in individual flow process or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions may be alternatively stored in and computer or the process of other programmable datas can be guided to set
In the standby computer-readable memory worked in a specific way so that be stored in this computer-readable memory
Instruction produce and include the manufacture of command device, this command device realizes in one flow process or multiple of flow chart
The function specified in flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions also can be loaded in computer or other programmable data processing device, makes
Sequence of operations step must be performed to produce computer implemented place on computer or other programmable devices
Reason, thus the instruction performed on computer or other programmable devices provides for realizing flow chart one
The step of the function specified in flow process or multiple flow process and/or one square frame of block diagram or multiple square frame.
Although preferred embodiments of the present invention have been described, but those skilled in the art once know base
This creativeness concept, then can make other change and amendment to these embodiments.So, appended right is wanted
Ask and be intended to be construed to include preferred embodiment and fall into all changes and the amendment of the scope of the invention.
Obviously, those skilled in the art can carry out various change and modification without deviating from this to the present invention
Bright spirit and scope.So, if the present invention these amendment and modification belong to the claims in the present invention and
Within the scope of its equivalent technologies, then the present invention is also intended to comprise these change and modification.
Claims (10)
1. the method that a photo selects, it is characterised in that described method includes:
Smart machine is continuously shot, by the dual camera on described smart machine, the N obtained and opens photo;
Described N being opened to every photo in photo, described smart machine is corresponding according to the depth of field of described photo
Span value and described photo in the brightness value of pixel that comprises, determine the eigenvalue of described photo;
Described smart machine, according to the eigenvalue determined, is opened photo from described N, selects at least one
Photo, and at least one photo described in display on the screen of described smart machine.
Method the most according to claim 1, it is characterised in that for described N open in photo every
Photo, described smart machine is according to comprising in span value corresponding to the depth of field of described photo and described photo
The brightness value of pixel, determines the eigenvalue of described photo, including:
Described smart machine opens in photo the brightness value of the pixel that every photo comprises according to described N, by institute
State N to open photo and be ranked up, determine that every photo opens, at described N, the row that sorting position in photo is corresponding
Sequence value;
Described N being opened to every photo in photo, described smart machine is corresponding according to the depth of field of described photo
The span value ranking value corresponding with described photo, determine described eigenvalue.
Method the most according to claim 2, it is characterised in that for described N open in photo every
Photo, described smart machine is according to the span value that the depth of field of described photo the is corresponding row corresponding with described photo
Sequence value, determines described eigenvalue, including:
Described N being opened to every photo in photo, described smart machine is by corresponding for the depth of field of described photo
The ranking value sum that span value is corresponding with described photo, is defined as described eigenvalue;Or
Described N being opened to every photo in photo, described smart machine is by corresponding for the depth of field of described photo
The span value ranking value corresponding with described photo is long-pending, is defined as described eigenvalue.
Method the most according to claim 3, it is characterised in that described smart machine is according to described N
In photo, the brightness value of the pixel that every photo comprises, opens photo by described N and is ranked up, determine
Every photo opens, at described N, the ranking value that sorting position in photo is corresponding, including:
Described smart machine, according to the brightness value of the pixel comprised in described photo, is determined for characterizing
The rectangular histogram of the brightness of pixel;
Described smart machine, according to described rectangular histogram, determines the normal state of the brightness of the pixel of described photo
The variance of distribution;
Described smart machine determines the difference of described variance and the variance of standard normal distribution;
Described N is opened photo and is ranked up, really according to described difference order from big to small by described smart machine
Make every photo and open, at described N, the ranking value that sorting position in photo is corresponding.
5. according to the method according to any one of Claims 1 to 4, it is characterised in that described smart machine
According to the eigenvalue determined, open photo from described N, select at least one photo, including:
Described smart machine, according to the eigenvalue determined, is opened photo from described N, is selected eigenvalue
Maximum photo;Or
Described smart machine, according to the eigenvalue determined, is opened photo from described N, is selected eigenvalue
Minimum photo.
6. the device that a photo selects, it is characterised in that described device includes:
Acquisition module, opens photo for being continuously shot, by the dual camera on smart machine, the N obtained;
Determine module, for opening every photo in photo for described N, according to the depth of field pair of described photo
The brightness value of the pixel comprised in the span value answered and described photo, determines the eigenvalue of described photo;
Select module, for according to the eigenvalue determined, opening photo from described N, select at least one
Photo, and at least one photo described in display on the screen of smart machine.
Device the most according to claim 6, it is characterised in that described determine module specifically for:
Open in photo the brightness value of the pixel that every photo comprises according to described N, described N is opened photo
It is ranked up, determines that every photo opens, at described N, the ranking value that sorting position in photo is corresponding;
Described N is opened to every photo in photo, the span value corresponding according to the depth of field of described photo and institute
State the ranking value that photo is corresponding, determine described eigenvalue.
Device the most according to claim 7, it is characterised in that described determine module specifically for:
Described N is opened to every photo in photo, by span value corresponding for the depth of field of described photo and described
The ranking value sum that photo is corresponding, is defined as described eigenvalue;Or
Described N is opened to every photo in photo, by span value corresponding for the depth of field of described photo and described
The ranking value that photo is corresponding is long-pending, is defined as described eigenvalue.
Device the most according to claim 8, it is characterised in that described determine that module is specifically additionally operable to:
According to the brightness value of the pixel comprised in described photo, determine brightness for characterizing pixel
Rectangular histogram;
According to described rectangular histogram, determine the variance of the normal distribution of the brightness of the pixel of described photo;
Determine the difference of described variance and the variance of standard normal distribution;
Described N opens photo be ranked up according to described difference order from big to small, determine every photo
The ranking value that sorting position in photo is corresponding is opened at described N.
10. according to the device according to any one of claim 6~9, it is characterised in that described selection module
Specifically for:
According to the eigenvalue determined, open photo from described N, select the photo that eigenvalue is maximum;
Or
According to the eigenvalue determined, open photo from described N, select the photo that eigenvalue is minimum.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610203626.1A CN105893578B (en) | 2016-03-31 | 2016-03-31 | A kind of method and device of photo selection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610203626.1A CN105893578B (en) | 2016-03-31 | 2016-03-31 | A kind of method and device of photo selection |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105893578A true CN105893578A (en) | 2016-08-24 |
CN105893578B CN105893578B (en) | 2019-06-18 |
Family
ID=57012117
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610203626.1A Active CN105893578B (en) | 2016-03-31 | 2016-03-31 | A kind of method and device of photo selection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105893578B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018113709A1 (en) * | 2016-12-20 | 2018-06-28 | 宁波舜宇光电信息有限公司 | Array camera module having height difference, circuit board assembly and manufacturing method therefor, and electronic device |
CN111464753A (en) * | 2020-05-21 | 2020-07-28 | 北京小米移动软件有限公司 | Picture shooting method and device and storage medium |
WO2021057752A1 (en) * | 2019-09-29 | 2021-04-01 | 华为技术有限公司 | Image preferential selection method and electronic device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101106699A (en) * | 2006-07-10 | 2008-01-16 | 致伸科技股份有限公司 | Method for deciding kept video in monitoring device |
CN101790047A (en) * | 2009-01-28 | 2010-07-28 | 索尼公司 | Image processing equipment, image management device and image management method and program |
CN104185981A (en) * | 2013-10-23 | 2014-12-03 | 华为终端有限公司 | Method and terminal selecting image from continuous captured image |
CN104954659A (en) * | 2014-03-28 | 2015-09-30 | 宇龙计算机通信科技(深圳)有限公司 | Method and device for processing image information |
-
2016
- 2016-03-31 CN CN201610203626.1A patent/CN105893578B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101106699A (en) * | 2006-07-10 | 2008-01-16 | 致伸科技股份有限公司 | Method for deciding kept video in monitoring device |
CN101790047A (en) * | 2009-01-28 | 2010-07-28 | 索尼公司 | Image processing equipment, image management device and image management method and program |
CN104185981A (en) * | 2013-10-23 | 2014-12-03 | 华为终端有限公司 | Method and terminal selecting image from continuous captured image |
CN104954659A (en) * | 2014-03-28 | 2015-09-30 | 宇龙计算机通信科技(深圳)有限公司 | Method and device for processing image information |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018113709A1 (en) * | 2016-12-20 | 2018-06-28 | 宁波舜宇光电信息有限公司 | Array camera module having height difference, circuit board assembly and manufacturing method therefor, and electronic device |
CN110089105A (en) * | 2016-12-20 | 2019-08-02 | 宁波舜宇光电信息有限公司 | Array camera module and circuit board module and its manufacturing method and electronic equipment with difference in height |
US11128787B2 (en) | 2016-12-20 | 2021-09-21 | Ningbo Sunny Opotech Co., Ltd. | Array camera module having height difference, circuit board assembly and manufacturing method therefor, and electronic device |
US11601576B2 (en) | 2016-12-20 | 2023-03-07 | Ningbo Sunny Opotech Co., Ltd. | Array camera module having height difference, circuit board assembly and manufacturing method therefor, and electronic device |
WO2021057752A1 (en) * | 2019-09-29 | 2021-04-01 | 华为技术有限公司 | Image preferential selection method and electronic device |
CN111464753A (en) * | 2020-05-21 | 2020-07-28 | 北京小米移动软件有限公司 | Picture shooting method and device and storage medium |
CN111464753B (en) * | 2020-05-21 | 2022-04-08 | 北京小米移动软件有限公司 | Picture shooting method and device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN105893578B (en) | 2019-06-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102480245B1 (en) | Automated generation of panning shots | |
CN105247567B (en) | A kind of image focusing device, method, system and non-transient program storage device again | |
CN105872393A (en) | High dynamic range image generation method and device | |
CN103646392B (en) | Backlighting detecting and equipment | |
CN108924427A (en) | A kind of video camera focus method, device and video camera | |
WO2014106445A1 (en) | Method and apparatus for detecting backlight | |
CN102946513A (en) | Method, device and terminal for starting HDR (high-dynamic range) function of shooting device | |
CN107590791A (en) | Image enchancing method and image processing apparatus | |
CN104867125B (en) | Obtain the method and device of image | |
CN108848367A (en) | A kind of method, device and mobile terminal of image procossing | |
CN107172354A (en) | Method for processing video frequency, device, electronic equipment and storage medium | |
CN106157241A (en) | A kind of method and device of Panorama Mosaic | |
CN110349080A (en) | A kind of image processing method and device | |
CN106331505A (en) | Shooting method and device | |
CN116051391B (en) | Image processing method and electronic equipment | |
CN105791793A (en) | Image processing method and electronic device | |
CN109559272A (en) | A kind of image processing method and device, electronic equipment, storage medium | |
CN105893578A (en) | Method and device for selecting photos | |
CN109089045A (en) | A kind of image capture method and equipment and its terminal based on multiple photographic devices | |
CN105556957B (en) | A kind of image processing method, computer storage media, device and terminal | |
CN112449115B (en) | Shooting method and device and electronic equipment | |
CN109064526A (en) | A kind of method and device generating picture mosaic | |
CN109788199B (en) | Focusing method suitable for terminal with double cameras | |
CN114005066B (en) | HDR-based video frame image processing method and device, computer equipment and medium | |
CN108305235B (en) | Method and device for fusing multiple pictures |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |