CN105338339B - Information processing method and electronic equipment - Google Patents
Information processing method and electronic equipment Download PDFInfo
- Publication number
- CN105338339B CN105338339B CN201410367131.3A CN201410367131A CN105338339B CN 105338339 B CN105338339 B CN 105338339B CN 201410367131 A CN201410367131 A CN 201410367131A CN 105338339 B CN105338339 B CN 105338339B
- Authority
- CN
- China
- Prior art keywords
- image
- fuzzy
- fuzzy core
- mapping relations
- energy amount
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The present invention discloses a kind of information processing method and electronic equipment, and methods described includes:The quality information of n the first images and the n the first images is obtained, n is the integer more than 1;N the first fuzzy cores are determined, the n the first fuzzy cores are the fuzzy core based on determined by the n the first images, and determine the nuclear energy amount of the n the first fuzzy cores successively;According to the nuclear energy amount of individual first fuzzy cores of the n and the quality information of the n the first images, the nuclear energy amount of first fuzzy core and the mapping relations of the quality information of described first image are determined;The second image is obtained, determines the second fuzzy core, second fuzzy core is the fuzzy core based on determined by second image, and determines the nuclear energy amount of second fuzzy core;According to the nuclear energy amount of second fuzzy core and the mapping relations, the quality of second image is determined;The present invention being capable of accurate evaluation picture quality.
Description
Technical field
The present invention relates to image processing techniques, more particularly to a kind of information processing method and electronic equipment.
Background technology
There is quick continuous shooting function handheld device at present when taking pictures, because motion and the reason such as out of focus can cause to be continuously shot
Photo occur different degrees of fuzzy, in correlation technique, how in the photo being continuously shot to select fog-level minimum
Photo, i.e., the fog-level of different photos how is determined, to assess photographic quality according to fog-level, there is no corresponding solution party
Case.
The content of the invention
The embodiment of the present invention provides a kind of information processing method and electronic equipment, can accurately determine the fuzzy journey of image
Degree, to assess picture quality.
What the technical scheme of the embodiment of the present invention was realized in:
The embodiment of the present invention provides a kind of information processing method, and methods described includes:
The quality information of n the first images and the n the first images is obtained, n is the integer more than 1;
N the first fuzzy cores are determined, the n the first fuzzy cores is successively based on determined by individual first images of the n
Fuzzy core, and determine the nuclear energy amount of the n the first fuzzy cores;
According to the nuclear energy amount of individual first fuzzy cores of the n and the quality information of the n the first images, it is determined that described
The mapping relations of the nuclear energy amount of first fuzzy core and the quality information of described first image;
The second image is obtained, determines the second fuzzy core, second fuzzy core is based on determined by second image
Fuzzy core, and determine the nuclear energy amount of second fuzzy core;
According to the nuclear energy amount of second fuzzy core and the mapping relations, the quality of second image is determined.
Preferably, the nuclear energy amount for determining n first fuzzy core, including:
By in the n the first fuzzy cores the element of each first fuzzy core square and/or absolute value sum, it is corresponding really
It is set to the nuclear energy amount of first fuzzy core;
Correspondingly, the nuclear energy amount for determining the second fuzzy core, including:
By the element of second fuzzy core square and/or absolute value sum, be defined as the nuclear energy of second fuzzy core
Amount.
Preferably, it is described according to the nuclear energy amount of first fuzzy core and the preset quality of described first image, it is determined that
The mapping relations of the nuclear energy amount of first fuzzy core and the quality of described first image, including:
It is one of any as initial mapping relations function using following form function:Quadratic Map relation function, repeatedly
Mapping relations function and Bezier mapping relations function;
Input using the energy of the n the first fuzzy cores as the mapping relations function, by the n the first images
Output of the quality information as the mapping relations function, the parameter of the mapping relations function is trained;To obtain
Mapping relations function after parameter training.
Preferably, the determination n the first fuzzy cores, including:
For each first image in the n the first images, with the Prior function of fuzzy core, the elder generation is determined successively
Test optimal value of the function on each first image in the n the first images, will successively identified optimal value to should determine that
For the first fuzzy core of the n the first images.
Preferably, methods described also includes:
The nonzero element distribution arrangement of second fuzzy core is determined, identified nonzero element distribution arrangement is defined as
The motion blur direction of second image;
Based on identified motion blur direction, second image is repaired.
The embodiment of the present invention also provides a kind of electronic equipment, and the electronic equipment includes:
First acquisition unit, for obtaining the quality information of n the first images and the n the first images, n be more than
1 integer;
First determining unit, for determining n the first fuzzy cores, the n the first fuzzy cores is successively based on the n
Fuzzy core determined by first image, and determine the nuclear energy amount of the n the first fuzzy cores;
Second determining unit, for the nuclear energy amount according to the n the first fuzzy cores and the n the first images
Quality information, determine the nuclear energy amount of first fuzzy core and the mapping relations of the quality information of described first image;
Second acquisition unit, for obtaining the second image;
3rd determining unit, for determining the second fuzzy core, second fuzzy core is true based on second image institute
Fixed fuzzy core, and determine the nuclear energy amount of second fuzzy core;
4th determining unit, for the nuclear energy amount according to second fuzzy core and the mapping relations, determine described
The quality of two images.
Preferably, second determining unit, it is additionally operable to the member of each first fuzzy core in the n the first fuzzy cores
Element square and/or absolute value sum, correspondence is defined as the nuclear energy amount of first fuzzy core;
3rd determining unit, be additionally operable to by the element of second fuzzy core square and/or absolute value sum, really
It is set to the nuclear energy amount of second fuzzy core.
Preferably, second determining unit, it is additionally operable to one of any as initial mapping using following form function
Relation function:Quadratic Map relation function, multiple mapping relations function and Bezier mapping relations function;
Input using the energy of the n the first fuzzy cores as the mapping relations function, by the n the first images
Output of the quality information as the mapping relations function, the parameter of the mapping relations function is trained;To obtain
Mapping relations function after parameter training.
Preferably, first determining unit, it is additionally operable to for each first image in the n the first images, with
The Prior function of fuzzy core, determine successively the Prior function in the n the first images each first image it is optimal
Value, identified optimal value successively is correspondingly defined as to the first fuzzy core of the n the first images.
Preferably, the electronic equipment also includes:
5th determining unit, for determining the nonzero element distribution arrangement of second fuzzy core, by identified non-zero
Elemental redistribution direction is defined as the motion blur direction of second image;
Unit is repaired, for the motion blur direction based on the determination, second image is repaired.
It is that n the first images determine that the quality information of image and image obscure using existing image in the embodiment of the present invention
Mapping relations between the nuclear energy amount of core, this just establishes the quantization judgment criteria of picture quality, as long as determining quality to be judged
Image (namely second image) fuzzy core nuclear energy amount, it is possible to the quality of the second image is determined based on the mapping relations
Information, the problem of so as to avoid manually judging picture quality inaccuracy.
Brief description of the drawings
Fig. 1 is the implementation process schematic diagram of information processing method in the embodiment of the present invention one;
Fig. 2 is the implementation process schematic diagram of information processing method in the embodiment of the present invention two
Fig. 3 is the implementation process schematic diagram of information processing method in the embodiment of the present invention three;
Fig. 4 is the implementation process schematic diagram of information processing method in the embodiment of the present invention four;
Fig. 5 is the implementation process schematic diagram of information processing method in the embodiment of the present invention five;
Fig. 6 is the structural representation one of electronic equipment in the embodiment of the present invention six;
Fig. 7 is the structural representation two of electronic equipment in the embodiment of the present invention six.
Embodiment
Inventor has found in the practice of the invention, if handled image, obtains the kernel estimates of image
(Kernel Estimation), because kernel estimates reflect a kind of forms of motion, for example image obscures Producing reason, therefore
Kernel estimates can be used for measuring the degree of image shake/fuzzy;And then, if it is possible to fuzzy core is quantified, such as quantified
For nuclear energy amount (Kernel Energy), then the mapping relations that can be established between nuclear energy amount and picture quality, and according to mapping
Relation determines the quality of other images.
The present invention is described in further detail with specific embodiment below in conjunction with the accompanying drawings.
Embodiment one
The present embodiment records a kind of information processing method, the implementation process signal for the information processing method that the present embodiment is recorded
Figure is as shown in figure 1, comprise the following steps:
Step 101, the quality information of n the first images and the n the first images is obtained, n is the integer more than 1.
N the first images are used for determining the mapping relations between the fuzzy core of image and picture quality, so as to root
According to the mapping relations, the quality of the second image is determined.
Step 102, n the first fuzzy cores are determined, the n the first fuzzy cores is successively based on the n the first images
Identified fuzzy core.
Step 103, the nuclear energy amount of the n the first fuzzy cores is determined.
Step 104, according to the nuclear energy amount of the n the first fuzzy cores and the quality information of the n the first images,
Determine the nuclear energy amount of first fuzzy core and the mapping relations of the quality information of described first image.
Step 101 to step 104 is the nuclear energy amount for the fuzzy core that image is determined based on existing image namely n the first images
The process of mapping relations between the quality information of image;In practical application, for determining the first figure of the mapping relations
The quantity of picture can be more than predetermined threshold value, to improve the precision of the mapping relations subsequently determined;Can also be by n the first image bases
Classified (type can be resolution ratio) in different types, to establish different mapping relations based on different types, from
And the quality of the second image is targetedly determined according to the type belonged to of the second image.
Step 105, the second image is obtained, determines the second fuzzy core, second fuzzy core is based on second image
Identified fuzzy core.
Second image is the unknown image of picture quality, the mapping determined in the present embodiment based on step 101 to 104
Relation, determine the quality information of the second image.
Step 106, the nuclear energy amount of second fuzzy core is determined.
Step 106 is that the picture quality of the second image is quantified as to the process of nuclear energy amount.
Step 107, according to the nuclear energy amount of second fuzzy core and the mapping relations, the matter of second image is determined
Amount.
Namely quality information corresponding with the nuclear energy amount of the second fuzzy core is searched in the mapping relations, as the second figure
The quality information of picture.
It is the quality information and image fuzzy core that n the first images determine image using existing image in the present embodiment
Mapping relations between nuclear energy amount, this just establishes the quantization judgment criteria of image quality information, as long as determining quality to be judged
Image (namely second image) fuzzy core nuclear energy amount, it is possible to the quality of the second image is determined based on the mapping relations
Information, the problem of so as to avoid manually judging picture quality inaccuracy.
Embodiment two
The present embodiment records a kind of information processing method, the implementation process signal for the information processing method that the present embodiment is recorded
Figure is as shown in Fig. 2 comprise the following steps:
Step 201, the quality information of n the first images and the n the first images is obtained, n is the integer more than 1.
N the first images are used for determining the mapping relations between the fuzzy core of image and picture quality, so as to root
According to the mapping relations, the quality of the second image is determined.
Step 202, n the first fuzzy cores are determined, the n the first fuzzy cores is successively based on the n the first images
Identified fuzzy core.
Step 203, by the n the first fuzzy cores the element of each first fuzzy core square and/or absolute value
With the corresponding nuclear energy amount for being defined as first fuzzy core.
In practical application, fuzzy core shows as the form of matrix, can be by fuzzy core accordingly, as an example
Element square and/or absolute value sum, as the nuclear energy amount of fuzzy core, be also not limited to above-mentioned shape certainly, in the present embodiment
Formula, for example, it is also possible to using the quadratic sum of the absolute value of the element of fuzzy core as the nuclear energy amount of fuzzy core.
Step 204, according to the nuclear energy amount of the n the first fuzzy cores and the quality information of the n the first images,
Determine the nuclear energy amount of first fuzzy core and the mapping relations of the quality information of described first image.
Step 201 to step 204 is the nuclear energy amount for the fuzzy core that image is determined based on existing image namely n the first images
The process of mapping relations between the quality information of image;In practical application, for determining the first figure of the mapping relations
The quantity of picture can be more than predetermined threshold value, to improve the precision of the mapping relations subsequently determined;Can also be by n the first image bases
Classified (type can be resolution ratio) in different types, to establish different mapping relations, root based on different types
The quality of the second image is targetedly determined according to the type belonged to of the second image.
Step 205, the second image is obtained, determines the second fuzzy core, second fuzzy core is based on second image
Identified fuzzy core.
Second image is the unknown image of picture quality, the mapping determined in the present embodiment based on step 201 to 204
Relation, determine the quality information of the second image.
Step 206, the nuclear energy amount of second fuzzy core is determined.
Step 206 is that the picture quality of the second image is quantified as to the process of nuclear energy amount.
Step 207, according to the nuclear energy amount of second fuzzy core and the mapping relations, the matter of second image is determined
Measure information.
Namely quality information corresponding with the nuclear energy amount of the second fuzzy core is searched in the mapping relations, as the second figure
The quality information of picture.
It is that n the first images determine the quality information of image and the fuzzy core of image using existing image in the present embodiment
Nuclear energy amount between mapping relations, this just establishes the quantization judgment criteria of image quality information, as long as determining matter to be judged
The nuclear energy amount of the fuzzy core of the image (namely second image) of amount, it is possible to the matter of the second image is determined based on the mapping relations
Information is measured, the problem of so as to avoid manually judging picture quality inaccuracy.
Embodiment three
The present embodiment records a kind of information processing method, the implementation process signal for the information processing method that the present embodiment is recorded
Figure is as shown in figure 3, comprise the following steps:
Step 301, the quality information of n the first images and the n the first images is obtained, n is the integer more than 1.
N the first images are used for determining the mapping relations between the fuzzy core of image and picture quality, so as to root
According to the mapping relations, the quality of the second image is determined.
Step 302, for each first image in the n the first images, with the Prior function of fuzzy core, successively really
Optimal value of the fixed Prior function on each first image in the n the first images, will identified optimal value successively
Corresponding the first fuzzy core for being defined as the n the first images.
The n the first fuzzy cores are the fuzzy core based on determined by the n the first images successively.
In practical application, the Prior function can be one of following function:Mix Laplace function, broad sense La Pula
This function.
Step 303, by the n the first fuzzy cores the element of each first fuzzy core square and/or absolute value
With the corresponding nuclear energy amount for being defined as first fuzzy core.
In practical application, fuzzy core shows as the form of matrix, can be by fuzzy core accordingly, as an example
Element square and/or absolute value sum, as the nuclear energy amount of fuzzy core, be also not limited to above-mentioned shape certainly, in the present embodiment
Formula, for example, it is also possible to using the quadratic sum of the absolute value of the element of fuzzy core as the nuclear energy amount of fuzzy core.
Step 304, according to the nuclear energy amount of the n the first fuzzy cores and the quality information of the n the first images,
Determine the nuclear energy amount of first fuzzy core and the mapping relations of the quality information of described first image.
Step 301 to step 304 is the nuclear energy amount for the fuzzy core that image is determined based on existing image namely n the first images
The process of mapping relations between the quality information of image;In practical application, for determining the first figure of the mapping relations
The quantity of picture can be more than predetermined threshold value, to improve the precision of the mapping relations subsequently determined;Can also be by n the first image bases
Classified (type can be resolution ratio) in different types, to establish different mapping relations based on different types, with
The quality of second image is targetedly determined according to the type belonged to of the second image.
Step 305, the second image is obtained, determines the second fuzzy core, second fuzzy core is based on second image
Identified fuzzy core.
Second image is the unknown image of picture quality, the mapping determined in the present embodiment based on step 301 to 304
Relation, determine the quality information of the second image.
Step 306, by the element of second fuzzy core square and/or absolute value sum, it is fuzzy to be defined as described second
The nuclear energy amount of core.
Step 306 is that the picture quality of the second image is quantified as to the process of nuclear energy amount.
Step 307, according to the nuclear energy amount of second fuzzy core and the mapping relations, the matter of second image is determined
Amount.
Namely quality information corresponding with the nuclear energy amount of the second fuzzy core is searched in the mapping relations, as the second figure
The quality information of picture.
It is that n the first images determine the quality information of image and the fuzzy core of image using existing image in the present embodiment
Nuclear energy amount between mapping relations, this just establishes the quantization judgment criteria of image quality information, as long as determining matter to be judged
The nuclear energy amount of the fuzzy core of the image (namely second image) of amount, it is possible to the matter of the second image is determined based on the mapping relations
Information is measured, the problem of so as to avoid manually judging picture quality inaccuracy.
Example IV
The present embodiment records a kind of information processing method, the implementation process signal for the information processing method that the present embodiment is recorded
Figure is as shown in figure 4, comprise the following steps:
Step 401, the quality information of n the first images and the n the first images is obtained, n is the integer more than 1.
N the first images are used for determining the mapping relations between the fuzzy core of image and picture quality, so as to root
According to the mapping relations, the quality of the second image is determined.
Step 402, for each first image in the n the first images, with the Prior function of fuzzy core, successively really
Optimal value of the fixed Prior function on each first image in the n the first images, will identified optimal value successively
Corresponding the first fuzzy core for being defined as the n the first images.
The n the first fuzzy cores are the fuzzy core based on determined by the n the first images successively.
In practical application, the Prior function can be one of following function:Mix Laplace function, broad sense La Pula
This function.
Step 403, by the n the first fuzzy cores the element of each first fuzzy core square and/or absolute value
With the corresponding nuclear energy amount for being defined as first fuzzy core.
In practical application, fuzzy core shows as the form of matrix, can be by fuzzy core accordingly, as an example
Element square and/or absolute value sum, as the nuclear energy amount of fuzzy core, be also not limited to above-mentioned shape certainly, in the present embodiment
Formula, for example, it is also possible to using the quadratic sum of the absolute value of the element of fuzzy core as the nuclear energy amount of fuzzy core.
Step 404, the input using the energy of the n the first fuzzy cores as mapping relations function, by the n first
Output of the quality information of image as the mapping relations function, the parameter of the mapping relations function is trained to obtain
Mapping relations function after to parameter training.
Initial mapping relations function can be one of any using following form function:Quadratic Map relation function, repeatedly
Mapping relations function and Bezier mapping relations function;Mapping relations function after training as the first fuzzy core nuclear energy amount with
The mapping relations of the quality information of described first image, the mapping relations are used for as the follow-up mark for judging image quality information
It is accurate.
Step 401 to step 404 is the nuclear energy amount for the fuzzy core that image is determined based on existing image namely n the first images
The process of mapping relations between the quality information of image;In practical application, for determining the first figure of the mapping relations
The quantity of picture can be more than predetermined threshold value, to improve the precision of the mapping relations subsequently determined;Can also be by n the first image bases
Classified (type can be resolution ratio) in different types, to establish different mapping relations based on different types, with
The quality of second image is targetedly determined according to the type belonged to of the second image.
Step 405, the second image is obtained, determines the second fuzzy core, second fuzzy core is based on second image
Identified fuzzy core.
Second image is the unknown image of picture quality, the mapping determined in the present embodiment based on step 401 to 404
Relation, determine the quality information of the second image.
Step 406, by the element of second fuzzy core square and/or absolute value sum, it is fuzzy to be defined as described second
The nuclear energy amount of core.
Step 406 is that the picture quality of the second image is quantified as to the process of nuclear energy amount.
Step 407, according to the nuclear energy amount of second fuzzy core and the mapping relations, the matter of second image is determined
Amount.
Namely quality information corresponding with the nuclear energy amount of the second fuzzy core is searched in the mapping relations, as the second figure
The quality information of picture.
It is the quality information and image fuzzy core that n the first images determine image using existing image in the present embodiment
Mapping relations between nuclear energy amount, this just establishes the quantization judgment criteria of image quality information, as long as determining quality to be judged
Image (namely second image) fuzzy core nuclear energy amount, it is possible to the quality of the second image is determined based on the mapping relations
Information, the problem of so as to avoid manually judging picture quality inaccuracy.
Embodiment five
The present embodiment records a kind of information processing method, the implementation process signal for the information processing method that the present embodiment is recorded
Figure is as shown in figure 5, comprise the following steps:
Step 501, the quality information of n the first images and the n the first images is obtained, n is the integer more than 1.
N the first images are used for determining the mapping relations between the fuzzy core of image and picture quality, so as to root
According to the mapping relations, the quality of the second image is determined.
Step 502, for each first image in the n the first images, with the Prior function of fuzzy core, successively really
Optimal value of the fixed Prior function on each first image in the n the first images, will identified optimal value successively
Corresponding the first fuzzy core for being defined as the n the first images.
The n the first fuzzy cores are the fuzzy core based on determined by the n the first images successively.
In practical application, the Prior function can be one of following function:Mix Laplace function, broad sense La Pula
This function.
Step 503, by the n the first fuzzy cores the element of each first fuzzy core square and/or absolute value
With the corresponding nuclear energy amount for being defined as first fuzzy core.
In practical application, fuzzy core shows as the form of matrix, can be by fuzzy core accordingly, as an example
Element square and/or absolute value sum, as the nuclear energy amount of fuzzy core, be also not limited to above-mentioned shape certainly, in the present embodiment
Formula, for example, it is also possible to using the quadratic sum of the absolute value of the element of fuzzy core as the nuclear energy amount of fuzzy core.
Step 504, the input using the energy of the n the first fuzzy cores as mapping relations function, by the n first
Output of the quality information of image as the mapping relations function, the parameter of the mapping relations function is trained to obtain
Mapping relations function after to parameter training.
Initial mapping relations function can be one of any using following form function:Quadratic Map relation function, repeatedly
Mapping relations function and Bezier mapping relations function;Mapping relations function after training as the first fuzzy core nuclear energy amount with
The mapping relations of the quality information of described first image, the mapping relations are used for as the follow-up mark for judging image quality information
It is accurate.
Step 501 to step 504 is the nuclear energy amount for the fuzzy core that image is determined based on existing image namely n the first images
The process of mapping relations between the quality information of image;In practical application, for determining the first figure of the mapping relations
The quantity of picture can be more than predetermined threshold value, to improve the precision of the mapping relations subsequently determined;Can also be by n the first image bases
Classified (type can be resolution ratio) in different types, to establish different mapping relations based on different types, with
The quality of second image is targetedly determined according to the type belonged to of the second image.
Step 505, the second image is obtained, determines the second fuzzy core, second fuzzy core is based on second image
Identified fuzzy core.
Second image is the unknown image of picture quality, the mapping determined in the present embodiment based on step 501 to 504
Relation, determine the quality information of the second image.
Step 506, by the element of second fuzzy core square and/or absolute value sum, it is fuzzy to be defined as described second
The nuclear energy amount of core.
Step 506 is that the picture quality of the second image is quantified as to the process of nuclear energy amount.
Step 507, according to the nuclear energy amount of second fuzzy core and the mapping relations, the matter of second image is determined
Measure information.
Namely quality information corresponding with the nuclear energy amount of the second fuzzy core is searched in the mapping relations, as the second figure
The quality information of picture.
Step 508, the nonzero element distribution arrangement of second fuzzy core is determined, by identified nonzero element distribution side
To the motion blur direction for being defined as second image.
Step 509, based on the identified direction of motion, second image is repaired, to lift second figure
The picture quality of picture.
For example, when nonzero element distribution arrangement for it is vertical when, it is due in shooting process upper to show the second image
Caused by lower shake, (shaken) based on the reason for cause the second image to obscure, the second image can be directed to up and down
Property repair, with lifted the second image quality.
It is the quality information and image fuzzy core that n the first images determine image using existing image in the present embodiment
Mapping relations between nuclear energy amount, this just establishes the quantization judgment criteria of image quality information, as long as determining quality to be judged
Image (namely second image) fuzzy core nuclear energy amount, it is possible to the quality of the second image is determined based on the mapping relations
Information, the problem of so as to avoid manually judging picture quality inaccuracy;Also, it is also based on the motion blur side of the second image
To targetedly being repaired to the second image.
It need to be noted that be:Description in following electronic equipment embodiment, with the above method description be it is similar, together
The beneficial effect description of method, is not repeated.For the ins and outs not disclosed in electronic equipment embodiment of the present invention, refer to
The description of the inventive method embodiment.
Embodiment six
The present embodiment records a kind of electronic equipment, as shown in fig. 6, the electronic equipment includes:
First acquisition unit 61, for obtaining the quality information of n the first images and the n the first images, n is big
In 1 integer;
First determining unit 62, for determining n the first fuzzy cores, the n the first fuzzy cores are to be based on the n successively
Fuzzy core determined by individual first image, and determine the nuclear energy amount of the n the first fuzzy cores;
Second determining unit 63, for the nuclear energy amount and the n the first images according to the n the first fuzzy cores
Quality information, determine the nuclear energy amount of first fuzzy core and the mapping relations of the quality information of described first image;
Second acquisition unit 64, for obtaining the second image;
3rd determining unit 65, for determining the second fuzzy core, second fuzzy core is based on the second image institute
The fuzzy core of determination, and determine the nuclear energy amount of second fuzzy core;
4th determining unit 66, for the nuclear energy amount according to second fuzzy core and the mapping relations, it is determined that described
The quality of second image.
As an embodiment, second determining unit 63, it is additionally operable in the n the first fuzzy cores each the
The element of one fuzzy core square and/or absolute value sum, the corresponding nuclear energy amount for being defined as first fuzzy core;
3rd determining unit 65, be additionally operable to by the element of second fuzzy core square and/or absolute value sum,
It is defined as the nuclear energy amount of second fuzzy core.
As an embodiment, second determining unit 63, it is additionally operable to make using following form function is one of any
For initial mapping relations function:Quadratic Map relation function, multiple mapping relations function and Bezier mapping relations function;
Input using the energy of the n the first fuzzy cores as the mapping relations function, by the n the first images
Output of the quality information as the mapping relations function, the parameter of the mapping relations function is trained;To obtain
Mapping relations function after parameter training.
As an embodiment, first determining unit 62, it is additionally operable to for each in the n the first images
First image, with the Prior function of fuzzy core, determine the Prior function in the n the first images each first successively
The optimal value of image, identified optimal value successively is correspondingly defined as to the first fuzzy core of the n the first images.
As an embodiment, as shown in fig. 7, the electronic equipment can also include:
5th determining unit 67, it is non-by determined by for determining the nonzero element distribution arrangement of second fuzzy core
Neutral element distribution arrangement is defined as the motion blur direction of second image;
Unit 68 is repaired, for the motion blur direction based on the determination, second image is repaired.
In practical application, each unit in electronic equipment can be by central processing unit (CPU, the Central in electronic equipment
Processing Unit), digital signal processor (DSP, Digital Signal Processor) or field-programmable gate array
(FPGA, Field Programmable Gate Array) is arranged to realize.
In several embodiments provided by the present invention, it should be understood that disclosed apparatus and method, it can be passed through
Its mode is realized.Apparatus embodiments described above are only schematical, for example, the division of the unit, is only
A kind of division of logic function, there can be other dividing mode when actually realizing, such as:Multiple units or component can combine, or
Another system is desirably integrated into, or some features can be ignored, or do not perform.In addition, shown or discussed each composition portion
Point mutual coupling or direct-coupling or communication connection can be the INDIRECT COUPLINGs by some interfaces, equipment or unit
Or communication connection, can be electrical, mechanical or other forms.
The above-mentioned unit illustrated as separating component can be or may not be physically separate, show as unit
The part shown can be or may not be physical location, you can positioned at a place, can also be distributed to multiple network lists
In member;Partly or entirely unit therein can be selected to realize the purpose of this embodiment scheme according to the actual needs.
In addition, each functional unit in various embodiments of the present invention can be fully integrated into a processing unit, also may be used
To be each unit individually as a unit, can also two or more units it is integrated in a unit;It is above-mentioned
Integrated unit can both be realized in the form of hardware, can also be realized in the form of hardware adds SFU software functional unit.
One of ordinary skill in the art will appreciate that:Realizing all or part of step of above method embodiment can pass through
Programmed instruction related hardware is completed, and foregoing program can be stored in a computer read/write memory medium, the program
Upon execution, the step of execution includes above method embodiment;And foregoing storage medium includes:It is movable storage device, read-only
Memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or
Person's CD etc. is various can be with the medium of store program codes.
Or if the above-mentioned integrated unit of the present invention is realized in the form of software function module and is used as independent product
Sale in use, can also be stored in a computer read/write memory medium.Based on such understanding, the present invention is implemented
The part that the technical scheme of example substantially contributes to prior art in other words can be embodied in the form of software product,
The computer software product is stored in a storage medium, including some instructions are causing a computer equipment (can be with
It is personal computer, server or network equipment etc.) perform all or part of each embodiment methods described of the present invention.
And foregoing storage medium includes:Movable storage device, ROM, RAM, magnetic disc or CD etc. are various can be with store program codes
Medium.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (8)
1. a kind of information processing method, it is characterised in that methods described includes:
The quality information of n the first images and the n the first images is obtained, n is the integer more than 1;
N the first fuzzy cores are determined, the n the first fuzzy cores are to be obscured successively based on determined by the n the first images
Core, and determine the nuclear energy amount of the n the first fuzzy cores;
According to the nuclear energy amount of individual first fuzzy cores of the n and the quality information of the n the first images, described first is determined
The mapping relations of the nuclear energy amount of fuzzy core and the quality information of described first image;
The second image is obtained, determines the second fuzzy core, second fuzzy core is to be obscured based on determined by second image
Core, and determine the nuclear energy amount of second fuzzy core;
According to the nuclear energy amount of second fuzzy core and the mapping relations, the quality of second image is determined;
Wherein, the nuclear energy amount of the determination n the first fuzzy cores, including:In the n the first fuzzy cores each first is obscured
The element of core square and/or absolute value sum, the corresponding nuclear energy amount for being defined as first fuzzy core;
Correspondingly, the nuclear energy amount for determining the second fuzzy core, including:By the element of second fuzzy core square and/or absolutely
To the sum of value, it is defined as the nuclear energy amount of second fuzzy core.
2. according to the method for claim 1, it is characterised in that the nuclear energy amount according to first fuzzy core and
The preset quality of described first image, determine that the mapping of the nuclear energy amount of first fuzzy core and the quality of described first image is closed
System, including:
It is one of any as initial mapping relations function using following form function:Quadratic Map relation function, repeatedly mapping
Relation function and Bezier mapping relations function;
Input using the energy of the n the first fuzzy cores as the mapping relations function, by the matter of the n the first images
Output of the information as the mapping relations function is measured, the parameter of the mapping relations function is trained;To obtain parameter
Mapping relations function after training.
3. according to the method for claim 1, it is characterised in that the determination n the first fuzzy cores, including:
For each first image in the n the first images, with the Prior function of fuzzy core, the priori letter is determined successively
Optimal value of the number on each first image in the n the first images, identified optimal value will correspondingly be defined as institute successively
State the first fuzzy core of n the first images.
4. according to the method described in any one of claims 1 to 3, it is characterised in that methods described also includes:
The nonzero element distribution arrangement of second fuzzy core is determined, identified nonzero element distribution arrangement is defined as described
The motion blur direction of second image;
Based on identified motion blur direction, second image is repaired.
5. a kind of electronic equipment, it is characterised in that the electronic equipment includes:
First acquisition unit, for obtaining the quality information of n the first images and the n the first images, n is more than 1
Integer;
First determining unit, for determining n the first fuzzy cores, the n the first fuzzy cores is successively based on the n first
Fuzzy core determined by image, and determine the nuclear energy amount of the n the first fuzzy cores;
Second determining unit, for the nuclear energy amount and the quality of the n the first images according to individual first fuzzy cores of the n
Information, determine the nuclear energy amount of first fuzzy core and the mapping relations of the quality information of described first image;
Second acquisition unit, for obtaining the second image;
3rd determining unit, for determining the second fuzzy core, second fuzzy core is based on determined by second image
Fuzzy core, and determine the nuclear energy amount of second fuzzy core;
4th determining unit, for the nuclear energy amount according to second fuzzy core and the mapping relations, determine second figure
The quality of picture;
Wherein, second determining unit, be additionally operable to by the n the first fuzzy cores the element of each first fuzzy core it is flat
Side and/or the sum of absolute value, the corresponding nuclear energy amount for being defined as first fuzzy core;
3rd determining unit, be additionally operable to by the element of second fuzzy core square and/or absolute value sum, be defined as
The nuclear energy amount of second fuzzy core.
6. electronic equipment according to claim 5, it is characterised in that
Second determining unit, it is additionally operable to one of any as initial mapping relations function using following form function:Two
Secondary mapping relations function, multiple mapping relations function and Bezier mapping relations function;
Input using the energy of the n the first fuzzy cores as the mapping relations function, by the matter of the n the first images
Output of the information as the mapping relations function is measured, the parameter of the mapping relations function is trained;To obtain parameter
Mapping relations function after training.
7. electronic equipment according to claim 5, it is characterised in that
First determining unit, it is additionally operable to for each first image in the n the first images, with the priori of fuzzy core
Function, determine optimal value of the Prior function on each first image in the n the first images successively, will successively really
Fixed optimal value is correspondingly defined as the first fuzzy core of the n the first images.
8. according to the electronic equipment described in any one of claim 5 to 7, it is characterised in that the electronic equipment also includes:
5th determining unit, for determining the nonzero element distribution arrangement of second fuzzy core, by identified nonzero element
Distribution arrangement is defined as the motion blur direction of second image;
Unit is repaired, for the motion blur direction based on the determination, second image is repaired, with described in lifting
The picture quality of second image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410367131.3A CN105338339B (en) | 2014-07-29 | 2014-07-29 | Information processing method and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410367131.3A CN105338339B (en) | 2014-07-29 | 2014-07-29 | Information processing method and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105338339A CN105338339A (en) | 2016-02-17 |
CN105338339B true CN105338339B (en) | 2018-02-27 |
Family
ID=55288582
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410367131.3A Active CN105338339B (en) | 2014-07-29 | 2014-07-29 | Information processing method and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105338339B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101079149A (en) * | 2006-09-08 | 2007-11-28 | 浙江师范大学 | Noise-possessing movement fuzzy image restoration method based on radial basis nerve network |
CN101282481A (en) * | 2008-05-09 | 2008-10-08 | 中国传媒大学 | Method for evaluating video quality based on artificial neural net |
CN101968881A (en) * | 2010-10-27 | 2011-02-09 | 东南大学 | Motion blurring and defocusing composite blurring image restoration method |
WO2011139980A1 (en) * | 2010-05-05 | 2011-11-10 | Digimarc Coporation | Hidden image signaling |
CN102567744A (en) * | 2011-12-29 | 2012-07-11 | 中国科学院自动化研究所 | Method for determining quality of iris image based on machine learning |
CN102724541A (en) * | 2012-05-21 | 2012-10-10 | 浙江捷尚视觉科技有限公司 | Intelligent diagnosis and recovery method for monitoring images |
CN102750679A (en) * | 2012-06-28 | 2012-10-24 | 西安电子科技大学 | Blind deblurring method for image quality evaluation |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4453734B2 (en) * | 2007-09-21 | 2010-04-21 | ソニー株式会社 | Image processing apparatus, image processing method, image processing program, and imaging apparatus |
-
2014
- 2014-07-29 CN CN201410367131.3A patent/CN105338339B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101079149A (en) * | 2006-09-08 | 2007-11-28 | 浙江师范大学 | Noise-possessing movement fuzzy image restoration method based on radial basis nerve network |
CN101282481A (en) * | 2008-05-09 | 2008-10-08 | 中国传媒大学 | Method for evaluating video quality based on artificial neural net |
WO2011139980A1 (en) * | 2010-05-05 | 2011-11-10 | Digimarc Coporation | Hidden image signaling |
CN101968881A (en) * | 2010-10-27 | 2011-02-09 | 东南大学 | Motion blurring and defocusing composite blurring image restoration method |
CN102567744A (en) * | 2011-12-29 | 2012-07-11 | 中国科学院自动化研究所 | Method for determining quality of iris image based on machine learning |
CN102724541A (en) * | 2012-05-21 | 2012-10-10 | 浙江捷尚视觉科技有限公司 | Intelligent diagnosis and recovery method for monitoring images |
CN102750679A (en) * | 2012-06-28 | 2012-10-24 | 西安电子科技大学 | Blind deblurring method for image quality evaluation |
Also Published As
Publication number | Publication date |
---|---|
CN105338339A (en) | 2016-02-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP7099509B2 (en) | Computer vision system for digitization of industrial equipment gauges and alarms | |
CN105928598A (en) | Method and system for measuring object mass based on photographing | |
CN108961184A (en) | A kind of bearing calibration of depth image, device and equipment | |
CN105637343B (en) | Detection control apparatus, detection system, storage medium and detection control method | |
CN110493595B (en) | Camera detection method and device, storage medium and electronic device | |
CN109671174A (en) | A kind of pylon method for inspecting and device | |
CN109272546B (en) | Fry length measuring method and system | |
CN109284700B (en) | Method, storage medium, device and system for detecting multiple faces in image | |
CN109858551A (en) | Method, apparatus, equipment and medium based on image recognition detection structure stress | |
US20220121705A1 (en) | Multi-Resolution Color-Based Image Search | |
CN113724259A (en) | Well lid abnormity detection method and device and application thereof | |
CN108647264A (en) | A kind of image automatic annotation method and device based on support vector machines | |
CN110349216A (en) | Container method for detecting position and device | |
CN109308516A (en) | A kind of method and apparatus of image procossing | |
CN115565020A (en) | Tooth surface damage identification method and device based on improved neural network | |
JP5704909B2 (en) | Attention area detection method, attention area detection apparatus, and program | |
CN108764040A (en) | A kind of image detecting method, terminal and computer storage media | |
CN105338339B (en) | Information processing method and electronic equipment | |
CN110222704A (en) | A kind of Weakly supervised object detection method and device | |
CN110162362A (en) | Dynamic controlware position detection and test method, device, equipment and storage medium | |
CN108734175A (en) | A kind of extracting method of characteristics of image, device and electronic equipment | |
CN115452101A (en) | Instrument verification method, device, equipment and medium | |
CN114490412A (en) | Three-dimensional CAD software performance measurement method and device based on self-subtraction reverse cloud generator | |
CN111640096B (en) | Method, device and terminal for detecting appearance of electronic product | |
CN105637344A (en) | Image processing device, program, storage medium, and image processing method |
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 |