CN107025645A - A kind of image processing method and terminal - Google Patents
A kind of image processing method and terminal Download PDFInfo
- Publication number
- CN107025645A CN107025645A CN201710105105.7A CN201710105105A CN107025645A CN 107025645 A CN107025645 A CN 107025645A CN 201710105105 A CN201710105105 A CN 201710105105A CN 107025645 A CN107025645 A CN 107025645A
- Authority
- CN
- China
- Prior art keywords
- image
- matrix
- terminal
- discrete cosine
- carried out
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20052—Discrete cosine transform [DCT]
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a kind of image processing method and its terminal, including：Obtain testing image；Discrete cosine transform is carried out to the testing image, the first matrix is obtained；Sign reversing is carried out to the first matrix；Inverse discrete cosine transform is carried out to the first matrix after sign reversing, Saliency maps picture is obtained.In the embodiment of the present invention, only by just having obtained Saliency maps picture to testing image progress discrete cosine transform and inverse discrete cosine transform, it is achieved thereby that the conspicuousness detection of testing image, reduces algorithm complex, and improve the efficiency of conspicuousness detection.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of image processing method and its terminal.
Background technology
The conspicuousness of image is the very important visual feature of image, embodies attention degree of the human eye to image some regions.
In image processing process, often need to detect image using conspicuousness detection algorithm, to obtain the conspicuousness of the image
Region.And, with continuing to develop for technology, the notable Journal of Sex Research of image is in the scene understanding of image, image retrieval, target identification
The many-side such as tracking, assisted focused has very strong demand.But, existing conspicuousness detection algorithm is mostly more complicated, so that
Reduce the efficiency of conspicuousness detection.
The content of the invention
The embodiment of the present invention provides a kind of image processing method and its terminal, it is possible to decrease algorithm complex, improves conspicuousness
The efficiency of detection.
The embodiments of the invention provide a kind of image processing method, including：
Obtain testing image；
Discrete cosine transform is carried out to the testing image, the first matrix is obtained；
Sign reversing is carried out to the first matrix；
Inverse discrete cosine transform is carried out to the first matrix after sign reversing, Saliency maps picture is obtained.
The embodiment of the present invention additionally provides a kind of image processing terminal, including:
Acquiring unit, for obtaining testing image；
First processing units, for carrying out discrete cosine transform to the testing image, obtain the first matrix；
Second processing unit, for carrying out sign reversing to the first matrix；
3rd processing unit, for carrying out inverse discrete cosine transform to the first matrix after sign reversing, is obtained significantly
Property image.
In the embodiment of the present invention, only by just being obtained to testing image progress discrete cosine transform and inverse discrete cosine transform
Saliency maps pictures, it is achieved thereby that the conspicuousness detection of testing image, reduces algorithm complex, and improve conspicuousness inspection
The efficiency of survey.
Brief description of the drawings
Technical scheme, is used required in being described below to embodiment in order to illustrate the embodiments of the present invention more clearly
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the present invention, general for this area
For logical technical staff, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow sheet for image processing method that first embodiment of the invention is provided；
Fig. 2 is a kind of schematic flow sheet for image processing method that second embodiment of the invention is provided；
Fig. 3 is a kind of schematic flow sheet for image processing method that third embodiment of the invention is provided；
Fig. 4 is the Saliency maps picture detected by step S304；
Fig. 5 is Fig. 4 thermodynamic chart；
Fig. 6 is the Energy distribution histogram of blurred picture；
Fig. 7 is the Energy distribution histogram of picture rich in detail；
Fig. 8 is Matlab simulated effect figures；
Fig. 9 is a kind of structural representation for image processing terminal that first embodiment of the invention is provided；
Figure 10 is a kind of structural representation for image processing terminal that second embodiment of the invention is provided；
Figure 11 is a kind of structural representation for image processing terminal that third embodiment of the invention is provided；
Figure 12 is a kind of structural representation for image processing terminal that fourth embodiment of the invention is provided.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described.
It should be appreciated that ought be in this specification and in the appended claims in use, term " comprising " and "comprising" be indicated
Described feature, entirety, step, operation, the presence of element and/or component, but be not precluded from one or more of the other feature, it is whole
Body, step, operation, element, component and/or its presence or addition for gathering.
It is also understood that the term used in this description of the invention is merely for the sake of the mesh for describing specific embodiment
And be not intended to limit the present invention.As used in description of the invention and appended claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singulative, " one " and "the" are intended to include plural form.
It will be further appreciated that, the term "and/or" used in description of the invention and appended claims is
Refer to any combinations of one or more of the associated item listed and be possible to combination, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determining " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to true
It is fixed " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
In the specific implementation, the terminal described in the embodiment of the present invention is including but not limited to such as with touch sensitive surface
The mobile phone, laptop computer or tablet PC of (for example, touch-screen display and/or touch pad) etc it is other just
Portable device.It is to be further understood that in certain embodiments, the equipment not portable communication device, but with touching
Touch the desktop computer of sensing surface (for example, touch-screen display and/or touch pad).
In discussion below, the terminal including display and touch sensitive surface is described.It is, however, to be understood that
It is that terminal can include one or more of the other physical user-interface device of such as physical keyboard, mouse and/or control-rod.
Terminal supports various application programs, such as one or more of following：Drawing application program, demonstration application journey
Sequence, word-processing application, website create application program, disk imprinting application program, spreadsheet applications, game application
Program, telephony application, videoconference application, email application, instant messaging applications, exercise
Support application program, photo management application program, digital camera application program, digital camera application program, web-browsing application
Program, digital music player application and/or video frequency player application program.
The various application programs that can be performed in terminal can use such as touch sensitive surface at least one is public
Physical user-interface device.It can adjust and/or change among applications and/or in corresponding application programs and touch sensitive table
The corresponding information shown in the one or more functions and terminal in face.So, the public physical structure of terminal is (for example, touch
Sensing surface) the various application programs with user interface directly perceived and transparent for a user can be supported.
Fig. 1 is refer to, is the schematic flow sheet for the image processing method that first embodiment of the invention is provided, as illustrated,
This method may comprise steps of：
S101, obtains testing image.
User can send the instruction for opening application of taking pictures by way of touch-control or voice to terminal, and terminal is being received
When the unlatching sent to user is taken pictures using instruction, it can open to take pictures and apply to obtain testing image.
S102, carries out discrete cosine transform to testing image, obtains the first matrix.
Obtain after the testing image, discrete cosine transform (Discrete Cosine are carried out to it
Transformation, DCT), obtain the first matrix.It should be noted that in image processing field, digital picture can use matrix
Represent.Wherein, the row of matrix correspond to image height (unit is pixel), matrix column correspond to image width (unit is picture
Element).Therefore, in the step, first testing image is represented with matrix X0, then dct transform is carried out to matrix X0, the first matrix is obtained
X1。
S103, sign reversing is carried out to the first matrix.
S104, carries out inverse discrete cosine transform to the first matrix after sign reversing, obtains Saliency maps picture.
Sign reversing first is carried out to the first matrix X1, afterwards, the first matrix X1 after sign reversing carried out inverse discrete
Cosine transform (Inverse Discrete Cosine Transformation, IDCT), so as to obtain matrix X2.With reference to foregoing
Description understands that the corresponding images of matrix X2 are Saliency maps picture.
In the embodiment of the present invention, first obtain and testing image and dct transform is carried out to it, obtain the first matrix, afterwards, to the
One matrix carries out sign reversing, finally carries out idct transform to the first matrix after sign reversing, obtains Saliency maps picture.By
DCT only is carried out to testing image in the embodiment of the present invention and idct transform has just obtained Saliency maps picture, it is achieved thereby that treating
The conspicuousness detection of altimetric image.With currently with saturation degree and brightness, universal search tree (Generalized Search
Trees, GiST) feature or other high complex characteristics carry out conspicuousness detection and compare, and it is complicated that the embodiment of the present invention reduces algorithm
Degree, calculates the time soon, so as to improve the efficiency of conspicuousness detection.
Fig. 2 is refer to, is the schematic flow sheet for the image processing method that first embodiment of the invention is provided, as illustrated,
This method may comprise steps of：
S201, obtains YUV image.
User can send the instruction for opening application of taking pictures by way of touch-control or voice to terminal, and terminal is being received
Unlatchings sent to user take pictures using instruction when, application of taking pictures can be opened to obtain testing image.Acquired in terminal
Testing image can be (i.e. the RGB image) of yuv format (i.e. YUV image) or rgb format.But, at present for,
Testing image acquired in the mobile terminals such as mobile phone is typically yuv format.
S202, RGB image is converted to by the YUV image.
It is that conspicuousness detection is carried out based on R, G, B triple channel in follow-up process step in the present embodiment, therefore, terminal is first
Need to be converted to RGB image to acquired YUV image.Wherein, YUV image be converted to RGB image formula (1) it is as follows：
In formula (1), R represents red, and G represents green, and B represents blueness, and Y represents lightness, and U and V represent colourity.
S203, carries out discrete cosine transform to RGB image, obtains the first matrix.
To R, G, B triple channel of RGB image, discrete cosine transform (Discrete Cosine are carried out using formula (2)
Transformation, DCT), obtain the first matrix：
Wherein, x, y, u, v=0,1 ..., N-1.
In formula (2), F (u, v) represents the signal after dct transform, and f (x, y) represents primary signal, and N represents original
The number of signal, c (u), c (v) represent penalty coefficient, and it can cause the matrix after dct transform to turn into orthogonal matrix.
It should be noted that carrying out dct transform to R, G, B triple channel of RGB image according to formula (2), R, G, B can be obtained
The corresponding matrix of triple channel, is represented by：The matrix F r (u, v) of R passages, the matrix F g (u, v) of G passages, the matrix F b of channel B
(u, v).That is, the first matrix includes corresponding three matrixes of R, G, B triple channel.
S204, sign reversing is carried out to the first matrix.
Sign reversing is carried out to the first matrix in step S202 using formula (3)：
Value obtained by formula (3) is represented from formula (2) is 1 or 0 or -1.
S205, carries out inverse discrete cosine transform to the first matrix after sign reversing, obtains Saliency maps picture.
Inverse discrete cosine transform (Inverse is carried out to carrying out the first matrix after sign reversing using formula (4)
Discrete Cosine Transformation, IDCT), obtain Saliency maps picture：
Wherein, x, y, u, v=0,1 ..., N-1.
In formula (4), F (u, v) represents primary signal, and N represents the number of primary signal, and f (x, y) represents to become through IDCT
Signal after changing, c (u), c (v) represent penalty coefficient, and it can cause the matrix after idct transform to turn into orthogonal matrix.
It should be noted that due to it is foregoing be that dct transform is carried out to R, G, B triple channel of RGB image, obtained, G, B tri-
The corresponding matrix of passage；Idct transform is carried out to the first matrix herein, the corresponding matrix of R, G, B triple channel still can be obtained, can
It is expressed as：The matrix fr (x, y) of R passages, the matrix fg (x, y) of G passages, the matrix fb (x, y) of channel B.
After the matrix fr (x, y), the matrix fg (x, y) of G passages, the matrix fb (x, y) of channel B of R passages is obtained, just
R, G, B triple channel image are can obtain, so as to obtain Saliency maps picture.
S206, Saliency maps picture is averaging processing.
Matrix fr (x, y), fg (x, y), fb (x, y) square matrices are first asked for using formula (5)：
F (x, y)=f (x, y) .^2 (5)
In formula (5), F (x, y) represents square matrices, and f (x, y) represents the matrix after idct transform.It is striked herein
Square matrices include：The square matrices Fr (x, y) of R passages, the square matrices Fg (x, y) of G passages, the square matrices of channel B
Fb (x, y).
The mean matrix of triple channel square matrices is calculated using formula (6) again：
In formula (6), G (x, y) represents mean matrix.
In the embodiment of the present invention, first obtain and testing image and dct transform is carried out to it, obtain the first matrix, afterwards, to the
One matrix carries out sign reversing, finally carries out idct transform to the first matrix after sign reversing, obtains Saliency maps picture.By
DCT only is carried out to testing image in the embodiment of the present invention and idct transform has just obtained Saliency maps picture, it is achieved thereby that treating
The conspicuousness detection of altimetric image.With carrying out conspicuousness currently with saturation degree and brightness, GIST features or other high complex characteristics
Detection is compared, and the embodiment of the present invention reduces algorithm complex, calculates the time soon, so as to improve the efficiency of conspicuousness detection.
Further, the embodiment of the present invention has also carried out average treatment using formula (5), (6) to Saliency maps picture, can make
The significant characteristics that must be detected are not easy to be misled to produce effect of errors by pure color scene, so as to improve the accurate of detection
Property.
Fig. 3 is refer to, is the schematic flow sheet for the image processing method that third embodiment of the invention is provided, as illustrated,
This method may comprise steps of：
S301, obtains YUV image.
S302, RGB image is converted to by the YUV image.
S303, carries out discrete cosine transform to RGB image, obtains the first matrix.
S304, sign reversing is carried out to the first matrix.
S305, carries out inverse discrete cosine transform to the first matrix after sign reversing, obtains Saliency maps picture.
S306, Saliency maps picture is averaging processing.
It should be noted that step S301 to S306 idiographic flow refer to step S201 to S206, no longer go to live in the household of one's in-laws on getting married herein
State.
S307, carries out denoising to the Saliency maps picture after averaged processing, obtains energy profile.
S308, the fuzzy region of testing image is determined according to energy profile.
In order to preferably describe step S307 to S308, following Jie first is done to the background context knowledge involved by this two step
Continue.As shown in figure 4, for by the Saliency maps picture detected by step S301 to S306, Fig. 5 is Fig. 4 thermodynamic chart.From Fig. 5
In as can be seen that energy concentrate on clearly image-region.Further, it refer to blurred picture shown in Fig. 6 and Fig. 7 and clear
Clear image energy distribution histogram, from this figure, it can be seen that energy concentrate on it is more compared with minizone.It therefore, it can set and close
The threshold value of reason, and combine the analysis to the probability distribution of energy diagram picture to determine the fuzzy region and fog-level of image.
Specifically, denoising first is carried out to Saliency maps picture, obtains energy profile.That is, first mean matrix is carried out
Gaussian smoothing is calculated, and to eliminate the noise in Saliency maps picture, and obtains energy profile.
Afterwards, energy profile is first divided into many sub-regions, each subregion is as a sample point, then calculates each
Sample point falls into the probability of predeterminable area, if probability is less than default threshold value, it is determined that the subregion is fuzzy region.Citing comes
Say, energy profile is divided into subregion 1, subregion 2 ... subregion n, and corresponding sample point is sample point 1, sample point
2 ... sample point n, predeterminable area is R, calculates the probability P that sample point 1 falls into predeterminable area, if probability P is less than default threshold
Value P0, it is determined that subregion 1 is fuzzy region.
It should be noted that the above method is to calculate probability using probability density algorithm, and image is determined with reference to threshold value
Fuzzy region.Wherein, the principle of probability density algorithm is as follows：
Assuming that sampled data values obey a unknown probability density function in D dimension spaces, then the probability in the R of region
For：
P=∫Rp(x)dx
Dx represents differential, and the implication of probability P is just that the probability that each sample number strong point falls into region R is P.Assuming that N number of sample
Notebook data point has K to fall into region R, then should just obey bi-distribution：
From probabilistic knowledge, when N sample datas are very big, K is approximately equal to N*P.And on the other hand, it is assumed that region R is enough
If small, then P is approximately equal to p (x) * V (V is region R space).It can be obtained with reference to two inequality：
It should be noted that being to pass through when the fuzzy region of testing image is determined indeed according to energy profile
What Matlab softwares were realized.Specifically, the region of energy profile is represented in the matrix form, and by the value of matrix as defeated
Enter, Matlab softwares are output as probability.Wherein, Matlab analogous diagram is as shown in Figure 8.In fig. 8, x-axis and y-axis represent figure
As coordinate, z-axis represents energy value.Clear area (the high region of energy) and fuzzy region (energy can be determined clearly from figure
The low region of amount).
Similarly, the fog-level in region can be determined based on probability density algorithm.
In the embodiment of the present invention, dct transform, sign reversing and idct transform first are carried out to testing image, conspicuousness is obtained
Image, determines the fuzzy region and fog-level of image based on Saliency maps picture afterwards.When carrying out conspicuousness detection, only carry out
DCT and idct transform, reduce algorithm complex, calculate that the time is fast, so as to improve the efficiency of conspicuousness detection.Simultaneously
Reduce detection fuzzy region and the difficulty of fog-level.In addition, the embodiment of the present invention is also averaged to Saliency maps picture
Processing, may be such that the significant characteristics detected are not easy to be misled to produce effect of errors by pure color scene, so as to improve
The accuracy of conspicuousness detection, and then improve the accuracy of image blurring detection.
It is a kind of structural representation for image processing terminal that first embodiment of the invention is provided, the present embodiment referring to Fig. 9
Described in terminal, including：
Acquiring unit 10, for obtaining testing image；
First processing units 11, for carrying out discrete cosine transform to testing image, obtain the first matrix；
Second processing unit 12, for carrying out sign reversing to the first matrix；
3rd processing unit 13, for carrying out inverse discrete cosine transform to the first matrix after sign reversing, is shown
Work property image.
In the embodiment of the present invention, first pass through acquiring unit 10 and obtain testing image, then treated by first processing units 11
Altimetric image carries out dct transform, obtains the first matrix, afterwards, and sign reversing is carried out by 12 pair of first matrix of second processing unit,
Idct transform is carried out finally by 13 pairs of first matrixes after sign reversing of the 3rd processing unit, Saliency maps picture is obtained.By
DCT only is carried out to testing image in the embodiment of the present invention and idct transform has just obtained Saliency maps picture, it is achieved thereby that treating
The conspicuousness detection of altimetric image.With carrying out conspicuousness currently with saturation degree and brightness, GIST features or other high complex characteristics
Detection is compared, and the embodiment of the present invention reduces algorithm complex, calculates the time soon, so as to improve the efficiency of conspicuousness detection.
Figure 10 is referred to, is that second embodiment of the invention provides a kind of structural representation of image processing terminal, such as Figure 10
Shown, the terminal can include：
Acquiring unit 20, for obtaining testing image, the testing image is YUV image；
Converting unit 24, for YUV image to be converted into RGB image；
First processing units 21, carry out discrete cosine transform for RGB image, obtain the first matrix；
Second processing unit 22, for carrying out sign reversing to the first matrix；
3rd processing unit 23, for carrying out inverse discrete cosine transform to the first matrix after sign reversing, is shown
Work property image；
Fourth processing unit 25, for Saliency maps picture to be averaging processing.
In the embodiment of the present invention, first pass through acquiring unit 20 and obtain YUV image, and by converting unit 24 by YUV image
RGB image is converted to, then, dct transform is carried out to RGB image by first processing units 21, the first matrix is obtained, afterwards,
Sign reversing is carried out by 22 pair of first matrix of second processing unit, and by 23 pairs of the 3rd processing unit after sign reversing
First matrix carries out idct transform, obtains Saliency maps picture.Due in the embodiment of the present invention only to testing image carry out DCT and
Idct transform has just obtained Saliency maps picture, it is achieved thereby that the conspicuousness detection of testing image.With currently with saturation degree and
Brightness, GIST features or other high complex characteristics carry out conspicuousness detection and compared, and the embodiment of the present invention reduces algorithm complex,
The calculating time is fast, so as to improve the efficiency of conspicuousness detection.
Further, the embodiment of the present invention has also carried out average treatment using fourth processing unit 25 to Saliency maps picture,
It may be such that the significant characteristics detected are not easy to be misled to produce effect of errors by pure color scene, so as to improve detection
Accuracy.
Figure 11 is referred to, is that third embodiment of the invention provides a kind of structural representation of image processing terminal, such as Figure 11
Shown, the mobile terminal can include：Acquiring unit 30, converting unit 34, first processing units 31, second processing unit 32,
3rd processing unit 33, fourth processing unit 35, denoising unit 36 and determining unit 37.Wherein, acquiring unit 30, conversion are single
Member 34, first processing units 31, second processing unit 32, the 3rd processing unit 33, fourth processing unit 35 and second embodiment
In acquiring unit 20, converting unit 24, first processing units 21, second processing unit 22, the 3rd processing unit 23, everywhere
Manage the structure of unit 25 and function is similar, will not be repeated here.
Further, denoising unit 36, for carrying out denoising to the Saliency maps picture after averaged processing, obtains energy
Measure distribution map；
Determining unit 37, the fuzzy region for determining testing image according to energy profile.
Specifically, it is determined that unit 37 specifically for：
Energy profile is divided into multiple regions, each region is used as a sample point；
Calculate the probability that each sample point falls into predeterminable area；
If the probability is less than default threshold value, it is determined that the region is fuzzy region.
In the embodiment of the present invention, first pass through acquiring unit 30 and obtain testing image, then handled by converting unit 34, first
Unit 31, second processing unit 32, the 3rd processing unit 33 carry out dct transform, sign reversing and idct transform to testing image,
Saliency maps picture is obtained, and Saliency maps picture is averaging processing by fourth processing unit 35, afterwards, passes through denoising unit
Saliency maps picture after 36 pairs of averaged processing carries out denoising, obtains energy profile, finally by determining unit 37
The fuzzy region and fog-level of testing image are determined according to energy profile.Carry out conspicuousness detection when, only carried out DCT and
Idct transform, reduces algorithm complex, calculates the time soon, so as to improve the efficiency of conspicuousness detection.Also reduce simultaneously
Detect fuzzy region and the difficulty of fog-level.In addition, the embodiment of the present invention has also carried out average treatment to Saliency maps picture, can
So that the significant characteristics detected are not easy to be misled to produce effect of errors by pure color scene, so as to improve conspicuousness inspection
The accuracy of survey, and then improve the accuracy of image blurring detection.
It should be noted that the specific workflow of terminal shown in Fig. 9 to Figure 11 is done in preceding method flow elements
It is described in detail, will not be repeated here.
Referring to Figure 12, in being a kind of structural representation for image terminal that fourth embodiment of the invention is provided, the present embodiment
Described terminal can include：At least one processor 401, such as CPU, at least one user interface 403, memory 404,
At least one communication bus 402.Wherein, communication bus 402 is used to realize the connection communication between these components.Wherein, user
Interface 403 can include display screen (Display), keyboard (Keyboard), and optional user interface 403 can also include standard
Wireline interface, wave point.Memory 404 can be high-speed RAM memory or non-labile memory (non-
Volatile memory), for example, at least one magnetic disk storage.It is remote that memory 404 optionally can also be that at least one is located at
From the storage device of aforementioned processor 401.The terminal that wherein processor 401 can be with reference to described by Fig. 9 to 11, memory 404
Middle storage batch processing code, and processor 401 calls the program code stored in memory 404, for performing following operation：
Obtain testing image；
Discrete cosine transform is carried out to the testing image, the first matrix is obtained；
Sign reversing is carried out to first matrix；
Inverse discrete cosine transform is carried out to first matrix after sign reversing, Saliency maps picture is obtained.
As an alternative embodiment, testing image is YUV image, processor 401 calls the generation in memory 404
Code can also carry out following operation：
The YUV image is converted into RGB image；
Discrete cosine transform is carried out to the RGB image, first matrix is obtained.
As an alternative embodiment, processor 401 calls the code in memory 404 to can also carry out following behaviour
Make：
The Saliency maps picture is averaging processing.
As an alternative embodiment, processor 401 calls the code in memory 404 to can also carry out following behaviour
Make：
Denoising is carried out to the Saliency maps picture after averaged processing, energy profile is obtained；
The fuzzy region of the testing image is determined according to the energy profile.
As an alternative embodiment, processor 401 calls the code in memory 404 to can also carry out following behaviour
Make：
The energy profile is divided into many sub-regions, each subregion is used as a sample point；
Calculate the probability that each sample point falls into predeterminable area；
If the probability is less than default threshold value, it is determined that the subregion is the fuzzy region.
In the embodiment of the present invention, only by just being obtained to testing image progress discrete cosine transform and inverse discrete cosine transform
Saliency maps pictures, it is achieved thereby that the conspicuousness detection of testing image, reduces algorithm complex, and improve conspicuousness inspection
The efficiency of survey.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Member and algorithm steps, can be realized with electronic hardware, computer software or the combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, the composition and step of each example are generally described according to function in the above description.This
A little functions are performed with hardware or software mode actually, depending on the application-specific and design constraint of technical scheme.Specially
Industry technical staff can realize described function to each specific application using distinct methods, but this realization is not
It is considered as beyond the scope of this invention.
, can be with addition, in several embodiments provided herein, it should be understood that disclosed, terminal and method
Realize by another way.For example, device embodiment described above is only schematical, for example, the unit
Divide, only a kind of division of logic function there can be other dividing mode when actually realizing, such as multiple units or component
Another system can be combined or be desirably integrated into, or some features can be ignored, or do not perform.In addition, shown or beg for
The coupling each other of opinion or direct-coupling or communication connection can be the INDIRECT COUPLINGs by some interfaces, device or unit
Or communication connection or electricity, mechanical or other forms are connected.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize scheme of the embodiment of the present invention according to the actual needs
Purpose.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit, can also
It is that unit is individually physically present or two or more units are integrated in a unit.It is above-mentioned integrated
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
Step in present invention method can be sequentially adjusted, merged and deleted according to actual needs.This hair
Unit in bright embodiment terminal can be combined, divided and deleted according to actual needs.It is described above, it is only the present invention's
Embodiment, but protection scope of the present invention is not limited thereto, and any one skilled in the art is at this
Invent in the technical scope disclosed, various equivalent modifications or substitutions can be readily occurred in, these modifications or substitutions should all cover
Within protection scope of the present invention.Therefore, protection scope of the present invention should be defined by scope of the claims.
Claims (10)
1. a kind of image processing method, it is characterised in that including：
Obtain testing image；
Discrete cosine transform is carried out to the testing image, the first matrix is obtained；
Sign reversing is carried out to first matrix；
Inverse discrete cosine transform is carried out to first matrix after sign reversing, Saliency maps picture is obtained.
2. the method as described in claim 1, it is characterised in that the testing image is YUV image, obtains the testing image
Also include afterwards：
The YUV image is converted into RGB image；
Discrete cosine transform is carried out to the testing image, the first matrix is obtained and specifically includes：
Discrete cosine transform is carried out to the RGB image, first matrix is obtained.
3. the method as described in claim 1, it is characterised in that obtain after Saliency maps picture, methods described also includes：
The Saliency maps picture is averaging processing.
4. method as claimed in claim 3, it is characterised in that described after the Saliency maps picture is averaging processing
Method also includes：
Denoising is carried out to the Saliency maps picture after averaged processing, energy profile is obtained；
According to the energy profile, the fuzzy region of the testing image is determined.
5. method as claimed in claim 4, it is characterised in that the mould of the testing image is determined according to the energy profile
Paste region is specifically included：
The energy profile is divided into many sub-regions, each subregion is used as a sample point；
Calculate the probability that each sample point falls into predeterminable area；
If the probability is less than default threshold value, it is determined that the subregion is the fuzzy region.
6. a kind of image processing terminal, it is characterised in that including：
Acquiring unit, for obtaining testing image；
First processing units, for carrying out discrete cosine transform to the testing image, obtain the first matrix,；
Second processing unit, for carrying out sign reversing to first matrix；
3rd processing unit, for carrying out inverse discrete cosine transform to first matrix after sign reversing, is obtained significantly
Property image.
7. terminal as claimed in claim 6, it is characterised in that the testing image is YUV image, the terminal also includes：
Converting unit, for the YUV image to be converted into RGB image；
The first processing units are used to carry out discrete cosine transform to the RGB image, obtain first matrix.
8. terminal as claimed in claim 6, it is characterised in that the terminal also includes：
Fourth processing unit, for the Saliency maps picture to be averaging processing.
9. terminal as claimed in claim 8, it is characterised in that the terminal also includes：
Denoising unit, for carrying out denoising to the Saliency maps picture after averaged processing, obtains energy profile；
Determining unit, for according to the energy profile, determining the fuzzy region of the testing image.
10. terminal as claimed in claim 9, it is characterised in that the determining unit specifically for：
The energy profile is divided into multiple regions, each region is used as a sample point；
Calculate the probability that each sample point falls into predeterminable area；
If the probability is less than default threshold value, it is determined that the region is the fuzzy region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710105105.7A CN107025645A (en) | 2017-02-25 | 2017-02-25 | A kind of image processing method and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710105105.7A CN107025645A (en) | 2017-02-25 | 2017-02-25 | A kind of image processing method and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107025645A true CN107025645A (en) | 2017-08-08 |
Family
ID=59525954
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710105105.7A Withdrawn CN107025645A (en) | 2017-02-25 | 2017-02-25 | A kind of image processing method and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107025645A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112954356A (en) * | 2021-01-27 | 2021-06-11 | 西安万像电子科技有限公司 | Image transmission processing method and device, storage medium and electronic equipment |
-
2017
- 2017-02-25 CN CN201710105105.7A patent/CN107025645A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112954356A (en) * | 2021-01-27 | 2021-06-11 | 西安万像电子科技有限公司 | Image transmission processing method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10388004B2 (en) | Image processing method and apparatus | |
| US9697416B2 (en) | Object detection using cascaded convolutional neural networks | |
| WO2020228406A1 (en) | Image stylization generation method and apparatus, and electronic device | |
| CN112102164B (en) | Image processing method, device, terminal and storage medium | |
| CN108961267B (en) | Picture processing method, picture processing device and terminal equipment | |
| CN111444807B (en) | Target detection method, device, electronic equipment and computer readable medium | |
| CN112306301A (en) | Touch data processing method, device, equipment and storage medium | |
| CN109657543B (en) | People flow monitoring method and device and terminal equipment | |
| WO2021164328A1 (en) | Image generation method, device, and storage medium | |
| CN110211017B (en) | Image processing method and device and electronic equipment | |
| CN113516697B (en) | Image registration method, device, electronic equipment and computer readable storage medium | |
| CN108629767B (en) | Scene detection method and device and mobile terminal | |
| CN107133940A (en) | A kind of patterning process and terminal | |
| CN110197459B (en) | Image stylization generation method and device and electronic equipment | |
| CN107025645A (en) | A kind of image processing method and terminal | |
| CN108932704B (en) | Picture processing method, picture processing device and terminal equipment | |
| CN111861965A (en) | Image backlight detection method, image backlight detection device and terminal equipment | |
| CN109102495A (en) | Target image determines method and system, computer equipment, computer storage medium | |
| CN111124862B (en) | Intelligent device performance testing method and device and intelligent device | |
| US20220075583A1 (en) | Information processing method, server, terminal, and computer storage medium | |
| US20200286246A1 (en) | Fingertip detection method, fingertip detection device, and medium | |
| CN108182656B (en) | Image processing method and terminal | |
| CN111160265A (en) | File conversion method and device, storage medium and electronic equipment | |
| CN111383238B (en) | Target detection method, target detection device and intelligent terminal | |
| CN111754411A (en) | Image noise reduction method, image noise reduction device and terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170808 |
|
| WW01 | Invention patent application withdrawn after publication |