CN106228551B - The adaptive decomposition method of filter is generated based on image Segmentation Technology - Google Patents
The adaptive decomposition method of filter is generated based on image Segmentation Technology Download PDFInfo
- Publication number
- CN106228551B CN106228551B CN201610569963.2A CN201610569963A CN106228551B CN 106228551 B CN106228551 B CN 106228551B CN 201610569963 A CN201610569963 A CN 201610569963A CN 106228551 B CN106228551 B CN 106228551B
- Authority
- CN
- China
- Prior art keywords
- time
- frequency
- group
- filter
- label
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000000354 decomposition reaction Methods 0.000 title claims abstract description 42
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 30
- 238000005516 engineering process Methods 0.000 title claims abstract description 20
- 238000003709 image segmentation Methods 0.000 title claims abstract description 19
- 230000009466 transformation Effects 0.000 claims abstract description 30
- 238000006243 chemical reaction Methods 0.000 claims abstract description 15
- 230000011218 segmentation Effects 0.000 claims abstract description 12
- 238000005070 sampling Methods 0.000 claims abstract description 11
- 235000013350 formula milk Nutrition 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 abstract description 14
- 239000004615 ingredient Substances 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011426 transformation method Methods 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- 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
- G06T2207/20024—Filtering details
-
- 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
- G06T2207/20056—Discrete and fast Fourier transform, [DFT, FFT]
-
- 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
- G06T2207/20064—Wavelet transform [DWT]
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention proposes a kind of adaptive decomposition method that filter is generated based on image Segmentation Technology, comprising the following steps: the first step carries out time-frequency conversion to signal to be analyzed, obtains corresponding time-frequency coefficients and time-frequency plane；Second step carries out Threshold segmentation to time-frequency plane, to obtain binary picture；Third step marks the connected domain in binary picture；4th step generates one group of Time frequency Filter according to connected domain, and is filtered according to Time frequency Filter to the time frequency system, exports filter result；5th step carries out time-frequency inverse transformation to filter result, to obtain decomposition result.Method of the invention is in each frequency content sampling time long enough of signal to be decomposed, can have optional frequency resolution ratio, compared with common empirical mode decomposition algorithm, substantially increase frequency resolution, adaptive decomposition can be carried out to the signal that closely spaced frequencies are distributed, and the instantaneous frequency and instantaneous amplitude of each ingredient are calculated with this, to widen the application range of adaptive decomposition algorithm.
Description
Technical field
The present invention relates to signal processing technology field, in particular to it is a kind of based on image Segmentation Technology generate filter from
Adapt to decomposition method.
Background technique
Currently, adaptive decomposition algorithm obtains very extensive application in field of signal processing.Its Typical Representative Empirical Mode
The publication paper that state decomposes (Empirical Mode Decomposition, EMD) has in Google's science super so far
Cross 12000 references, it can be seen that one spot.It is combined, is provided with Hilbert transformation to find out its cause, being primarily due to EMD method
A kind of convenient approach for calculating signal each frequency content instantaneous frequency and instantaneous amplitude.It is normal as quantitative assessment signal characteristic
Parameter, instantaneous frequency and instantaneous amplitude are widely used.Instantaneous frequency is examined in such as radar, sonar, Mechanical System Trouble
Disconnected engineering field is widely applied.Same instantaneous amplitude is applied to modal parameter determination and non-destructive testing detection field.
The method currently calculated instantaneous frequency and instantaneous amplitude can be divided mainly into two classes: one kind is based on inner product
The time-frequency conversion method of calculation, for example, Short Time Fourier Transform, wavelet transformation, framework decomposition etc.；Another kind of is combining adaptive point
(for example, EMD, local mean value decomposes (Local Mean Decompositio, LMD) to resolving Algorithm and experience wavelet transformation decomposes
(Empirical Wavelet transform, EWT)) and instantaneous frequency and instantaneous amplitude instantaneous algorithm (for example, Hilbert
Transformation and energy operator method).
Due to decomposing the diversity of waveform, the former different components are easier to accumulate in the corresponding region in time-frequency plane,
It is easily separated.It but since inner product calculates is carried out between certain section of signal to be analyzed and decomposition waveform, so this is not a kind of
Real instantaneous calculation method, calculated result cannot accurately reflect the transient change of signal frequency and amplitude.It is excellent for the latter
Point is that calculating process includes two stages: signal decomposition is different independent components by the first stage, for example, in the side EMD
Intrinsic mode functions (Intrinsic Mode Function, IMF) in method；Second stage calculates each point using Transient Technique
The instantaneous frequency and instantaneous amplitude of amount, such as Hilbert transformation and energy operator method.So can more acurrate calculating using the method
The instantaneous frequency and instantaneous amplitude of signal.But the frequency resolution of the method is not ideal enough.So far, still for LMD and EWT method
Not about the report of frequency discrimination.For classical adaptive decomposition algorithm EMD method, it has been reported that but when two
(the f when frequency ratio of a component is greater than 0.75It is low/fIt is high), this method just cannot separate the two, to limit adaptive decomposition calculation
The application range of method.
Summary of the invention
The present invention is directed at least solve one of above-mentioned technical problem.
For this purpose, it is an object of the invention to propose a kind of adaptive decomposition side for generating filter based on image Segmentation Technology
Method, this method can have optional frequency resolution ratio in each frequency content sampling time long enough of signal to be decomposed, and common
Empirical mode decomposition algorithm compare, substantially increase frequency resolution, can to closely spaced frequencies be distributed signal carry out it is adaptive
It should decompose, and calculate the instantaneous frequency and instantaneous amplitude of each ingredient with this, to widen the application model of adaptive decomposition algorithm
It encloses.
To achieve the goals above, the embodiment of the present invention, which proposes, a kind of generates filter based on image Segmentation Technology
Adaptive decomposition method, comprising the following steps: S1: to signal to be analyzed carry out time-frequency conversion, obtain corresponding time-frequency coefficients and
Time-frequency plane；S2: Threshold segmentation is carried out to the time-frequency plane, to obtain binary picture；S3: it marks in the binary picture
Connected domain；S4: one group of Time frequency Filter is generated according to the connected domain, and according to the Time frequency Filter to the time frequency system
It is filtered, exports filter result；And S5: time-frequency inverse transformation is carried out to the filter result, to obtain decomposition result.
In addition, the adaptive decomposition method according to the above embodiment of the present invention for generating filter based on image Segmentation Technology
It can also have the following additional technical features:
In some instances, in the S1, the mode of the time-frequency conversion includes: that Short Time Fourier Transform or small echo become
It changes.
In some instances, the transformation for mula of the Short Time Fourier Transform are as follows:
Wherein, STFTw(s) [m, n] is the Short Time Fourier Transform coefficient at point (m, n), and m is to become the time of time-frequency plane
Amount, n are frequency variable, and s [k] is discrete signal to be analyzed, and k is the time variable of sample point, and K is sampling time length, w
[k-l] is window function, and | | w | |=1.
In some instances, in the S2, the transformation for mula for obtaining binary picture are as follows:
Wherein,For the binary picture, c (m, n) is the time-frequency coefficients, T0For segmentation threshold.
In some instances, the S3 further comprises: S31: the binary picture is progressively scanned, by the binary picture
Every a line in continuously value for 1 a sequence forming of pixel as a group, and write down starting point and the end of the group
Line number where point and the group；S32: being scanned the group in all rows in addition to the first row, if current group is with before
All groups in a line then give described one new label of current group all without overlapping region, if current group only with lastrow
In a group have overlapping region, then be marked with the label currently rolled into a ball, if current group with 2 or more of lastrow
There is overlapping region in group, then assigns the minimum label in connection group to the current group, and by the label of several groups in lastrow
Write-in is of equal value right；S33: will be described of equal value to being converted to equivalent sequence, and an identical label is assigned to each equivalent sequence；
S34: traversal starts the label of group, searches equivalent sequence, and give the group new label；S35: the label of each group is inserted
In the binary image.
In some instances, in the S4, the filter result are as follows:
Wherein,(i=1,2,3 ..., P) is the filter result, and P is Time frequency Filter number, FiFor i-th of time-frequency
Filter, C are the matrix of the time-frequency coefficients.
In some instances, in the S5, the transformation for mula of the time-frequency inverse transformation are as follows:
Wherein, STFTw(s) [m, n] is the Short Time Fourier Transform coefficient at point (m, n), and m is to become the time of time-frequency plane
Amount, n are frequency variable, and s [k] is discrete signal to be analyzed, and k is the time variable of sample point, and K is sampling time length, w
[k-M] is window function, and | | w | |=1.
The adaptive decomposition method according to an embodiment of the present invention that filter is generated based on image Segmentation Technology, in conjunction with time-frequency
Transformation and inverse transformation method divide the image into method introducing, for constructing Time frequency Filter, the decomposition of Lai Shixian signal component,
And in each frequency content sampling time long enough of signal to be decomposed, can have optional frequency resolution ratio, with common experience
Mode decomposition algorithm is compared, and frequency resolution is substantially increased, and can carry out adaptive decomposition to the signal that closely spaced frequencies are distributed,
And the instantaneous frequency and instantaneous amplitude of each ingredient are calculated with this, to widen the application range of adaptive decomposition algorithm.
Additional aspect and advantage of the invention will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect of the invention and advantage will become from the description of the embodiment in conjunction with the following figures
Obviously and it is readily appreciated that, in which:
Fig. 1 is the stream of the adaptive decomposition method according to an embodiment of the present invention that filter is generated based on image Segmentation Technology
Cheng Tu；
Fig. 2 is the Fourier transformation time-frequency figure of example signal accord to a specific embodiment of that present invention；
Fig. 3 is the image of the binary picture obtained after Threshold segmentation accord to a specific embodiment of that present invention；And
Fig. 4 is the adaptive decomposition that filter is generated based on image Segmentation Technology accord to a specific embodiment of that present invention
Schematic diagram based on the Hilbert instantaneous frequency converted and instantaneous amplitude after method is decomposed.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and for explaining only the invention, and is not considered as limiting the invention.
In the description of the present invention, it is to be understood that, term " center ", " longitudinal direction ", " transverse direction ", "upper", "lower",
The orientation or positional relationship of the instructions such as "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is
It is based on the orientation or positional relationship shown in the drawings, is merely for convenience of description of the present invention and simplification of the description, rather than instruction or dark
Show that signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as pair
Limitation of the invention.In addition, term " first ", " second " are used for description purposes only, it is not understood to indicate or imply opposite
Importance.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；It can
To be mechanical connection, it is also possible to be electrically connected；It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in invention.
It is described below in conjunction with attached drawing according to an embodiment of the present invention based on the adaptive of image Segmentation Technology generation filter
Decomposition method.
Fig. 1 is the adaptive decomposition method according to an embodiment of the invention that filter is generated based on image Segmentation Technology
Flow chart.As shown in Figure 1, method includes the following steps:
Step S1: time-frequency conversion is carried out to signal to be analyzed, obtains corresponding time-frequency coefficients and time-frequency plane.
Wherein, the mode of time-frequency conversion is, for example, Short Time Fourier Transform or wavelet transformation.When used in the present embodiment
Frequency transform method is Short Time Fourier Transform, transformation for mula are as follows:
Wherein, STFTw(s) [m, n] is the Short Time Fourier Transform coefficient at point (m, n), and m is to become the time of time-frequency plane
Amount, n are frequency variable, and s [k] is discrete signal to be analyzed, and k is the time variable of sample point, and K is sampling time length, w
[k-l] is window function, and | | w | |=1.
Certainly, time-frequency conversion method of the invention is not limited only to this, can be two-dimentional time-frequency plane for any transformation results
Time-frequency conversion algorithm, be only the description for the purpose of exemplary herein.
Step S2: Threshold segmentation is carried out to time-frequency plane, to obtain binary picture.
In one embodiment of the invention, the expression formula of binary picture is for example are as follows:
Wherein,For binary picture, c (m, n) is time-frequency coefficients, T0For segmentation threshold.
Step S3: the connected domain in label binary picture.
Specifically, step S3 further comprises:
S31: progressive scan binary picture, one that the pixel that continuously value is 1 in every a line of binary picture is formed
A sequence is as a group, and the line number where the beginning and end for the group of writing down and group.
S32: being scanned the group in all rows in addition to the first row, if all groups in current group and previous row are all
There is no overlapping region, then to currently one new label of group, if only there is overlapping region in current group with a group in lastrow,
It is marked with the label currently rolled into a ball, if there are overlapping region in current group and 2 or more groups of lastrow, is assigned to current group
The minimum label in connection group is given, and the write-in of the label of several groups in lastrow is of equal value right.
S33: by equivalence to being converted to equivalent sequence, and an identical label is assigned to each equivalent sequence.
S34: traversal starts the label of group, searches equivalent sequence, and the label that the group of giving is new.
S35: will be in the label filling binary image of each group.
Step S4: one group of Time frequency Filter is generated according to connected domain, and the time frequency system is filtered according to Time frequency Filter
Wave exports filter result.
In one embodiment of the invention, filter result is for example are as follows:
Wherein,(i=1,2,3 ..., P) is time-frequency coefficients matrix after filter result, namely filtering, and P is Time frequency Filter
Number, FiFor i-th of Time frequency Filter, C is the matrix of time-frequency coefficients.
Step S5: time-frequency inverse transformation is carried out to filter result, to obtain decomposition result.
In one embodiment of the invention, the transformation for mula of time-frequency inverse transformation is carried out to filter result are as follows:
Wherein, STFTw(s) [m, n] is the Short Time Fourier Transform coefficient at point (m, n), and m is to become the time of time-frequency plane
Amount, n are frequency variable, and s [k] is discrete signal to be analyzed, and k is the time variable of sample point, and K is sampling time length, w
[k-M] is window function, and | | w | |=1.
For the ease of more fully understanding adaptive point based on image Segmentation Technology generation filter of the embodiment of the present invention
Solution method further specifically describes method of the invention below in conjunction with attached drawing and specific embodiment.
In the present embodiment, this method is realized under matlab software platform.It is with a specific example signal
Example is illustrated this method.The expression formula of the example signal are as follows:
S (t)=s1(t)+s2(t)+s3(t),0≤t≤1
s1=(t-t2)sin(1000·2π·t)
s2=(t-t2)sin(750·2π·t)
s3=(t-t2) sin (4002 π t+200sin (2 π t)),
It include 3 components, sample frequency f i.e. in the example signalsFor 100kHz.
Based on this, in the present embodiment, method includes the following steps:
Step 1: time-frequency conversion is carried out to example signal.Using Short Time Fourier Transform the most common to showing in this example
Example signal carries out time-frequency conversion, specific transformation for mula are as follows:
Wherein, k represents the time, and it is mobile that m (m=0,1,2 ..., M-1) represents the time in time-frequency conversion, n (n=0,1,
2 ..., N-1) represent in time-frequency conversion frequency variation.Further, transformation results (i.e. time-frequency coefficients) c (m, the n) example obtained
As shown in Figure 2.As shown in Figure 2, the corresponding time-frequency coefficients of 3 different frequency ingredients accumulate in not same district respectively in time-frequency plane
Domain.
Step 2: time-frequency plane obtained in Threshold segmentation step 1 generates binary picture.Specific formula for calculation are as follows:
Wherein,For the pixel number of the binary image after calculating, T0For segmentation threshold.Herein, segmentation threshold
Being set as 0.01, then transformation results form 3 independent connected domains as shown in figure 3, from the figure 3, it may be seen that after Threshold segmentation,
Wherein contain the corresponding time-frequency coefficients of 3 frequency contents.
Step 3: the connected domain in binary picture is obtained in markers step 2,3 connected regions are marked respectively, are convenient for journey
Sequence is automatically performed decomposable process.Specific label connected domain algorithmic procedure is as follows:
(1) binary picture obtained in step 2 is progressively scanned, the pixel that continuously value is 1 in every a line is formed
One sequence is known as a group, and writes down its beginning and end and the line number where it.
(2) group in all rows other than the first row is scanned, if all groups in it and previous row are all
There is no overlapping region, then gives its new label；It, will be with the group if only having overlapping region with a group in lastrow
Label is marked；If it has overlapping region with 2 or more of lastrow groups, assigned in connection group most to current group
Small label, and the label write-in of these groups of lastrow is of equal value right.
(3) by equivalence to equivalent sequence is converted to, each sequence assigns an identical label.Assign each equivalent sequence
One label, since 1.
(4) traversal starts the label of group, searches equivalent sequence, gives their new labels.
It (5) will be in the label filling tag image of each group.
Step 4: one group of Time frequency Filter is generated according to connected domain, and time-frequency coefficients obtained in step 1 are filtered,
Specific Filtering Formula are as follows:
Wherein,(i=1,2,3 ..., P, P are Time frequency Filter number) is filter result, namely time-frequency coefficients after filtering
Matrix, FiFor i-th of Time frequency Filter, C is time-frequency coefficients matrix obtained in step 1.
In the present embodiment, 3 groups of filters are produced, after filtering, have also just obtained 3 groups of different time-frequency systems accordingly
Number.
Step 5: time-frequency inverse transformation corresponding with step 1 being carried out to filter result obtained in step 4, to be decomposed
As a result, specific calculation formula are as follows:
Wherein, STFTw(s) [m, n] is the Short Time Fourier Transform coefficient at point (m, n), and m is to become the time of time-frequency plane
Amount, n are frequency variable, and s [k] is discrete signal to be analyzed, and k is the time variable of sample point, and K is sampling time length, w
[k-M] is window function, and | | w | |=1.
Further, after obtaining decomposition result, instantaneous frequency and wink based on Hilbert transformation calculations decomposition result
When frequency, result is as shown in Figure 4.By Fig. 4 (a) it is found that for instantaneous frequency, in addition to endpoint location, calculated value and setting value
It coincide；By Fig. 4 (b) it is found that for instantaneous amplitude, calculated value and setting value curve are essentially coincided together.Instantaneous frequency and wink
When amplitude calculated result show the algorithm and effectively separate 3 ingredients.
To sum up, the adaptive decomposition method according to an embodiment of the present invention that filter is generated based on image Segmentation Technology, knot
Time-frequency conversion and inverse transformation method are closed, method introducing, for constructing Time frequency Filter, Lai Shixian signal component are divided the image into
It decomposes, and in each frequency content sampling time long enough of signal to be decomposed, can have optional frequency resolution ratio, and it is common
Empirical mode decomposition algorithm is compared, and frequency resolution is substantially increased, and can be carried out to the signal that closely spaced frequencies are distributed adaptive
It decomposes, and calculates the instantaneous frequency and instantaneous amplitude of each ingredient with this, to widen the application range of adaptive decomposition algorithm.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that: not
A variety of change, modification, replacement and modification can be carried out to these embodiments in the case where being detached from the principle of the present invention and objective, this
The range of invention is by claim and its equivalent limits.
Claims (5)
1. a kind of adaptive decomposition method for generating filter based on image Segmentation Technology, which comprises the following steps:
S1: time-frequency conversion is carried out to signal to be analyzed, obtains corresponding time-frequency coefficients and time-frequency plane；
S2: Threshold segmentation is carried out to the time-frequency plane, to obtain binary picture；
S3: the connected domain in the binary picture is marked, wherein the S3 further comprises:
S31: progressively scanning the binary picture, and the pixel that continuously value is 1 in every a line of the binary picture is formed
A sequence as a group, and the beginning and end for writing down the group and the line number where the group；
S32: being scanned the group in all rows in addition to the first row, if all groups in current group and previous row all do not have
Described one new label of current group is then given in overlapping region, if only there is overlapping region in current group with a group in lastrow,
It is marked with the label currently rolled into a ball, if there are overlapping region in current group and 2 or more groups of lastrow, to described
Current group assigns the minimum label in connection group, and the write-in of the label of several groups in lastrow is of equal value right；
S33: will be described of equal value to being converted to equivalent sequence, and an identical label is assigned to each equivalent sequence；
S34: traversal starts the label of group, searches equivalent sequence, and give the group new label；
S35: the label of each group is inserted in the binary picture；
S4: according to the connected domain generate one group of Time frequency Filter, and according to the Time frequency Filter to the time-frequency coefficients into
Row filtering, exports filter result, wherein the filter result are as follows:
Wherein,For the filter result, P is Time frequency Filter number, FiFor i-th of Time-frequency Filter
Device, C are the matrix of the time-frequency coefficients；And
S5: time-frequency inverse transformation is carried out to the filter result, to obtain decomposition result.
2. the adaptive decomposition method according to claim 1 for being generated filter based on image Segmentation Technology, feature are existed
In in the S1, the mode of the time-frequency conversion includes: Short Time Fourier Transform or wavelet transformation.
3. the adaptive decomposition method according to claim 2 for being generated filter based on image Segmentation Technology, feature are existed
In the transformation for mula of the Short Time Fourier Transform are as follows:
Wherein, STFTw(s) [m, n] is the Short Time Fourier Transform coefficient at point (m, n), and m is the time variable of time-frequency plane, n
For frequency variable, s [k] is discrete signal to be analyzed, and k is the time variable of sample point, and K is sampling time length, w [k-l]
For window function, and | | w | |=1.
4. the adaptive decomposition method according to claim 1 for being generated filter based on image Segmentation Technology, feature are existed
In, in the S2, the transformation for mula for obtaining binary picture are as follows:
Wherein,For the binary picture, c (m, n) is the time-frequency coefficients, T0For segmentation threshold.
5. the adaptive decomposition method according to claim 3 for being generated filter based on image Segmentation Technology, feature are existed
In, in the S5, the transformation for mula of the time-frequency inverse transformation are as follows:
Wherein, STFTw(s) [m, n] is the Short Time Fourier Transform coefficient at point (m, n), and m is the time variable of time-frequency plane, n
For frequency variable, s [k] is discrete signal to be analyzed, and k is the time variable of sample point, and K is sampling time length, w [k-M]
For window function, and | | w | |=1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610569963.2A CN106228551B (en) | 2016-07-19 | 2016-07-19 | The adaptive decomposition method of filter is generated based on image Segmentation Technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610569963.2A CN106228551B (en) | 2016-07-19 | 2016-07-19 | The adaptive decomposition method of filter is generated based on image Segmentation Technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106228551A CN106228551A (en) | 2016-12-14 |
| CN106228551B true CN106228551B (en) | 2019-04-23 |
Family
ID=57532530
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610569963.2A Expired - Fee Related CN106228551B (en) | 2016-07-19 | 2016-07-19 | The adaptive decomposition method of filter is generated based on image Segmentation Technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106228551B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800777A (en) * | 2018-09-21 | 2019-05-24 | 上海营阅企业管理服务中心(有限合伙) | A kind of urine test paper physical signs automatic identifying method |
| CN109741330A (en) * | 2018-12-21 | 2019-05-10 | 东华大学 | A kind of medical image cutting method of mixed filtering strategy and fuzzy C-mean algorithm |
| CN109470647B (en) * | 2019-01-20 | 2020-11-24 | 南京林业大学 | Method for measuring terahertz absorption spectrum of water vapor |
| CN111862007B (en) * | 2020-07-02 | 2021-01-08 | 哈尔滨市科佳通用机电股份有限公司 | Freight car brake cylinder inclination detection method based on variance region segmentation |
| CN114759951B (en) * | 2022-06-15 | 2022-09-02 | 成都中星世通电子科技有限公司 | Frequency hopping signal real-time blind detection method, parameter estimation method, system and terminal |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103995289A (en) * | 2014-05-19 | 2014-08-20 | 中国石油大学(华东) | Time-varying mixed-phase seismic wavelet extraction method based on time-frequency spectrum simulation |
| CN105678781A (en) * | 2016-01-19 | 2016-06-15 | 中国人民解放军电子工程学院 | Object micro Doppler feature separation and extraction method based on edge detection |
-
2016
- 2016-07-19 CN CN201610569963.2A patent/CN106228551B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103995289A (en) * | 2014-05-19 | 2014-08-20 | 中国石油大学(华东) | Time-varying mixed-phase seismic wavelet extraction method based on time-frequency spectrum simulation |
| CN105678781A (en) * | 2016-01-19 | 2016-06-15 | 中国人民解放军电子工程学院 | Object micro Doppler feature separation and extraction method based on edge detection |
Non-Patent Citations (4)
| Title |
|---|
| Binary and ratio time-frequency masks for robust speech recognition;Soundararajan Srinivasan等;《Speech Communication》;20061231;第48卷;第1486-1501页 |
| 一种二值图像连通区域标记的新方法;刘奇琦等;《计算机工程与应用》;20121231;第48卷(第11期);第178-180页 |
| 基于时频图像处理的多分量ＬＦＭ信号分离;刘歌等;《航天电子对抗》;20151031;第31卷(第5期);第46-49页 |
| 基于时频子空间的多分量宽带调频信号DOA 估计;王雪飞等;《电讯技术》;20121031;第52卷(第10期);基于时频子空间的多分量宽带调频信号DOA 估计 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106228551A (en) | 2016-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106228551B (en) | The adaptive decomposition method of filter is generated based on image Segmentation Technology | |
| Wang et al. | Complete ensemble local mean decomposition with adaptive noise and its application to fault diagnosis for rolling bearings | |
| Tong et al. | A fault diagnosis approach for rolling element bearings based on RSGWPT-LCD bilayer screening and extreme learning machine | |
| CN101477140B (en) | Automatic generation of frequency domain mask | |
| Bao et al. | Ship classification using nonlinear features of radiated sound: An approach based on empirical mode decomposition | |
| Senroy et al. | Two techniques to enhance empirical mode decomposition for power quality applications | |
| CN101441766B (en) | SAR image fusion method based on multiple-dimension geometric analysis | |
| Cao et al. | Zoom synchrosqueezing transform and iterative demodulation: methods with application | |
| CN103512960A (en) | Ultrasound array imaging method | |
| DE202013105253U1 (en) | imaging device | |
| Veltcheva et al. | Nonlinearity of abnormal waves by the Hilbert–Huang Transform method | |
| CN109359633B (en) | Signal joint classification method based on Hilbert-Huang transform and wavelet ridge line | |
| Zhongrong et al. | Application of complex wavelet transform to suppress white noise in GIS UHF PD signals | |
| Ahmadi et al. | Types of EMD algorithms | |
| CN107110967A (en) | Tracking process device and tracking process method | |
| Seferi et al. | A novel arc detection method for DC railway systems | |
| CN108761202B (en) | Harmonic detection method combining pole symmetric modal decomposition and Hilbert transform | |
| CN109965905A (en) | A kind of radiography region detection imaging method based on deep learning | |
| Furusato et al. | Fractal analysis of positive pulsed streamer patterns in supercritical carbon dioxide | |
| CN108680782B (en) | Voltage flicker parameter detection method based on extreme point symmetric mode decomposition | |
| Adoul et al. | Time-frequency readability enhancement of compact support kernel-based distributions using image post-processing: Application to instantaneous frequency estimation of M-ary frequency shift keying signals | |
| Ponomareva et al. | Application of parametric discrete Fourier transform in nondestructive testing of composite materials with a free oscillation method | |
| DE202013105255U1 (en) | ultrasonic testing | |
| CN109799284A (en) | A kind of multiple harmonic auto-adaptive separating method of ultrasound echo signal | |
| Sanabria-Villamizar et al. | Hybrid technique for the analysis of non-linear and non-stationary signals focused on power quality |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190423 Termination date: 20190719 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |