CN110458856A - A kind of crater image edge detection method, device and storage medium - Google Patents
A kind of crater image edge detection method, device and storage medium Download PDFInfo
- Publication number
- CN110458856A CN110458856A CN201910661667.9A CN201910661667A CN110458856A CN 110458856 A CN110458856 A CN 110458856A CN 201910661667 A CN201910661667 A CN 201910661667A CN 110458856 A CN110458856 A CN 110458856A
- Authority
- CN
- China
- Prior art keywords
- edge
- image
- subgraph
- formula
- edge image
- 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- Withdrawn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
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- 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]
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
Abstract
The present invention provides a kind of crater image edge detection method, device and storage medium, its method includes: to obtain initial crater image, it is extracted according to edge of the wavelet modulus maxima method to initial crater image, obtain first edge image, it is extracted according to edge of the Morphology edge detection algorithm to initial crater image, obtain second edge image, wavelet decomposition is carried out to first edge image and the second edge image respectively, it obtains first edge and decomposes image set and second edge decomposition image set, image set is decomposed to first edge and second edge decomposes the low frequency subgraph picture in image set and carries out fusion treatment, and the high frequency subgraph in image set and second edge decomposition image set is decomposed to first edge and carries out fusion treatment, obtain combination of edge image set.Initial pictures are divided into the mode of two edge image combination processings by the present invention, are able to suppress picture noise, keep marginal information prominent, obtained edge continuity is good.
Description
Technical field
The invention mainly relates to technical field of image processing, and in particular to a kind of crater image edge detection method, device
And storage medium.
Background technique
The increasingly maturation of computer vision technique, greatly improves the reliability of Automation of Welding.It was welding
The real-time monitoring of welding quality and control are the premises that Automation of Welding is realized in journey, and accurately On-line Control is very for welding quality
It is determined in big degree by extracting the precision of melt tank edge.Edge contains a large amount of valuable information, from melt tank edge image
In maximum width information in available crater image build and according to molten bath half is long and the relevant informations such as molten bath butt angle
The characteristic image of vertical welding pool, to adjust industrial molten bath welding conditions according to crater image mapping model, realize to molten bath
The control of welding process.
The method of existing Image Edge-Detection has very much, is all to utilize in spatial filter the most commonly used is spatial filter
Operator carries out edge detection, but operator is generally very sensitive to noise, there is great defect in practice.
Summary of the invention
The technical problem to be solved by the present invention is in view of the deficiencies of the prior art, provide a kind of crater image edge detection
Method, apparatus and storage medium.
The technical scheme to solve the above technical problems is that a kind of crater image edge detection method, including such as
Lower step:
Obtain initial crater image.
It is extracted according to edge of the wavelet modulus maxima method to the initial crater image, obtains first edge figure
Picture, and extracted according to edge of the Morphology edge detection algorithm to the initial crater image, obtain second edge
Image.
Wavelet decomposition is carried out to the first edge image and the second edge image respectively, obtains first edge decomposition
Image set and second edge decompose image set, and it includes the first low frequency subgraph picture and the first high frequency that the first edge, which decomposes image set,
Subgraph, it includes the second low frequency subgraph picture and the second high frequency subgraph that the second edge, which decomposes image set,.
Fusion treatment is carried out to first low frequency subgraph picture and second low frequency subgraph picture, and to first high frequency
High frequency subgraph described in subgraph and second high frequency subgraph carries out fusion treatment, obtains combination of edge image set, described
Combination of edge image set include it is fused after low frequency subgraph picture and high frequency subgraph.
Processing is reconstructed to the combination of edge image set, obtains crater image edge.
Another technical solution that the present invention solves above-mentioned technical problem is as follows: a kind of crater image edge detecting device, packet
It includes:
Initial pictures obtain module, for obtaining initial crater image.
Edge extracting module, for being mentioned according to edge of the wavelet modulus maxima method to the initial crater image
It takes, obtains first edge image, and carry out according to edge of the Morphology edge detection algorithm to the initial crater image
It extracts, obtains second edge image.
Decomposing module is obtained for carrying out wavelet decomposition to the first edge image and the second edge image respectively
Image set is decomposed to first edge and second edge decomposes image set, and it includes the first low frequency that the first edge, which decomposes image set,
Image and the first high frequency subgraph, it includes the second low frequency subgraph picture and the second high frequency subgraph that the second edge, which decomposes image set,
Picture.
Fusion Module, for carrying out fusion treatment to first low frequency subgraph picture and second low frequency subgraph picture, and
Fusion treatment is carried out to first high frequency subgraph and second high frequency subgraph, obtains combination of edge image set, it is described
Combination of edge image set include it is fused after low frequency subgraph picture and high frequency subgraph.
Reconstructed module obtains crater image edge for processing to be reconstructed to the combination of edge image set.
Another technical solution that the present invention solves above-mentioned technical problem is as follows: a kind of crater image edge detecting device, packet
The computer program that includes memory, processor and storage in the memory and can run on the processor, works as institute
When stating the processor execution computer program, crater image edge detection method as described above is realized.
Another technical solution that the present invention solves above-mentioned technical problem is as follows: a kind of computer readable storage medium, described
Computer-readable recording medium storage has computer program, when the computer program is executed by processor, realizes institute as above
The crater image edge detection method stated.
The beneficial effects of the present invention are: by wavelet modulus maxima method and Morphology edge detection algorithm to first
Beginning crater image is detected, and two edge images are respectively obtained, and two edge images are decomposed, respectively obtain low frequency and
High frequency imaging, then the low frequency of two edge images and high frequency imaging are subjected to fusion and reconstruction processing, obtain final molten bath figure
As edge；Initial pictures are divided into the mode of two edge image combination processings, are able to suppress picture noise, keep marginal information prominent
Out, the edge continuity obtained is good.
Detailed description of the invention
Fig. 1 is the flow diagram for the crater image edge detection method that one embodiment of the invention provides；
Fig. 2 is the module frame chart for the crater image edge detecting device that one embodiment of the invention provides.
Specific embodiment
The principle and features of the present invention will be described below with reference to the accompanying drawings, and the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the invention.
Fig. 1 is the flow diagram for the crater image edge detection method that one embodiment of the invention provides.
As shown in Figure 1, a kind of crater image edge detection method, includes the following steps:
Obtain initial crater image.
It is extracted according to edge of the wavelet modulus maxima method to the initial crater image, obtains first edge figure
Picture, and extracted according to edge of the Morphology edge detection algorithm to the initial crater image, obtain second edge
Image.
Wavelet decomposition is carried out to the first edge image and the second edge image respectively, obtains first edge decomposition
Image set and second edge decompose image set, and it includes the first low frequency subgraph picture and the first high frequency that the first edge, which decomposes image set,
Subgraph, it includes the second low frequency subgraph picture and the second high frequency subgraph that the second edge, which decomposes image set,.
Fusion treatment is carried out to first low frequency subgraph picture and second low frequency subgraph picture, and to first high frequency
Subgraph and second high frequency subgraph carry out fusion treatment, obtain combination of edge image set, the combination of edge image set
Including the low frequency subgraph picture and high frequency subgraph after fused.
Processing is reconstructed to the combination of edge image set, obtains crater image edge.
In above-described embodiment, by wavelet modulus maxima method and Morphology edge detection algorithm to initial molten bath
Image is detected, and two edge images are respectively obtained, and two edge images are decomposed, low frequency and high frequency figure are respectively obtained
Picture, then the low frequency of two edge images and high frequency imaging are subjected to fusion and reconstruction processing, obtain final crater image edge；
Initial pictures are divided into the mode of two edge image combination processings, are able to suppress picture noise, keeps marginal information prominent, obtains
Edge continuity it is good.
Optionally, as an embodiment of the present invention, it is described according to wavelet modulus maxima method to the molten bath side
The process that the edge of edge image extracts includes:
If the melt tank edge image is f (x, y), scale is s and smooth function is θs(x, y), melt tank edge image f
(x, y) smoothed function #s(x, y) carries out two-dimentional dyadic wavelet transform under scale s effect, calculates level side by the first formula
To gradient vector and vertical gradient vector, first formula are as follows:
Wherein,Indicate edgeGradient vector in the horizontal direction,Indicate side
EdgeGradient vector vertically,For vector, vectorMould take part
The point of maximum has corresponded to edgeThe position of catastrophe point or the sharp point variation of corresponding position；Its size reflects the gray-scale intensity of the position.
According to horizontal direction gradient vectorVertical gradient vectorInstitute is calculated with the second formula
State the modulus value of melt tank edge image f (x, y), second formula are as follows:
The gradient vector direction of the melt tank edge image f (x, y), the third formula are calculated according to third formula are as follows:
The Local modulus maxima of the melt tank edge image f (x, y), i.e. basis are obtained according to the modulus valueCalculate edgeThe direction of point corresponding to modulus maximum, obtains gradient, according to the gradient
Direction vector detects the Local modulus maxima, obtains the first edge image.
Optionally, as an embodiment of the present invention, described to be melted according to Morphology edge detection algorithm to described
The process that the edge of pond edge image extracts includes:
If the melt tank edge image is f (x, y), if structural element is B,
Dilation operation, the dilation operation formula are carried out to melt tank edge image f (x, y) according to dilation operation formula are as follows:
Wherein, (x-i, y-i) ∈ Df, (x+i, y+i) ∈ Df, (i, j) ∈ DB,
Edge, first inspection are detected in the melt tank edge image f (x, y) of expanded operation according to the first detective operators
Measuring and calculating are as follows:
Erosion operation, the erosion operation formula are carried out to melt tank edge image f (x, y) according to erosion operation formula are as follows:
(f Θ B) (x, y)=f (x, y) Θ B (x, y)=min { f (x+i, y+i)-B (i, j) },
Wherein, (x-i, y-i) ∈ Df, (x+i, y+i) ∈ Df, (i, j) ∈ DB,
Edge, second inspection are detected in the melt tank edge image f (x, y) through erosion operation according to the second detective operators
Measuring and calculating are as follows:
Ed2(x, y)=f (x, y)-f (x, y) Θ B (x, y),
Erosion operation again, the 4th formula are first expanded to the melt tank edge image f (x, y) according to the 4th formula are as follows:
It is described according to third detective operators to detection edge in expanded and erosion operation melt tank edge image f (x, y)
Third detective operators are as follows:
The second edge image is obtained according to first detective operators, the second detective operators and third detective operators.
In above-described embodiment, first edge image is obtained using wavelet modulus maxima method, utilizes mathematical morphology side
Edge detection algorithm obtains second edge image, using the marginality of first edge image is good and the continuity of second edge image is good
The advantages of, the two is handled, marginality and the good crater image edge of continuity are obtained.
Optionally, as an embodiment of the present invention, described respectively to the first edge image and second side
Edge image carry out wavelet decomposition process include:
If the melt tank edge image is f (x, y), according to the 5th formula to the first edge image and the second edge
Image carries out wavelet decomposition, the 5th formula are as follows:
Wherein, C indicates the low-frequency approximation subgraph obtained after the first edge image or the second edge picture breakdown
Picture,Indicate the horizontal high-frequent details subgraph obtained after the first edge image or the second edge picture breakdown,Indicate the vertical high frequency details subgraph obtained after the first edge image or the second edge picture breakdown,
Indicate that the diagonal high frequency detail subgraph obtained after the first edge image or the second edge picture breakdown, H indicate ruler
The coefficient matrix of coefficient respective filter is spent, G indicates that the coefficient matrix of wavelet coefficient respective filter, H ' and G ' respectively indicate H
With the associate matrix of G, j indicates Decomposition order, and the first edge decomposes image set and the second edge decomposes image
Collection respectively includes low-frequency approximation subgraph, horizontal high-frequent details subgraph, vertical high frequency details subgraph and diagonal high frequency detail
Subgraph.
It will be appreciated that the first high frequency subgraph includes the horizontal high-frequent details subgraph obtained by first edge picture breakdown
Picture, vertical high frequency details subgraph and diagonal high frequency detail subgraph；Second high frequency subgraph includes by second edge image point
Horizontal high-frequent details subgraph, vertical high frequency details subgraph and the diagonal high frequency detail subgraph that solution obtains.
Specifically, three layers of wavelet decomposition are carried out using db4 small echo, obtains low-frequency approximation subgraph, horizontal high-frequent details
Image, vertical high frequency details subgraph and diagonal high frequency detail subgraph.
In above-described embodiment, the low-frequency image of first edge image and second edge image is merged, first edge figure is made
Multiple high frequency imagings of picture and second edge image fusion, to obtain clearly image border.
Optionally, as an embodiment of the present invention, processing is reconstructed in the melt tank edge image after described pair of decomposition
Process include:
Processing, the small echo inversion are reconstructed to the melt tank edge image after decomposition according to wavelet inverse transformation reconstruction formula
Change reconstruction formula are as follows:
Wherein, Cj-1Crater image edge after indicating reconstruct, CjIndicate fused low-frequency approximation subgraph,It indicates
Fused horizontal high-frequent details subgraph,Indicate fused vertical high frequency details subgraph, DdIndicate fused right
Angle high frequency detail subgraph, G indicate the coefficient matrix of wavelet coefficient respective filter, and the conjugation that H ' and G ' respectively indicate H and G turns
Matrix is set, j indicates Decomposition order.
In above-described embodiment, fused low-frequency image and multiple high frequency imagings are all reconstructed, to obtain marginality
And the crater image edge that continuity is good, clarity and accuracy are all preferable.
Fig. 2 is the module frame chart for the crater image edge detecting device that one embodiment of the invention provides.
Optionally, as an embodiment of the present invention, as shown in Fig. 2, a kind of crater image edge detecting device, packet
It includes:
Initial pictures obtain module, for obtaining initial crater image.
Edge extracting module, for being mentioned according to edge of the wavelet modulus maxima method to the initial crater image
It takes, obtains first edge image, and carry out according to edge of the Morphology edge detection algorithm to the initial crater image
It extracts, obtains second edge image.
Decomposing module is obtained for carrying out wavelet decomposition to the first edge image and the second edge image respectively
Image set is decomposed to first edge and second edge decomposes image set, and it includes the first low frequency that the first edge, which decomposes image set,
Image and the second high frequency subgraph, it includes the second low frequency subgraph picture and the second high frequency subgraph that the second edge, which decomposes image set,
Picture.
Fusion Module, for carrying out fusion treatment to first low frequency subgraph picture and second low frequency subgraph picture, and
Fusion treatment is carried out to first high frequency subgraph and second high frequency subgraph, obtains combination of edge image set, it is described
Combination of edge image set include it is fused after low frequency subgraph picture and high frequency subgraph.
Reconstructed module obtains crater image edge for processing to be reconstructed to the combination of edge image set.
In above-described embodiment, by wavelet modulus maxima method and Morphology edge detection algorithm to initial molten bath
Image is detected, and two edge images are respectively obtained, and two edge images are decomposed, low frequency and high frequency figure are respectively obtained
Picture, then the low frequency of two edge images and high frequency imaging are subjected to fusion and reconstruction processing, obtain final crater image edge；
Initial pictures are divided into the mode of two edge image combination processings, are able to suppress picture noise, keeps marginal information prominent, obtains
Edge continuity it is good.
Optionally, as an embodiment of the present invention, the decomposing module is specifically used for:
If the melt tank edge image is f (x, y), scale is s and smooth function is θs(x, y), melt tank edge image f
(x, y) smoothed function #s(x, y) carries out two-dimentional dyadic wavelet transform under scale S effect, specifically: it is calculated by the first formula
Horizontal direction gradient vector and vertical gradient vector, first formula are as follows:
Wherein,Indicate edgeGradient vector in the horizontal direction,Indicate side
EdgeGradient vector vertically,For vector, vectorMould take part
The point of maximum has corresponded to edgeThe position of catastrophe point or the sharp point variation of corresponding position；Its size reflects the gray-scale intensity of the position.
According to horizontal direction gradient vectorVertical gradient vectorInstitute is calculated with the second formula
State the modulus value of melt tank edge image f (x, y), second formula are as follows:
The gradient vector direction of the melt tank edge image f (x, y), the third formula are calculated according to third formula are as follows:
The Local modulus maxima of the melt tank edge image f (x, y), i.e. basis are obtained according to the modulus valueCalculate edgeThe direction of point corresponding to modulus maximum, obtains gradient, according to the gradient
Direction vector detects the Local modulus maxima, obtains the first edge image.
Optionally, as an embodiment of the present invention, the decomposing module is specifically used for:
If the melt tank edge image is f (x, y), if structural element is B,
Dilation operation, the dilation operation formula are carried out to melt tank edge image f (x, y) according to dilation operation formula are as follows:
Wherein, (x-i, y-i) ∈ Df, (x+i, y+i) ∈ Df, (i, j) ∈ DB,
Edge, first inspection are detected in the melt tank edge image f (x, y) of expanded operation according to the first detective operators
Measuring and calculating are as follows:
Erosion operation, the erosion operation formula are carried out to melt tank edge image f (x, y) according to erosion operation formula are as follows:
(f Θ B) (x, y)=f (x, y) Θ B (x, y)=min { f (x+i, y+i)-B (i, j) },
Wherein, (x-i, y-i) ∈ Df, (x+i, y+i) ∈ Df, (i, j) ∈ DB,
Edge, second inspection are detected in the melt tank edge image f (x, y) through erosion operation according to the second detective operators
Measuring and calculating are as follows:
Ed2(x, y)=f (x, y)-f (x, y) Θ B (x, y),
Erosion operation again, the 4th formula are first expanded to the melt tank edge image f (x, y) according to the 4th formula are as follows:
It is described according to third detective operators to detection edge in expanded and erosion operation melt tank edge image f (x, y)
Third detective operators are as follows:
Second side is obtained according to first detective operators, second detective operators and the third detective operators
Edge image.
Optionally, another embodiment of the present invention provides a kind of crater image edge detecting devices, including memory, place
The computer program managing device and storage in the memory and can running on the processor, when the processor executes
When the computer program, crater image edge detection method as described above is realized.The device can be the devices such as computer.
Optionally, another embodiment of the present invention provides a kind of computer readable storage mediums, described computer-readable
Storage medium is stored with computer program, when the computer program is executed by processor, realizes molten bath figure as described above
As edge detection method.
It is apparent to those skilled in the art that for convenience of description and succinctly, the dress of foregoing description
The specific work process with unit is set, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of unit, only
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.
Unit may or may not be physically separated as illustrated by the separation member, shown as a unit
Component may or may not be physical unit, it can and it is in one place, or may be distributed over multiple networks
On unit.It can select some or all of unit therein according to the actual needs to realize the mesh of the embodiment of the present invention
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, is also possible to two or more units and is integrated in one unit.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
It, can if integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product
To be stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention substantially or
Say that all or part of the part that contributes to existing technology or the technical solution can embody in the form of software products
Out, which is stored in a storage medium, including some instructions are used so that a computer equipment
(can be personal computer, server or the network equipment etc.) executes all or part of each embodiment method of the present invention
Step.And storage medium above-mentioned include: USB flash disk, it is mobile hard disk, read-only memory (ROM, Read-Only Memory), random
Access various Jie that can store program code such as memory (RAM, Random Access Memory), magnetic or disk
Matter.
More than, only a specific embodiment of the invention, but scope of protection of the present invention is not limited thereto, and it is any to be familiar with
Those skilled in the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or substitutions,
These modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be wanted with right
Subject to the protection scope asked.
Claims (10)
1. a kind of crater image edge detection method, which comprises the steps of:
Obtain initial crater image；
It is extracted according to edge of the wavelet modulus maxima method to the initial crater image, obtains first edge image,
And extracted according to edge of the Morphology edge detection algorithm to the initial crater image, obtain second edge figure
Picture；
Wavelet decomposition is carried out to the first edge image and the second edge image respectively, first edge is obtained and decomposes image
Collection and second edge decompose image set, and it includes the first low frequency subgraph picture and the first high frequency subgraph that the first edge, which decomposes image set,
Picture, it includes the second low frequency subgraph picture and the second high frequency subgraph that the second edge, which decomposes image set,；
Fusion treatment is carried out to first low frequency subgraph picture and second low frequency subgraph picture, and to the first high frequency subgraph
Picture and second high frequency subgraph carry out fusion treatment, obtain combination of edge image set, the combination of edge image set includes
Low frequency subgraph picture and high frequency subgraph after fused；
Processing is reconstructed to the combination of edge image set, obtains crater image edge.
2. crater image edge detection method according to claim 1, which is characterized in that described according to WAVELET TRANSFORM MODULUS pole
The process that big value method extracts the edge of the melt tank edge image includes:
If the melt tank edge image is f (x, y), scale is s and smooth function is θs(x, y), melt tank edge image f (x, y)
Smoothed function #s(x, y) carries out two-dimentional dyadic wavelet transform under scale s effect, specifically: it is calculated by the first formula horizontal
Directional gradient vector and vertical gradient vector, first formula are as follows:
Wherein,Indicate edgeGradient vector in the horizontal direction,Indicate edgeGradient vector vertically,For vector, vectorMould take local pole
The point being worth greatly has corresponded to edgeThe position of catastrophe point or the sharp point variation of corresponding position；
According to horizontal direction gradient vectorVertical gradient vectorIt is calculated with the second formula described molten
The modulus value of pond edge image f (x, y), second formula are as follows:
The gradient vector direction of the melt tank edge image f (x, y), the third formula are calculated according to third formula are as follows:
The Local modulus maxima of the melt tank edge image f (x, y) is obtained according to the modulus value, according to the gradient vector direction
The Local modulus maxima is detected, the first edge image is obtained.
3. crater image edge detection method according to claim 1, which is characterized in that described according to mathematical morphology side
The process that edge detection algorithm extracts the edge of the melt tank edge image includes:
If the melt tank edge image is f (x, y), if structural element is B,
Dilation operation, the dilation operation formula are carried out to melt tank edge image f (x, y) according to dilation operation formula are as follows:
Wherein, (x-i, y-i) ∈ Df, (x+i, y+i) ∈ Df, (i, j) ∈ DB,
Edge is detected in the melt tank edge image f (x, y) of expanded operation according to the first detective operators, first detection is calculated
Son are as follows:
Erosion operation, the erosion operation formula are carried out to melt tank edge image f (x, y) according to erosion operation formula are as follows:
(f Θ B) (x, y)=f (x, y) Θ B (x, y)=min { f (x+i, y+i)-B (i, j) },
Wherein, (x-i, y-i) ∈ Df, (x+i, y+i) ∈ Df, (i, j) ∈ DB,
Edge is detected in the melt tank edge image f (x, y) through erosion operation according to the second detective operators, second detection is calculated
Son are as follows:
Ed2(x, y)=f (x, y)-f (x, y) Θ B (x, y),
Erosion operation again, the 4th formula are first expanded to the melt tank edge image f (x, y) according to the 4th formula are as follows:
According to third detective operators to detection edge, the third in expanded and erosion operation melt tank edge image f (x, y)
Detective operators are as follows:
The second edge figure is obtained according to first detective operators, second detective operators and the third detective operators
Picture.
4. crater image edge detection method according to claim 1, which is characterized in that described respectively to first side
The process that edge image and the second edge image carry out wavelet decomposition includes:
If the melt tank edge image is f (x, y), according to the 5th formula to the first edge image and the second edge image
Carry out wavelet decomposition, the 5th formula are as follows:
Wherein, C indicates the low-frequency approximation subgraph obtained after the first edge image or the second edge picture breakdown,Indicate the horizontal high-frequent details subgraph obtained after the first edge image or the second edge picture breakdown,
Indicate the vertical high frequency details subgraph obtained after the first edge image or the second edge picture breakdown,It indicates
The diagonal high frequency detail subgraph obtained after the first edge image or the second edge picture breakdown, H indicate scale system
The coefficient matrix of number respective filter, G indicate that the coefficient matrix of wavelet coefficient respective filter, H ' and G ' respectively indicate H's and G
Associate matrix, j indicate Decomposition order, and it includes being obtained by the first edge picture breakdown that the first edge, which decomposes image set,
Low-frequency approximation subgraph, horizontal high-frequent details subgraph, vertical high frequency details subgraph and the diagonal high frequency detail subgraph arrived,
It includes that low-frequency approximation subgraph, the level that picture breakdown obtains are decomposed by the second edge that the second edge, which decomposes image set,
High frequency detail subgraph, vertical high frequency details subgraph and diagonal high frequency detail subgraph.
5. crater image edge detection method according to claim 1, which is characterized in that the molten bath side after described pair of decomposition
The process that processing is reconstructed in edge image includes:
Processing, the wavelet inverse transformation weight are reconstructed to the melt tank edge image after decomposition according to wavelet inverse transformation reconstruction formula
Structure formula are as follows:
Wherein, Cj-1Crater image edge after indicating reconstruct, CjIndicate fused low-frequency approximation subgraph,Indicate fusion
Horizontal high-frequent details subgraph afterwards,Indicate fused vertical high frequency details subgraph, DdIndicate fused diagonal height
Frequency details subgraph, G indicate that the coefficient matrix of wavelet coefficient respective filter, H ' and G ' respectively indicate the conjugate transposition square of H and G
Battle array, j indicate Decomposition order.
6. a kind of crater image edge detecting device characterized by comprising
Initial pictures obtain module, for obtaining initial crater image；
Edge extracting module, for being extracted according to edge of the wavelet modulus maxima method to the initial crater image,
First edge image is obtained, and is mentioned according to edge of the Morphology edge detection algorithm to the initial crater image
It takes, obtains second edge image；
Decomposing module obtains for carrying out wavelet decomposition to the first edge image and the second edge image respectively
One edge decomposition image set and second edge decompose image set, and it includes the first low frequency subgraph picture that the first edge, which decomposes image set,
With the first high frequency subgraph, it includes the second low frequency subgraph picture and the second high frequency subgraph that the second edge, which decomposes image set,；
Fusion Module, for carrying out fusion treatment to first low frequency subgraph picture and second low frequency subgraph picture, and to institute
It states the first high frequency subgraph and second high frequency subgraph carries out fusion treatment, obtain combination of edge image set, the fusion
Edge graph image set include it is fused after low frequency subgraph picture and high frequency subgraph；
Reconstructed module obtains crater image edge for processing to be reconstructed to the combination of edge image set.
7. crater image edge detecting device according to claim 6, which is characterized in that the decomposing module is specifically used
In:
If the melt tank edge image is f (x, y), scale is s and smooth function is θs(x, y), melt tank edge image f (x, y)
Smoothed function #s(x, y) carries out two-dimentional dyadic wavelet transform under scale s effect, specifically: it is calculated by the first formula horizontal
Directional gradient vector and vertical gradient vector, first formula are as follows:
Wherein,Indicate edgeGradient vector in the horizontal direction,Indicate edgeGradient vector vertically,For vector, vectorMould take local pole
The point being worth greatly has corresponded to edgeThe position of catastrophe point or the sharp point variation of corresponding position；
According to horizontal direction gradient vectorVertical gradient vectorIt is calculated with the second formula described molten
The modulus value of pond edge image f (x, y), second formula are as follows:
The gradient vector direction of the melt tank edge image f (x, y), the third formula are calculated according to third formula are as follows:
The Local modulus maxima of the melt tank edge image f (x, y) is obtained according to the modulus value, according to the gradient vector direction
The Local modulus maxima is detected, the first edge image is obtained.
8. crater image edge detecting device according to claim 6, which is characterized in that the decomposing module is specifically used
In:
If the melt tank edge image is f (x, y), if structural element is B,
Dilation operation, the dilation operation formula are carried out to melt tank edge image f (x, y) according to dilation operation formula are as follows:
Wherein, (x-i, y-i) ∈ Df, (x+i, y+i) ∈ Df, (i, j) ∈ DB,
Edge is detected in the melt tank edge image f (x, y) of expanded operation according to the first detective operators, first detection is calculated
Son are as follows:
Erosion operation, the erosion operation formula are carried out to melt tank edge image f (x, y) according to erosion operation formula are as follows:
(f Θ B) (x, y)=f (x, y) Θ B (x, y)=min { f (x+i, y+i)-B (i, j) },
Wherein, (x-i, y-i) ∈ Df, (x+i, y+i) ∈ Df, (i, j) ∈ DB,
Edge is detected in the melt tank edge image f (x, y) through erosion operation according to the second detective operators, second detection is calculated
Son are as follows:
Ed2(x, y)=f (x, y)-f (x, y) Θ B (x, y),
Erosion operation again, the 4th formula are first expanded to the melt tank edge image f (x, y) according to the 4th formula are as follows:
According to third detective operators to detection edge, the third in expanded and erosion operation melt tank edge image f (x, y)
Detective operators are
The second edge figure is obtained according to first detective operators, second detective operators and the third detective operators
Picture.
9. a kind of crater image edge detecting device, including memory, processor and storage are in the memory and can be
The computer program run on the processor, which is characterized in that when the processor executes the computer program, realize
Such as the described in any item crater image edge detection methods of Claims 1-4.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In, when the computer program is executed by processor, realization such as the described in any item crater image edges of Claims 1-4
Detection method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910661667.9A CN110458856A (en) | 2019-07-22 | 2019-07-22 | A kind of crater image edge detection method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910661667.9A CN110458856A (en) | 2019-07-22 | 2019-07-22 | A kind of crater image edge detection method, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110458856A true CN110458856A (en) | 2019-11-15 |
Family
ID=68482915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910661667.9A Withdrawn CN110458856A (en) | 2019-07-22 | 2019-07-22 | A kind of crater image edge detection method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110458856A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111325765A (en) * | 2020-02-18 | 2020-06-23 | 山东超越数控电子股份有限公司 | Image edge detection algorithm based on redundant wavelet transform |
| CN115631122A (en) * | 2022-11-07 | 2023-01-20 | 北京拙河科技有限公司 | Image optimization method and device for edge image algorithm |
-
2019
- 2019-07-22 CN CN201910661667.9A patent/CN110458856A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111325765A (en) * | 2020-02-18 | 2020-06-23 | 山东超越数控电子股份有限公司 | Image edge detection algorithm based on redundant wavelet transform |
| CN111325765B (en) * | 2020-02-18 | 2022-07-05 | 超越科技股份有限公司 | Image edge detection method based on redundant wavelet transform |
| CN115631122A (en) * | 2022-11-07 | 2023-01-20 | 北京拙河科技有限公司 | Image optimization method and device for edge image algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9536147B2 (en) | Optical flow tracking method and apparatus | |
| CN104978715A (en) | Non-local mean value image denoising method based on filter window and parameter adaption | |
| CN101996406A (en) | No-reference structural sharpness image quality evaluation method | |
| CN108416789A (en) | Method for detecting image edge and system | |
| EP2570966A2 (en) | Fast obstacle detection | |
| CN104282011B (en) | The method and device of interference stripes in a kind of detection video image | |
| CN109632808B (en) | Edge defect detection method and device, electronic equipment and storage medium | |
| CN108827181B (en) | Vision-based plate surface detection method | |
| CN109685766A (en) | A kind of Fabric Defect detection method based on region fusion feature | |
| CN104574393A (en) | Three-dimensional pavement crack image generation system and method | |
| DE112014003818T5 (en) | Object estimator and object estimation method | |
| CN106163404A (en) | Lung for ray image is split and bone suppression technology | |
| CN110458856A (en) | A kind of crater image edge detection method, device and storage medium | |
| CN104915930B (en) | The method and device of grey level compensation and noise suppressed is carried out to image | |
| CN108550145A (en) | A kind of SAR image method for evaluating quality and device | |
| CN113012157A (en) | Visual detection method and system for equipment defects | |
| KR20200068709A (en) | Human body identification methods, devices and storage media | |
| CN112396618B (en) | Grain boundary extraction and grain size measurement method based on image processing | |
| CN105915763A (en) | Video denoising and detail enhancement method and device | |
| CN105530505B (en) | 3-D view conversion method and device | |
| Biswas et al. | Spine medical image fusion using wiener filter in shearlet domain | |
| CN106846262A (en) | Remove the method and system of mosquito noise | |
| Khan et al. | Fully automatic heart beat rate determination in digital video recordings of rat embryos | |
| CN109785312A (en) | A kind of image fuzzy detection method, system and electronic equipment | |
| CN111860326B (en) | Building site article movement detection method, device, equipment and storage medium |
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: 20191115 |
|
| WW01 | Invention patent application withdrawn after publication |