CN109685752A - A kind of multiple dimensioned Shearlet area image method for amalgamation processing decomposed based on block - Google Patents
A kind of multiple dimensioned Shearlet area image method for amalgamation processing decomposed based on block Download PDFInfo
- Publication number
- CN109685752A CN109685752A CN201910019110.5A CN201910019110A CN109685752A CN 109685752 A CN109685752 A CN 109685752A CN 201910019110 A CN201910019110 A CN 201910019110A CN 109685752 A CN109685752 A CN 109685752A
- Authority
- CN
- China
- Prior art keywords
- shearlet
- block
- image
- coefficient
- decomposed
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012545 processing Methods 0.000 title claims abstract description 23
- 238000005267 amalgamation Methods 0.000 title claims abstract description 17
- 230000004927 fusion Effects 0.000 claims abstract description 52
- 230000009466 transformation Effects 0.000 claims abstract description 11
- 230000000694 effects Effects 0.000 abstract description 22
- 230000000903 blocking effect Effects 0.000 abstract description 9
- 230000000007 visual effect Effects 0.000 abstract description 3
- 238000000354 decomposition reaction Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000007500 overflow downdraw method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000007499 fusion processing Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
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 using two or more images, e.g. averaging or subtraction
-
- 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
- G06T7/0012—Biomedical image inspection
-
- 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
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/42—Analysis of texture based on statistical description of texture using transform domain methods
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of multiple dimensioned Shearlet area image method for amalgamation processing decomposed based on block, it comprises the following steps that step S1, two images to be fused are subjected to Shearlet direct transform respectively, obtain the Shearlet coefficient of different scale, different directions；The Shearlet coefficient of different scale, different directions is decomposed into multiple sub-blocks by step S2；Step S3 carries out fusion treatment to low scale Shearlet coefficient using local variance algorithm；Step S4 carries out fusion treatment to high yardstick Shearlet coefficient using local energy maximum algorithm；Step S5 carries out Shearlet inverse transformation to the Shearlet coefficient after fusion treatment, obtains fused image.Fusion accuracy of the present invention is higher, syncretizing effect is more preferable, can avoid blocking artifact phenomenon and blooming occur, and the effective protection detailed information of image improves visual effect and improves the resolution ratio of image, has better meet application requirement.
Description
Technical field
The present invention relates to image processing methods more particularly to a kind of multiple dimensioned Shearlet area image decomposed based on block to melt
Close processing method.
Background technique
In the prior art, image co-registration is to generate the image for the Same Scene that different imaging mechanisms or different time obtain
One information image more abundant, image fusion technology have important application in many fields, as computer vision,
Medicine, remote sensing, meteorology and military field have and extremely important application.Multiple focussing image can make far and near different scenes poly-
Burnt part is more accurate, is more clear the distant view of image and close shot by fusion.Different sensors can obtain image not
Same feature, such as infrared image and visible images, radar is merged with infrared image, computer tomography CT and nuclear magnetic resonance figures
As MRI image.It, can be with rich image information, raising resolution ratio and identification by being merged to the image that multisensor obtains
Degree, these technologies suffer from highly important application on military and civil field.
The effect of picture breakdown method directly influences the quality of image co-registration, discrete cosine transform (DCT) and small echo
Transformation has been widely applied to field of image processing.DCT has the characteristics that be simple and efficient, and is suitble to processing in real time, however it is merged
Effect does not have wavelet transformation good.Between past 20 years, wavelet transformation has one-dimensional signal with it and accurately indicates to obtain
It widely applies, however what is denounced by people is that its one-dimensional excellent characteristics is difficult to be extended to 2D 3D data.
On the other hand, the design of fusion criterion is also particularly important to the effect of fusion.Image co-registration is carried out in the transform domain as illustrated
Different fusion methods mainly is used to the coefficient of different sub-band.Mainly there is absolute coefficient maximal criterion average energy maximum
Criterion and local variance criterion etc..1993, Burt and Kolczynski proposed a kind of fusion criterion of split window, and
Occurs the fusion method chosen based on window again afterwards, however these methods will lead to the appearance of blocking artifact.
Although conventional DCT method and small wave converting method indicate image sparse there are above-mentioned fusion treatment mode
Effect is not good enough, and multi-direction resolving effect is not good enough, in addition, will appear blocking artifact based on the fusion method that block decomposes, is unfavorable for
Image co-registration, it is difficult to meet application demand.
Summary of the invention
The technical problem to be solved in the present invention is that in view of the deficiencies of the prior art, providing one kind can avoid block effect occur
Phenomenon is answered, while syncretizing effect is good, the high multiple dimensioned Shearlet area image fusion treatment side decomposed based on block of fusion accuracy
Method.
In order to solve the above technical problems, the present invention adopts the following technical scheme that.
A kind of multiple dimensioned Shearlet area image method for amalgamation processing decomposed based on block comprising have the following steps: step
Two images to be fused are carried out Shearlet direct transform respectively, obtain the Shearlet of different scale, different directions by rapid S1
Coefficient；The Shearlet coefficient of different scale, different directions is decomposed into multiple sub-blocks by step S2；Step S3 utilizes local side
Difference algorithm carries out fusion treatment to low scale Shearlet coefficient；Step S4, using local energy maximum algorithm to high yardstick
Shearlet coefficient carries out fusion treatment；Step S5 carries out Shearlet inverse transformation to the Shearlet coefficient after fusion treatment,
Obtain fused image.
Preferably, in the step S3, after carrying out fusion treatment to low scale Shearlet coefficient, image low frequency letter is obtained
Edge and textural characteristics in breath.
Preferably, in the step S4, after carrying out fusion treatment to high yardstick Shearlet coefficient, image high frequency letter is obtained
It include the minutia of profile in breath.
Preferably, in the step S2, the Shearlet coefficient of different scale, different directions, which is decomposed into multiple sizes, is
The sub-block Y of N × N, for any sub-block Y, mean μ and variances sigma2It is as follows:
In formula, X indicates source images A, source images B, YX(i, j) indicates (i, j) a pixel of the Y block in image X.
Preferably, in the step S3, low scale Shearlet coefficient is selected to be merged from source images A, source images B
Processing:
In formula, (k, l) indicates the sub-block of row k l column in the image after decomposing.
Preferably, in the step S4, for high yardstick Shearlet coefficient, each sub-block local energy E is defined as:
It preferably, include: that consistency desired result is carried out to the Shearlet coefficient after fusion treatment after the step S4.
Preferably, consistency desired result is carried out to the Shearlet coefficient after fusion treatment using 3 × 3 mean filters.
Preferably, in the step S1, image to be fused is multiple focussing image or multi-sensor image.
Preferably, this method is realized by being installed on the image processing software of computer system.
In the multiple dimensioned Shearlet area image method for amalgamation processing disclosed by the invention decomposed based on block, in different scale
It is handled in the form of block decomposition on the Shearlet coefficient of different directions, while being respectively adopted in low scale and high yardstick
Local variance and the maximum algorithm of local energy carry out image co-registration processing, are preferably solved using sparse Shearlet coefficient
Conventional block decomposition method leads to the problem of blooming, and compared to existing technologies, fusion accuracy of the present invention is higher, fusion effect
Fruit is more preferable, can avoid blocking artifact phenomenon and blooming occur, and the effective protection detailed information of image improves visual effect
And the resolution ratio of image is improved, better meet application requirement.
Detailed description of the invention
Fig. 1 is the flow chart of image fusion processing method；
Fig. 2 is multi-focus image fusion treated effect picture one；
Fig. 3 is multi-focus image fusion treated effect picture two；
Fig. 4 is multi-focus image fusion treated effect picture three；
Fig. 5 is Multi-sensor Image Fusion treated effect picture one；
Fig. 6 is Multi-sensor Image Fusion treated effect picture two；
Fig. 7 is Multi-sensor Image Fusion treated effect picture three.
Specific embodiment
The present invention is described in more detail with reference to the accompanying drawings and examples.
The invention discloses a kind of multiple dimensioned Shearlet area image method for amalgamation processing decomposed based on block, please refer to figure
1 comprising have the following steps:
Two images to be fused are carried out Shearlet direct transform respectively, obtain different scale, different directions by step S1
Shearlet coefficient；
The Shearlet coefficient of different scale, different directions is decomposed into multiple sub-blocks by step S2；
Step S3 carries out fusion treatment to low scale Shearlet coefficient using local variance algorithm；
Step S4 carries out fusion treatment to high yardstick Shearlet coefficient using local energy maximum algorithm；
Step S5 carries out Shearlet inverse transformation to the Shearlet coefficient after fusion treatment, obtains fused image.
In the above method, on the Shearlet coefficient of different scale different directions in the form of block decomposition
Reason, while local variance and the maximum algorithm progress image co-registration processing of local energy is respectively adopted in low scale and high yardstick,
It preferably solves the problems, such as that conventional block decomposition method generates blooming using sparse Shearlet coefficient, compares existing skill
For art, fusion accuracy of the present invention is higher, syncretizing effect is more preferable, can avoid blocking artifact phenomenon and blooming occur, effectively protects
The detailed information of image has been protected, visual effect is improved and has improved the resolution ratio of image, has better meet application requirement.
In the embodiment of the present invention step S1, by taking a size is the image of m × n as an example, 4 scales are carried out to it
Shearlet transformation, available 49 sizes are similarly the Shearlet coefficient of the different scale of m × n, different directions.
In actual process, low scale Shearlet coefficient carries more low-frequency information, in this regard, in the step
In S3, after carrying out fusion treatment to low scale Shearlet coefficient, the edge and textural characteristics in image low-frequency information are obtained.
Similarly, image medium-high frequency information often information such as example traditional thread binding profile of details of carrier's image, in this regard, the step
In rapid S4, after carrying out fusion treatment to high yardstick Shearlet coefficient, the details obtained in image high-frequency information comprising profile is special
Sign.
Further, in the step S2, the Shearlet coefficient of different scale, different directions is decomposed into multiple sizes
For the sub-block Y of N × N, for any sub-block Y, mean μ and variances sigma2It is as follows:
In formula, X indicates source images A, source images B, YX(i, j) indicates (i, j) a pixel of the Y block in image X.
About the treatment process of local variance algorithm, in the step S3, low scale is selected from source images A, source images B
Shearlet coefficient carries out fusion treatment:
In formula, (k, l) indicates the sub-block of row k l column in the image after decomposing.
On this basis, in the step S4, for high yardstick Shearlet coefficient, each sub-block local energy E definition
Are as follows:
It include: to fusion after the step S4 in the present embodiment to exclude the blocking artifact phenomenon as caused by erroneous judgement
Treated, and Shearlet coefficient carries out consistency desired result.Specifically refer to, using 3 × 3 mean filters to fusion treatment after
Shearlet coefficient carries out consistency desired result.Using the above process, can prevent from being coefficient block B or coefficient around coefficient block A
The case where being all coefficient block A around block B appearance.
As a preferred method, in the step S1, image to be fused is multiple focussing image or multisensor figure
Picture.Based on These characteristics, so that the present invention is not only suitable for multi-focus image fusion, it is also applied for answering for Multi-sensor Image Fusion
Use occasion.
In actual application, this method is realized by being installed on the image processing software of computer system.
The present invention carries out multi-focus image fusion treated effect picture referring to figure 2. to Fig. 4, and the Fig. 2 is right into Fig. 4
Figure be to it is left, in the two figures effect pictures that obtained after fusion treatment, by contrast as it can be seen that after multi-focus image fusion processing
The fusion results arrived, subjective vision effect is preferable, does not introduce illusion, also without blocking artifact and blooming；
The present invention carries out Multi-sensor Image Fusion treated effect picture referring to figure 5. to Fig. 7, the Fig. 5 into Fig. 7,
Right figure be to it is left, in the effect picture that obtained after fusion treatment of two figures.According to Fig. 5 as can be seen that it is fused treated figure
As retaining bone and institutional framework all than more complete, information more abundant is provided for clinic；Fig. 6 is that Review for Helicopter is different
The image of photoelectric sensor acquisition, fused treated that image is more clear intuitively the identification of road and river；Fig. 7 is
The remote sensing images of different spectrum, in fused treated image, the resolution ratio in road and house has further raising.
The multiple dimensioned Shearlet area image method for amalgamation processing disclosed by the invention decomposed based on block, compares existing skill
Beneficial effect for art is that tradition is compared in the mathematic(al) manipulation present invention employs Shearlet transformation as processing image
DCT and wavelet transformation for, the present invention is expressed with better image, and details to image and directionality are held more quasi-
Really；Secondly, the different scale different directions in the domain Shearlet are used with the meter of piecemeal present invention employs the algorithm that block decomposes
Calculation mode, it is preferable based on block decomposition algorithm syncretizing effect；Again, since Shearlet transformation can produce redundancy coefficient, so
Shearlet coefficient number is tens times of the number of pixels of original image, and the coefficient of redundancy is able to solve conventional block and decomposes generation
Blocking artifact；In addition, the present invention uses the step of consistency check further to eliminate the blocking artifact phenomenon as caused by erroneous judgement,
So that the picture quality after fusion treatment is more preferable.
The above is preferred embodiments of the present invention, is not intended to restrict the invention, all in technology model of the invention
Interior done modification, equivalent replacement or improvement etc. are enclosed, should be included in the range of of the invention protect.
Claims (10)
1. a kind of multiple dimensioned Shearlet area image method for amalgamation processing decomposed based on block, which is characterized in that include as follows
Step:
Two images to be fused carry out Shearlet direct transform by step S1 respectively, obtain different scale, different directions
Shearlet coefficient；
The Shearlet coefficient of different scale, different directions is decomposed into multiple sub-blocks by step S2；
Step S3 carries out fusion treatment to low scale Shearlet coefficient using local variance algorithm；
Step S4 carries out fusion treatment to high yardstick Shearlet coefficient using local energy maximum algorithm；
Step S5 carries out Shearlet inverse transformation to the Shearlet coefficient after fusion treatment, obtains fused image.
2. the multiple dimensioned Shearlet area image method for amalgamation processing decomposed as described in claim 1 based on block, feature are existed
In, in the step S3, after carrying out fusion treatment to low scale Shearlet coefficient, obtain edge in image low-frequency information and
Textural characteristics.
3. the multiple dimensioned Shearlet area image method for amalgamation processing decomposed as described in claim 1 based on block, feature are existed
In after carrying out fusion treatment to high yardstick Shearlet coefficient, obtaining in image high-frequency information comprising profile in the step S4
Minutia.
4. the multiple dimensioned Shearlet area image method for amalgamation processing decomposed as described in claim 1 based on block, feature are existed
In, in the step S2, the Shearlet coefficient of different scale, different directions is decomposed into the sub-block Y that multiple sizes are N × N,
For any sub-block Y, mean μ and variances sigma2It is as follows:
In formula, X indicates source images A, source images B, YX(i, j) indicates (i, j) a pixel of the Y block in image X.
5. the multiple dimensioned Shearlet area image method for amalgamation processing decomposed as claimed in claim 4 based on block, feature are existed
In selecting low scale Shearlet coefficient to carry out fusion treatment from source images A, source images B in the step S3:
In formula, (k, l) indicates the sub-block of row k l column in the image after decomposing.
6. the multiple dimensioned Shearlet area image method for amalgamation processing decomposed as claimed in claim 5 based on block, feature are existed
In, in the step S4, for high yardstick Shearlet coefficient, each sub-block local energy E is defined as:
7. the multiple dimensioned Shearlet area image method for amalgamation processing decomposed as described in claim 1 based on block, feature are existed
In the step S4 includes: to carry out consistency desired result to the Shearlet coefficient after fusion treatment later.
8. the multiple dimensioned Shearlet area image method for amalgamation processing decomposed as claimed in claim 7 based on block, feature are existed
In using 3 × 3 mean filters to the Shearlet coefficient progress consistency desired result after fusion treatment.
9. the multiple dimensioned Shearlet area image method for amalgamation processing decomposed as described in claim 1 based on block, feature are existed
In in the step S1, image to be fused is multiple focussing image or multi-sensor image.
10. the multiple dimensioned Shearlet area image method for amalgamation processing decomposed as described in claim 1 based on block, feature are existed
In this method is realized by being installed on the image processing software of computer system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910019110.5A CN109685752A (en) | 2019-01-09 | 2019-01-09 | A kind of multiple dimensioned Shearlet area image method for amalgamation processing decomposed based on block |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910019110.5A CN109685752A (en) | 2019-01-09 | 2019-01-09 | A kind of multiple dimensioned Shearlet area image method for amalgamation processing decomposed based on block |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109685752A true CN109685752A (en) | 2019-04-26 |
Family
ID=66192117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910019110.5A Pending CN109685752A (en) | 2019-01-09 | 2019-01-09 | A kind of multiple dimensioned Shearlet area image method for amalgamation processing decomposed based on block |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109685752A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950714A (en) * | 2020-08-24 | 2020-11-17 | 重庆市云迈科技有限公司 | Energy spectrum CT image domain material identification method based on 3D full convolution neural network |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000275906A (en) * | 1999-03-23 | 2000-10-06 | Konica Corp | Method and device for formation of image, and developing toner used therefor |
| CN101546428A (en) * | 2009-05-07 | 2009-09-30 | 西北工业大学 | Image fusion of sequence infrared and visible light based on region segmentation |
| CN103985104A (en) * | 2014-02-20 | 2014-08-13 | 江南大学 | Multi-focusing image fusion method based on higher-order singular value decomposition and fuzzy inference |
| CN104008537A (en) * | 2013-11-04 | 2014-08-27 | 无锡金帆钻凿设备股份有限公司 | Novel noise image fusion method based on CS-CT-CHMM |
| CN104268833A (en) * | 2014-09-15 | 2015-01-07 | 江南大学 | New image fusion method based on shift invariance shearlet transformation |
| CN105894483A (en) * | 2016-03-30 | 2016-08-24 | 昆明理工大学 | Multi-focusing image fusion method based on multi-dimensional image analysis and block consistency verification |
| CN106897987A (en) * | 2017-01-18 | 2017-06-27 | 江南大学 | Image interfusion method based on translation invariant shearing wave and stack own coding |
-
2019
- 2019-01-09 CN CN201910019110.5A patent/CN109685752A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000275906A (en) * | 1999-03-23 | 2000-10-06 | Konica Corp | Method and device for formation of image, and developing toner used therefor |
| CN101546428A (en) * | 2009-05-07 | 2009-09-30 | 西北工业大学 | Image fusion of sequence infrared and visible light based on region segmentation |
| CN104008537A (en) * | 2013-11-04 | 2014-08-27 | 无锡金帆钻凿设备股份有限公司 | Novel noise image fusion method based on CS-CT-CHMM |
| CN103985104A (en) * | 2014-02-20 | 2014-08-13 | 江南大学 | Multi-focusing image fusion method based on higher-order singular value decomposition and fuzzy inference |
| CN104268833A (en) * | 2014-09-15 | 2015-01-07 | 江南大学 | New image fusion method based on shift invariance shearlet transformation |
| CN105894483A (en) * | 2016-03-30 | 2016-08-24 | 昆明理工大学 | Multi-focusing image fusion method based on multi-dimensional image analysis and block consistency verification |
| CN106897987A (en) * | 2017-01-18 | 2017-06-27 | 江南大学 | Image interfusion method based on translation invariant shearing wave and stack own coding |
Non-Patent Citations (5)
| Title |
|---|
| LI LI LÜ ET AL: "Multi-focus image fusion based on shearlet and local energy", 《2010 2ND INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING SYSTEMS》 * |
| 潘泉波: "压缩感知技术在图像融合中的应用研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 王莉: "基于Contourlet变换和区域能量区域方差的图像融合方法", 《计算机时代》 * |
| 苗启广: "《多传感器图像融合技术及应用》", 30 April 2014, 《西安电子科技大学出版社》 * |
| 苗启广等: "基于shearlets的多聚焦图像融合新算法", 《光学学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950714A (en) * | 2020-08-24 | 2020-11-17 | 重庆市云迈科技有限公司 | Energy spectrum CT image domain material identification method based on 3D full convolution neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104809734B (en) | A method of the infrared image based on guiding filtering and visual image fusion | |
| Chai et al. | Image fusion using quaternion wavelet transform and multiple features | |
| Yang et al. | Multimodality medical image fusion based on multiscale geometric analysis of contourlet transform | |
| Xiao-Hui et al. | Fusion algorithm for remote sensing images based on nonsubsampled contourlet transform | |
| CN109242888B (en) | Infrared and visible light image fusion method combining image significance and non-subsampled contourlet transformation | |
| Choi et al. | Fusion of multispectral and panchromatic satellite images using the curvelet transform | |
| Yang et al. | Image fusion using nonsubsampled contourlet transform | |
| Wang et al. | The application of wavelet transform to multi-modality medical image fusion | |
| Shah et al. | Multifocus and multispectral image fusion based on pixel significance using multiresolution decomposition | |
| Yang | Multimodal medical image fusion through a new DWT based technique | |
| CN102800070B (en) | Multi-modality image fusion method based on region and human eye contrast sensitivity characteristic | |
| CN107657217A (en) | The fusion method of infrared and visible light video based on moving object detection | |
| CN109447909A (en) | The infrared and visible light image fusion method and system of view-based access control model conspicuousness | |
| CN108447059A (en) | It is a kind of to refer to light field image quality evaluating method entirely | |
| Liu et al. | Research on fusion technology based on low-light visible image and infrared image | |
| Patel et al. | A review on infrared and visible image fusion techniques | |
| CN110633759A (en) | Image fusion method and device and electronic equipment | |
| CN109685752A (en) | A kind of multiple dimensioned Shearlet area image method for amalgamation processing decomposed based on block | |
| Kannan et al. | Optimal decomposition level of discrete wavelet transform for pixel based fusion of multi-focused images | |
| Zhang | A selection of image processing techniques: from fundamentals to research front | |
| Tawade et al. | Image fusion based on wavelet transforms | |
| Lan et al. | Multimodal medical image fusion using wavelet transform and human vision system | |
| Jain et al. | Multimodal image fusion employing discrete cosine transform | |
| Al-Azzawi et al. | An efficient medical image fusion method using contourlet transform based on PCM | |
| CN105005976B (en) | A kind of infrared image enhancing method based on fusion |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190426 |