CN106408539A - Augmented reality image reproduction method based on fuzzy logic - Google Patents
Augmented reality image reproduction method based on fuzzy logic Download PDFInfo
- Publication number
- CN106408539A CN106408539A CN201610852659.9A CN201610852659A CN106408539A CN 106408539 A CN106408539 A CN 106408539A CN 201610852659 A CN201610852659 A CN 201610852659A CN 106408539 A CN106408539 A CN 106408539A
- Authority
- CN
- China
- Prior art keywords
- image
- fuzzy
- coefficient
- augmented reality
- domain
- 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 49
- 230000003190 augmentative effect Effects 0.000 title claims abstract description 15
- 239000011159 matrix material Substances 0.000 claims abstract description 20
- 230000009466 transformation Effects 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000000354 decomposition reaction Methods 0.000 abstract description 2
- 238000013507 mapping Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 7
- 230000002708 enhancing effect Effects 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 3
- 230000036039 immunity Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000000686 essence Substances 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/006—Mixed reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration using non-spatial domain filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
-
- 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
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an augmented reality image reproduction method based on fuzzy logic, which relates to the technical field of augmented reality. The augmented reality image reproduction method comprises the steps of carrying out dual-tree complex wavelet decomposition on a reproduced image after denoising treatment firstly, so as to obtain a low-high-frequency coefficient matrix, performing fuzzy processing on low-frequency and low-frequency and high-frequency coefficients, namely, processing the coefficient matrix by utilizing a generalized fuzzy operator (GFO), mapping the coefficients into an ordinary fuzzy set, wherein some parameters therein are obtained through self-adaption, and performing inverse transformation on the processed coefficient matrix to obtain an augmented image. By adopting the augmented reality image reproduction method based on fuzzy logic, the objective image definition of the reproduced image can be increased, the noise can be reduced, and the edge details are expressed more obviously.
Description
Technical field
The present invention relates to augmented reality field, especially a kind of augmented reality image reproducing side based on fuzzy logic
Method.
Background technology
Nineteen sixty-five famous cybernetist L.A.Zade proposes fuzzy mathematics, is had not true with strict mathematical method solution
The qualitative problem with ambiguity.In the last few years, fuzzy theory was widely used in a lot of fields, in image processing field
Application and research obtained the very big concern of scholars.Enhancing substance with regard to fuzzy logic is by membership function
Spatial domain picture is transformed to fuzzy field, that is, on Fuzzy property domain, then by fuzzy stretching enhancing function processing coefficient, finally right
It is blurred the coefficient inverse transformation processing to make the return trip empty domain, thus obtaining image enhanced through fuzzy logic.
Image enhaucament can be divided into two classes by action scope:Spatial domain and transform domain method.Traditional Space domain is main
Including histogram equalization, greyscale transformation, unsharp masking etc.;And the transform domain method of early stage is mainly being fourier transformed
Carry out in frequency domain afterwards.However, these traditional methods especially Space domain, or because gray level merges figure easy to lose
As detailed information, the image enhancement effects for low-light level and low contrast are poor;Or while strengthening picture contrast
Also enhanced effect is served to noise, and not good enough in the performance of details effect.The wavelet transformed domain Enhancement Method subsequently proposing,
Because the multiple dimensioned characteristic of small echo is so that enhanced image has very big improvement in noise suppressed, details expression, once became
Focus for image enhaucament research.Dual-tree complex wavelet transform is a kind of improvement on wavelet transform base, and wavelet transformation lacks
Translation invariance and set direction, thus when being processed to image using wavelet transformation, can lose to a certain extent
Image information.
Content of the invention
A kind of augmented reality imaging reconstruction method based on fuzzy logic proposed by the present invention, enables to reproduction image image
Definition increases, and noise reduces, and edge details performance becomes apparent from.
The technical scheme is that and be achieved in that:
The method comprises the following steps:
Step 1:Read in augmented reality reproduction image image;
Step 2:First holographic reconstructed image is done with two-layer dual-tree complex wavelet transform, can get 1 low frequency component of reproduction image
With 12 high fdrequency components;
Step 3:The low frequency decomposing out and high frequency coefficient Matrix Calculating are obtained with the maximum x of coefficient in matrixmax, xmin, to ψ
One initial value, ψ=(xmax-xmin)/m, m=100;
Step 4:Application formula is by coefficient domain I={ xmnTransform to generalized fuzzy domain μ={ μmn, and by for wide
The definition of adopted fuzzy operator GFO acts on generalized fuzzy domain, the common fuzzy field μ '={ μ ' after being processedmn};
Step 5:T after application enhancementsIX the inverse transformation of (), calculates enhanced coefficient I '={ x 'mn, more logical ask be
In matrix number, the gradient of each coefficient, obtains Q;
Step 6:Make ψ=(x againmax-xmin)/m, m=m-1, substitutes into step 3 and is calculated;
Step 7:After iterative cycles finish, obtain working as m=m ', Q is maximum, then ψ=(xmax-xmin)/m ', selects this ψ value to increase
Low high frequency coefficient matrix by force;
Step 8:High and low frequency coefficient matrix after Fuzzy Processing is done with dual-tree complex wavelet inverse transformation, returns to spatial domain
Just can get enhanced image.
The present invention passes through a kind of augmented reality imaging reconstruction method based on fuzzy logic providing, and its advantage exists
In:First dual-tree complex wavelet decomposition is carried out to the reproduction image through denoising, low high frequency coefficient matrix can be obtained;Then divide
Other Fuzzy Processing is carried out to low frequency and high frequency coefficient, using Generalized Fuzzy Operator, coefficient matrix is processed, is re-mapped
In common fuzzy set, some parameters therein are obtained by self adaptation, then carry out inverse transformation to the coefficient matrix processing and obtain
Enhanced image, this method enables to reproduction image image definition to be increased, and noise reduces, and edge details performance is brighter
Aobvious.
Brief description
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
Have technology description in required use accompanying drawing be briefly described it should be apparent that, drawings in the following description be only this
Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, also may be used
So that other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 compares 1 for 4 kinds of reinforced effects of reproduction image;
Fig. 2 compares 2 for 4 kinds of reinforced effects of reproduction image.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation description is it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of not making creative work
Embodiment, broadly falls into the scope of protection of the invention.
A kind of being comprised the following steps based on the augmented reality imaging reconstruction method of fuzzy logic of present invention offer:
Step 1:Read in augmented reality reproduction image image;
Step 2:First holographic reconstructed image is done with two-layer dual-tree complex wavelet transform, can get 1 low frequency component of reproduction image
With 12 high fdrequency components;
Step 3:The low frequency decomposing out and high frequency coefficient Matrix Calculating are obtained with the maximum x of coefficient in matrixmax, xmin, to ψ
One initial value, ψ=(xmax-xmin)/m, m=100;
Step 4:Application formula is by coefficient domain I={ xmnTransform to generalized fuzzy domain μ={ μmn, and by for wide
The definition of adopted fuzzy operator GFO acts on generalized fuzzy domain, the common fuzzy field μ '={ μ ' after being processedmn};
Step 5:T after application enhancementsIX the inverse transformation of (), calculates enhanced coefficient I '={ x 'mn, more logical ask be
In matrix number, the gradient of each coefficient, obtains Q;
Step 6:Make ψ=(x againmax-xmin)/m, m=m-1, substitutes into step 3 and is calculated;
Step 7:After iterative cycles finish, obtain working as m=m ', Q is maximum, then ψ=(xmax-xmin)/m ', selects this ψ value to increase
Low high frequency coefficient matrix by force;
Step 8:High and low frequency coefficient matrix after Fuzzy Processing is done with dual-tree complex wavelet inverse transformation, returns to spatial domain
Just can get enhanced image.
Carry out Enhancement test using method set forth above, and with histogram equalizing method, fuzzy contrast Enhancement Method,
3 kinds of Enhancement Method such as wavelet field image enchancing method compare, the method for selection or related to fuzzy set theory, or and chi
Degree is related.The experimental result of the present embodiment is in Core i3 processor, leaves and record in 2G.Because length limits, now with wherein 2
Width is illustrated as a example having the experimental result of reproduction image of making an uproar.Two width image backgrounds are partially dark, contrast is low, details is not clear and contains
There is noise.For 2 width images, the enhancing result using above-mentioned 3 kinds of methods is distinguished as shown in Figure 1, 2.Wherein, (a) is original graph
Picture, (b) is plus image after making an uproar, and (c) is histogram equalizing method, and (d) is fuzzy contrast Enhancement Method, and (e) is wavelet field mould
Paste Enhancement Method strengthens result;F () is then the image enhaucament result of this chapter method.Carefully compare the enhancing obtained by said method
Image afterwards, finds that the overall reinforced effects of this method are better than other 3 kinds of Enhancement Method.As can be seen from Figure 1:Histogram equalization side
Although method improves picture contrast in enhancing image, the enhancing for noise is it is also obvious that and clearly enhance
The zero-order image not being completely eliminated and conjugate image, visual effect obscures, and noise immunity is poor;Fuzzy contrast Enhancement Method contrast is drawn
Stretch not as good as wavelet field Method of Fuzzy Enhancement, image is not clear, and edge performance is poor;Wavelet field Method of Fuzzy Enhancement has certain
Noise immunity, but details performance is poor, the method especially proposing not as this chapter in edge performance.In general the base that the application proposes
Reproduction image Enhancement Method in dual-tree complex wavelet and fuzzy logic can improve the visual effect of reproduction image well, by material picture
Stretching substantially, suppresses substantially, more preferably to present the details after image reduction, and suppress noise for zero-order image and conjugate image.Fig. 2
Eliminate the interference of zero-order image and conjugate image, enhancement process is carried out to the reproduction image image of certain historical relic:Find this method than right
The raising that the method energy of ratio is apparent reproduces image contrast, image clearly.Can be seen that this method from Fig. 1 and Fig. 2 to different
It is all effective for reproducing image intensifying, compared with existing several method, for image as matter has more preferable visual effect, in suppression
While noise, remain the detailed information of image, improve contrast.
Table 1 have rated the denoising effect of reproduction image from the angle of objective quantitative, gives comentropy, average gradient and peak value
Signal to noise ratio.As can be seen from the table, although histogram equalization method comentropy and average gradient value are higher, substantially anti-
Answer far away from other 3 kinds of methods in the value of signal to noise ratio of denoising, although improved anti-based on the fuzzy contrast method in spatial domain
Making an uproar property, but its definition not as good as other methods, wavelet field Method of Fuzzy Enhancement relatively above two methods have certain improvement, but
Still not as good as this method.
Table 1 is made an uproar and is reproduced image intensifying index
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all essences in the present invention
Within god and principle, any modification, equivalent substitution and improvement made etc., should be included within the scope of the present invention.
Claims (1)
1. a kind of bore hole 3D reproduces image speckle suppressing method it is characterised in that the method comprises the following steps:
Step 1:Read in augmented reality reproduction image image;
Step 2:First holographic reconstructed image is done with two-layer dual-tree complex wavelet transform, can get 1 low frequency component and 12 of reproduction image
Individual high fdrequency components;
Step 3:The low frequency decomposing out and high frequency coefficient Matrix Calculating are obtained with the maximum x of coefficient in matrixmax, xmin, to ψ mono-
Initial value, ψ=(xmax-xmin)/m, m=100;
Step 4:Application formula is by coefficient domain I={ xmnTransform to generalized fuzzy domain μ={ μmn, and by for generalized fuzzy
The definition of operator GFO acts on generalized fuzzy domain, the common fuzzy field μ '={ μ ' after being processedmn};
Step 5:T after application enhancementsIX the inverse transformation of (), calculates enhanced coefficient I '={ x 'mn, the more logical coefficient square asked
In battle array, the gradient of each coefficient, obtains Q;
Step 6:Make ψ=(x againmax-xmin)/m, m=m-1, substitutes into step 3 and is calculated;
Step 7:After iterative cycles finish, obtain working as m=m ', Q is maximum, then ψ=(xmax-xmin)/m ', selects this ψ value to strengthen low
High frequency coefficient matrix;
Step 8:High and low frequency coefficient matrix after Fuzzy Processing is done with dual-tree complex wavelet inverse transformation, returns to spatial domain and just may be used
Obtain enhanced image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610852659.9A CN106408539A (en) | 2016-09-26 | 2016-09-26 | Augmented reality image reproduction method based on fuzzy logic |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610852659.9A CN106408539A (en) | 2016-09-26 | 2016-09-26 | Augmented reality image reproduction method based on fuzzy logic |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106408539A true CN106408539A (en) | 2017-02-15 |
Family
ID=57998261
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610852659.9A Pending CN106408539A (en) | 2016-09-26 | 2016-09-26 | Augmented reality image reproduction method based on fuzzy logic |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106408539A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107784638A (en) * | 2017-10-27 | 2018-03-09 | 北京信息科技大学 | A kind of Dongba ancient books image enchancing method of optimization |
CN108364266A (en) * | 2018-02-09 | 2018-08-03 | 重庆大学 | The flow passage structure minimizing technology of cell holographic reconstruction observation is carried out using micro-fluidic chip |
-
2016
- 2016-09-26 CN CN201610852659.9A patent/CN106408539A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107784638A (en) * | 2017-10-27 | 2018-03-09 | 北京信息科技大学 | A kind of Dongba ancient books image enchancing method of optimization |
CN108364266A (en) * | 2018-02-09 | 2018-08-03 | 重庆大学 | The flow passage structure minimizing technology of cell holographic reconstruction observation is carried out using micro-fluidic chip |
CN108364266B (en) * | 2018-02-09 | 2021-11-30 | 重庆大学 | Flow path structure removing method for cell holographic reconstruction observation by using microfluidic chip |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liu et al. | Efficient single image dehazing and denoising: An efficient multi-scale correlated wavelet approach | |
Zhang et al. | Fast depth image denoising and enhancement using a deep convolutional network | |
CN116051428B (en) | Deep learning-based combined denoising and superdivision low-illumination image enhancement method | |
Wen et al. | Medical X-ray image enhancement based on wavelet domain homomorphic filtering and CLAHE | |
CN113724164B (en) | Visible light image noise removing method based on fusion reconstruction guidance filtering | |
Kumar et al. | Image Denoising by Wavelet Based Thresholding Method | |
Magudeeswaran et al. | Brightness preserving bi‐level fuzzy histogram equalization for MRI brain image contrast enhancement | |
Shedbalkar et al. | A comparative analysis of filters for noise reduction and smoothening of brain MRI images | |
Dileep et al. | A comparison between different colour image contrast enhancement algorithms | |
Josephus et al. | Multilayered contrast limited adaptive histogram equalization using frost filter | |
Hayat et al. | Detailed and enhanced multi-exposure image fusion using recursive filter | |
CN106408539A (en) | Augmented reality image reproduction method based on fuzzy logic | |
Wang et al. | Retinex algorithm on changing scales for haze removal with depth map | |
Yang et al. | Speckle reduction and structure enhancement by multichannel median boosted anisotropic diffusion | |
Jagatheeswari et al. | A novel approach for contrast enhancement based on histogram equalization followed by median filter | |
Chawla et al. | Hybrid filtering technique for image denoising using artificial neural network | |
Tun et al. | Joint Training of Noisy Image Patch and Impulse Response of Low-Pass Filter in CNN for Image Denoising | |
Batna | Comparative study between wavelet thresholding techniques (hard, soft and invariant-translation) in ultrasound images | |
Laftah | Image Denoising Using Multiwavelet Transform with Different Filters and Rules. | |
Hanumantharaju et al. | Natural color image enhancement based on modified multiscale retinex algorithm and performance evaluation using wavelet energy | |
Thayammal et al. | Performance analysis of image denoising using deep convolutional neural network | |
Parihar et al. | A hybrid approach for image denoising using explicit guided filter and collaborative wiener filter | |
Sari et al. | Development of denoising method for digital image in low-light condition | |
CN112465719A (en) | Transform domain image denoising method and system | |
Liu | New method for image denoising while keeping edge information |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
CB02 | Change of applicant information |
Address after: 100041 Beijing, Shijingshan District Xing Xing street, building 30, No. 3, building 2, C-0058 Applicant after: Beijing micro cloud Software Co., Ltd. Address before: 100041 Beijing, Shijingshan District Xing Xing street, building 30, No. 3, building 2, C-0058 Applicant before: Micro light capital investment management (Beijing) Co., Ltd. |
|
CB02 | Change of applicant information | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170215 |
|
WD01 | Invention patent application deemed withdrawn after publication |