CN105654496B - The bionical adaptive fuzzy edge detection method of view-based access control model characteristic - Google Patents
The bionical adaptive fuzzy edge detection method of view-based access control model characteristic Download PDFInfo
- Publication number
- CN105654496B CN105654496B CN201610010368.5A CN201610010368A CN105654496B CN 105654496 B CN105654496 B CN 105654496B CN 201610010368 A CN201610010368 A CN 201610010368A CN 105654496 B CN105654496 B CN 105654496B
- Authority
- CN
- China
- Prior art keywords
- image
- brightness
- fuzzy
- edge
- local
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000003708 edge detection Methods 0.000 title claims abstract description 31
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 21
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 40
- 238000000605 extraction Methods 0.000 claims abstract description 25
- 230000006870 function Effects 0.000 claims abstract description 22
- 230000000007 visual effect Effects 0.000 claims abstract description 13
- 230000009466 transformation Effects 0.000 claims abstract description 12
- 230000016776 visual perception Effects 0.000 claims abstract description 6
- 230000002708 enhancing effect Effects 0.000 claims description 24
- 230000000694 effects Effects 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 14
- 230000004438 eyesight Effects 0.000 claims description 14
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 230000005764 inhibitory process Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 210000001116 retinal neuron Anatomy 0.000 claims description 7
- 230000000747 cardiac effect Effects 0.000 claims description 6
- 230000002964 excitative effect Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000035807 sensation Effects 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000002146 bilateral effect Effects 0.000 claims description 3
- 230000023886 lateral inhibition Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 claims 1
- 230000001629 suppression Effects 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 12
- 238000013461 design Methods 0.000 description 8
- 241000209094 Oryza Species 0.000 description 6
- 235000007164 Oryza sativa Nutrition 0.000 description 6
- 238000002474 experimental method Methods 0.000 description 6
- 235000009566 rice Nutrition 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 206010016322 Feeling abnormal Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000003278 mimic effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 235000001968 nicotinic acid Nutrition 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000007704 transition Effects 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
- G06T5/73—Deblurring; Sharpening
-
- 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
- G06T2207/20004—Adaptive image processing
- G06T2207/20008—Globally adaptive
-
- 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
- G06T2207/20004—Adaptive image processing
- G06T2207/20012—Locally adaptive
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of bionical adaptive fuzzy edge detection methods of image based on human visual system, belong to digital image processing techniques field.The present invention is realized using following steps：Carrying out global brightness to operation image adaptively enhances, original image transform of spatial domain is turned into fuzzy field, carrying out local luminance to operation image fuzzy field adaptively enhances, and inverse transformation is carried out to original image fuzzy field, finally using " Nakagowa " operator to treated Edge extraction.The present invention optimizes traditional Pal algorithms Blurring edge detector the low gray value boundary information for remaining image according to the global and local Adaptive of human eye visual perception system, simplify membership function, with stronger anti-noise ability, effectively edge from complicated background can be extracted, edge detection can be adaptively carried out for different types of image.
Description
Technical field：
The present invention relates to a kind of bionical adaptive fuzzy edge detection methods of image based on human visual system, belong to
Digital image processing techniques field.
Technical background：
Bionics is the science that mankind's mimic biology function carrys out innovation and creation, be using biology structure and function principle come
Develop machinery or a subject of various new technologies.Human visual system has brightness adaptive characteristic and retinal neurons sense
By wild non-classical lateral inhibition characteristic, imitative human visual system's thought is applied to image procossing, is by more and more researchers
In terms of system identification and machine vision.
Edge detection is one of most important research contents in image procossing, is to carry out iamge description, analysis and understanding
Key technology.Nineteen fifty-nine Julez is put forward for the first time edge detection concept, later both at home and abroad a large amount of experts and scholars to edge detection this
Subject has carried out research extensively and profoundly and has proposed many methods, common edge detection method have calculus of finite differences, Robert,
The methods of Sobel, Prewitt, Log, Canny, but these methods mainly enhance the high-frequency informations such as the edge of image, effectively carry
Image border is taken, but more sensitive to noise, effect is unsatisfactory in real image is handled.Pal and King are fuzzy
Concept is introduced into the field of image procossing, proposes the image partition method based on Fuzzy Set Theory, which can play
Preferably press down hot-tempered effect, preferable image segmentation can be obtained, but pass through theoretical and experimental analysis：Pal and King is calculated
Method does not carry out denoising early period, unsatisfactory for noisy image effect, be easy to cause erroneous judgement；Power series form is subordinate to
Degree function is mapped to the effect of fuzzy set only up to image, almost without the effect of some enhanced fuzzies；Image is by non-
Low gray value can become 0 in image after linear transformation, cause the loss of marginal information, influence final effect；Iterations, segmentation
The selection of threshold values has a significant impact to the enhanced fuzzy processing of image, and existing on fuzzy area image inverse transformation influences.
Based on background above, the present invention is using traditional Pal and King Fuzzy Edge-detection Algorithms as frame, with human vision system
The global enhancing characteristic of system and local Adaptive are theoretical foundation, it is proposed that a kind of view-based access control model characteristic it is bionical from
Fuzzy edge detection method is adapted to, and is applied the method in real image edge extracting, the brightness overall situation is carried out to image certainly
It adapts to and local enhancement processing, the contrast on border and raising that can enhance image well being filtered out by traditional receptive field
Regional luminance comparison and half tone information, remain low gray-scale edges information, enhanced picture quality meets human eye
Subjective vision effect, the patent of invention of relevant patent such as 103310461 A of application publication number CN disclose one kind based on block
The image edge extraction method of Kalman filter, is respectively adopted layered shaping and interpolation arithmetic effectively increases filter effect and behaviour
Make the signal-to-noise ratio of object, improve the quality of Image Edge-Detection.The patent of invention of 104809733 A of application publication number CN is public
A kind of ancient architecture wall has been opened to get dirty topic note character image edge extracting method, using gabor wave filters to space average, identification and
Pseudo-edge and discontinuous edge caused by eliminating pollution.The patent of invention of 101286233 A of application publication number CN discloses one kind
Fuzzy edge detection method based on object cloud adaptively carries out the processing of edge transition area using principle of maximum entropy, makes up and be based on
The defects of fuzzy set theory algorithm.The patent of invention of 104268872 A of application publication number CN discloses a kind of based on consistency
Edge detection method introduces shade of gray direction, and shade of gray changes caused by distinguishing true edge, noise.More than but specially
Profit does not relate to the Edge extraction based on human visual system.
Invention content：
Smaller for picture contrast, the ineffective problem of edge detection, the present invention is with traditional Pal and King fuzzy edges
Detection algorithm is frame, using the global enhancing characteristic and local Adaptive of human visual system as theoretical foundation, is carried
Gone out a kind of bionical adaptive fuzzy edge detection method of view-based access control model characteristic, according to human eye visual perception system the overall situation and
Local auto-adaptive control characteristic optimizes traditional Pal and King algorithms Blurring edge detector.
This optimization algorithm remains important marginal information in Image Edge-Detection, detects with the subjective vision of people more
For consistent image border, the adaptivity and practicability of Blurring edge detector are improved.
The present invention adopts the following technical scheme that：
A kind of bionical adaptive fuzzy edge detection method of view-based access control model characteristic, step are：
Step 1, carrying out global brightness to operation image adaptively enhances, using the overall situation based on human visual system's characteristic
Adaptivity logarithmic model carries out nonlinear adjustment, to image darker or lighter to bright-dark degree's overall brightness of original image
Part is adjusted, and makes the light and shade region contrast of image enhance；
Step 2, original image transform of spatial domain is turned into fuzzy field, it is original defines a simple and effective membership function substitution
Membership function, improve fuzzy edge extraction algorithm real-time；Property and definition using SIN function, it is effective to realize
The conversion of fuzzy field avoids most low gray value in image and is set as 0 by hardness, saves the low gray-scale edges of image
Information；
Step 3, carrying out local luminance to operation image fuzzy field adaptively enhances, non-using retinal neurons receptive field
The bilateral filtering calculating field subjective sensation brightness that three Gauss models and gaussian filtering of classical lateral inhibition are combined, foundation are worked as
Linear relationship enhancing image local detailed information between preceding brightness and subjective sensation brightness；
Step 4, inverse transformation is carried out to original image fuzzy field, fuzzy membership matrix is converted into spatial domain figure by inversion function
Picture；
Step 5, Edge extraction, using " Nakagowa " operator to treated Edge extraction.
Compared with existing technique of image edge detection, the advantage of the invention is that：The overall situation according to human eye visual perception system
The low gray value boundary for remaining image is optimized to traditional Pal algorithms Blurring edge detector with local Adaptive
Information simplifies membership function, has stronger anti-noise ability, and effectively edge can be extracted from complicated background
Come, edge detection can be adaptively carried out for different types of image.
The present invention preferred embodiment be：
According to the global enhancing characteristic of human eye visual perception system, the step 1 image overall brightness enhances calculation formula
For：
In formula：For original imagePixel value at position,It is enhanced by global brightness
Normalize brightness,、、It is the degree that global logarithm adjustment is confirmed according to the brightness of image itself；Human eye vision
System is according to the overall brightness situation of target, the initial stage adaptively global brightness for enhancing image, by parameterizing logarithmic model
Adaptively global enhancing brightness of image, the Nonlinear Adjustment effectively have compressed the dynamic range of image, make the dark space of image
Domain brightens.
In step 2, image membership function is determined：Define a simple and effective membership function, Pal and King algorithms
The element in the fuzzy set for obtaining imageRepresent pixelDegree of membership；Calculation formula is：
In formula,Represent image pixelGray value,、Represent maximum, minimum in image respectively
Gray level；Property and definition by SIN function know that it is subordinate to the degree of membership letter that the codomain linearity is better than Pal and King algorithms
Number, the low gray value avoided in image are set as 0 by hardness, save the low gray-scale edges information of image.
According to human vision local auto-adaptive control characteristic, the step 3 image local brightness enhancing calculation formula is：
In formula：It is the proportionality coefficient of local linear relationship for a positive constant；It is the image after blurring mapping
Value,It is current pointThe neighborhood averaging brightness at place, it reflects the brightness that current point position human eye is experienced
Situation；Domain core is depended on for weight coefficientWith codomain coreProduct, the value of output pixel depends on field pixel
The weighted array of value；Learn that human eye is more sensitive for local contrast by human visual system's characteristic, vision system is to letter
Number carry out final process when, have Flanker task effect, human eye can be made to have the feeling of enhancing to the edge of image.
In step 4, inverse transformation is carried out to fuzzy set：Inverse transformation is carried out to local enhancement image, by fuzzy membership matrix
It is converted into space area image；Calculation formula is：
According to human vision local auto-adaptive control characteristic, three Gaussian modes of the step 3 retinal neurons receptive field
Type calculation formula is：
In formula,Represent the excited reaction size at any point in receptive field,Cardiac excitatory area, four in representing respectively
Disinthibite the susceptibility peak value in area on a large scale for all inhibition zones, periphery,Cardiac excitatory area, inhibition zone, the big model in periphery in representing respectively
Enclose the area coefficient in area of disinthibiting.
Step 5, Edge extraction：The minimal operator proposed using Nakagowa defines the edge of image, calculates public
Formula is：
In formula：Represent treated image,,Represent 3 × 3 window.
Description of the drawings
Fig. 1 is method flow diagram according to the present invention.
Fig. 2 is the logarithmic relationship of human eye brightness and luminous intensity.
Fig. 3 is three Gauss models of receptive field.
Fig. 4 is " rice " image.
Fig. 5 is to " rice " Edge extraction design sketch using Canny operators.
Fig. 6 is utilizes Pal and King algorithms（n=2）To " rice " Edge extraction design sketch.
Fig. 7 is to " rice " Edge extraction design sketch using inventive algorithm.
Fig. 8 is " cameraman " image.
Fig. 9 is to " cameraman " Edge extraction design sketch using Canny operators.
Figure 10 is utilizes Pal and King algorithms（n=2）To " cameraman " Edge extraction design sketch.
Figure 11 is to " cameraman " Edge extraction design sketch using inventive algorithm.
Specific embodiment：
The invention will be further described with reference to the accompanying drawings and detailed description.
The present invention is carried out according to the step flow of Fig. 1：
Step 1：
Carrying out global brightness to operation image adaptively enhances, adaptive using the overall situation based on human visual system's characteristic
Property logarithmic model, nonlinear adjustment is carried out to the bright-dark degree overall brightness of original image, to image darker or lighter part into
Row is adjusted, and makes the light and shade region contrast of image enhance, in order to eye-observation.
According to the global enhancing characteristic of human eye visual perception system, image overall brightness enhancing calculation formula is：
In formula：For original imagePixel value at position,It is enhanced by global brightness
Normalize brightness,、、It is the degree that global logarithm adjustment is confirmed according to the brightness of image itself；Human eye vision
System is according to the overall brightness situation of target, and the brightness of initial stage adaptively global enhancing image is excessively bright to avoid image enhancement
Useful luminance information is then lost in subsequent step, adaptively global enhancing image is bright by parameterizing logarithmic model
Degree, then the characteristic of logarithmic function make the dark areas of image it is found that the Nonlinear Adjustment effectively has compressed the dynamic range of image
It brightens.
Step 2：
Original image transform of spatial domain is turned into fuzzy field, a simple and effective membership function is defined and replaces original be subordinate to
Function is spent, improves the real-time of fuzzy edge extraction algorithm；Property and definition using SIN function, effectively realize fuzzy field
Conversion, avoid most low gray value in image and be set as 0 by hardness, save the low gray-scale edges information of image.
Determine image membership function：A simple and effective membership function is defined, Pal and King algorithms are obtaining figure
Element in the fuzzy set of pictureRepresent pixelDegree of membership；Calculation formula is：
In formula,Represent image pixelGray value,、Represent maximum, minimum in image respectively
Gray level；Property and definition by SIN function know that it is subordinate to the degree of membership letter that the codomain linearity is better than Pal and King algorithms
Number, the low gray value avoided in image are set as 0 by hardness, save the low gray-scale edges information of image.
Step 3：
Carrying out local luminance to operation image fuzzy field adaptively enhances, using the non-classical side of retinal neurons receptive field
The bilateral filtering calculating field subjective sensation brightness that three Gauss models and gaussian filtering of inhibition are combined, foundation are currently lighted
Linear relationship enhancing image local detailed information between degree and subjective sensation brightness.
According to human vision local auto-adaptive control characteristic, image local brightness enhancing calculation formula is：
In formula：It is the proportionality coefficient of local linear relationship for a positive constant；It is the image after blurring mapping
Value,It is current pointThe neighborhood averaging brightness at place, it reflects the brightness that current point position human eye is experienced
Situation；Domain core is depended on for weight coefficientWith codomain coreProduct, the value of output pixel depends on field pixel
The weighted array of value；Learn that human eye is more sensitive for local contrast by human visual system's characteristic, vision system is to letter
When number carrying out final process, similar to a kind of calculating process summed by weight is carried out, with the band logical in signal processing
Filtering process is more similar, has the effect of Flanker task, human eye can be made to have the feeling of enhancing to the edge of image.
Three Gauss model calculation formula of retinal neurons receptive field are：
Medical research shows also there is a large-scale region in place of traditional cell receptive field concentric circles, right
Region stimulation can play modulating action to the response at receptive field center.In formula,Represent any point in receptive field
Excitement reaction size,Cardiac excitatory area in representing respectively, surrounding inhibition zone, periphery disinthibite the susceptibility peak value in area on a large scale,Disinthibite the area coefficient in area on a large scale for cardiac excitatory area, inhibition zone, periphery in representing respectively.
Step 4：
Inverse transformation is carried out to original image fuzzy field, fuzzy membership matrix is converted into space area image by inversion function；It is right
Fuzzy set carries out inverse transformation：Inverse transformation is carried out to local enhancement image, fuzzy membership matrix is converted into space area image；Meter
Calculating formula is：
Step 5：
Edge extraction, using " Nakagowa " operator to treated Edge extraction.The edge of image is defined,
Calculation formula is：
In formula：Represent treated image,,Represent 3 × 3 window.
Table 1 is that design method of the present invention is compared with Pal and King method edge extracting processing times：
1 fuzzy algorithmic approach edge extracting processing time of table
| Pal and King (n=1) | Pal and King (n=2) | Inventive algorithm | |
| rice | 1.264000s | 1.404000s | 0.677000s |
| cameraman | 1.457000s | 1.629000s | 0.826000s |
The example that Edge extraction is carried out using the present invention is given below.The basic demand of Image Edge-Detection is：Just
Really detect edge, edge, continuous edge and unilateral response is accurately positioned out.But these requirements commenting there is no accurate authority
Valency method, present most commonly used evaluation method are exactly subjective judgement, but the experience of evaluation result person easily evaluated, image type
Influence, it is impossible to strong illustrates edge detection effect, and the present invention is carried out using without reference to reference edge image evaluation method
Evaluation.
Embodiment 1：
Inventive algorithm tests " rice " edge extracting Contrast on effect with classics Canny operators, Pal and King algorithms,
Canny operators are one of current main edge detection methods, utilize single order local derviation finite difference formulations gradient magnitude and side
To, have extraordinary detection result, it is very extensive in Practical Project and practical application.Selected Canny operators and fuzzy extraction
Algorithm is contrast experiment, and Fig. 4 has selected first original graph, handling result indexNumerical value is respectively 0.834,0.756,
0.813.Experiment effect and subjective effect explanation, Fuzzy Edge-detection Algorithm is applicable not only to soft image, while also fits
For general image.But as can be seen clearly from figure 6 although edge effectively extracts, and there is many abnormal bright spots, warp
Analyzing to obscure to enhance for traditional Pal and King algorithms causes.
Embodiment 2：
Inventive algorithm is with classics Canny operators, Pal and King algorithms to " cameraman " edge extracting Contrast on effect
Experiment, experiment effect find out that Canny is poor for the smaller Edge extraction effect of contrast, is partitioned into many redundancies,
Treatment effect is unsatisfactory.And tradition Pal and King algorithms have effectively filtered out some noises and pseudo-edge, but inhibit noise energy
Power is relatively low, and exists simultaneously and obscured enhancing phenomenon, and analysis is obtained because spatial domain is improper to fuzzy field conversion process parameter selection
Cause, handling result indexNumerical value is respectively 0.587,0.675,0.731.Experiment effect of the present invention can be seen that and relatively pass
System Pal and King algorithms, effectively inhibit high-frequency noise point, effectively have adjusted global brightness, enhanced picture quality symbol
The subjective vision effect of human eye is closed, while avoids image and crosses enhancing phenomenon, remains the original details of image, and processing procedure
Parameter need not be manually adjusted, is effectively improved the adaptive ability and practicability of algorithm.
Embodiment 3：
Design method of the present invention is compared with Pal and King algorithm edge extracting processing times, and embodiment 1 and embodiment 2 are adopted
The iterations of Pal and King algorithms selections are 2, if selection iterations are 1, edge extracting image occurs a large amount of superfluous
Remaining information and more abnormal bright spot, therefore do not list experiment effect.
Embodiment 3 is by using inventive algorithm and traditional fuzzy algorithm（The iteration of the present invention is respectively 1, traditional fuzzy
When algorithm is 2）The Edge extraction time is calculated, verifies the real-time of inventive algorithm.Two images should as can be seen from Table 1
It is 0.677s and 0.826s respectively with the edge detection process time of the present invention, more traditional Pal and King algorithms reduce 46% respectively
With 43% processing time, the effectively less processing time of fuzzy edge extraction algorithm improves the real-time of algorithm.
Claims (6)
1. a kind of bionical adaptive fuzzy edge detection method of view-based access control model characteristic, step are：
Step 1, carrying out global brightness to operation image adaptively enhances, adaptive using the overall situation based on human visual system's characteristic
Answering property logarithmic model carries out nonlinear adjustment, to image darker or lighter part to bright-dark degree's overall brightness of original image
It is adjusted, makes the light and shade region contrast of image enhance；
According to the global enhancing characteristic of human eye visual perception system, image overall brightness enhancing calculation formula is：
In formula：For original imagePixel value at position,It is by the enhanced normalizing of global brightness
Change brightness,、、It is the degree that global logarithm adjustment is confirmed according to the brightness of image itself；Human visual system's root
According to the overall brightness situation of target, the initial stage adaptively global brightness for enhancing image is adaptive by parameterizing logarithmic model
Ground overall situation enhancing brightness of image, the Nonlinear Adjustment effectively have compressed the dynamic range of image, the dark areas of image are made to brighten；
Step 2, original image transform of spatial domain is turned into fuzzy field, defines a simple and effective membership function and replace original person in servitude
Category degree function improves the real-time of fuzzy edge extraction algorithm；Property and definition using SIN function, effective realize obscure
The conversion in domain avoids most low gray value in image and is set as 0 by hardness, saves the low gray-scale edges letter of image
Breath；
Step 3, carrying out local luminance to operation image fuzzy field adaptively enhances, non-classical using retinal neurons receptive field
The bilateral filtering calculating field subjective sensation brightness that three Gauss models and gaussian filtering of lateral inhibition are combined, according to current point
Linear relationship enhancing image local detailed information between brightness and subjective sensation brightness；
Step 4, inverse transformation is carried out to original image fuzzy field, fuzzy membership matrix is converted into space area image by inversion function；
Step 5, Edge extraction, using " Nakagowa " operator to treated Edge extraction.
2. the bionical adaptive fuzzy edge detection method of view-based access control model characteristic according to claim 1, it is characterised in that：
In step 2, image membership function is determined：A simple and effective membership function is defined, Pal and King algorithms are obtaining figure
Element in the fuzzy set of pictureRepresent pixelDegree of membership；Calculation formula is：
In formula,Represent image pixelGray value,、Maximum, minimal gray in image is represented respectively
Grade；Property and definition by SIN function are known that it is subordinate to the membership function that the codomain linearity is better than Pal and King algorithms, are kept away
The low gray value exempted from image is set as 0 by hardness, saves the low gray-scale edges information of image.
3. the bionical adaptive fuzzy edge detection method of view-based access control model characteristic according to claim 1, which is characterized in that
According to human vision local auto-adaptive control characteristic, the step 3 image local brightness enhancing calculation formula is：
In formula：It is the proportionality coefficient of local linear relationship for a positive constant；It is the image value after blurring mapping,It is current pointThe neighborhood averaging brightness at place, it reflects the brightness case that current point position human eye is experienced；Domain core is depended on for weight coefficientWith codomain coreProduct, the value of output pixel dependent on field pixel value plus
Power combination；Learn that human eye is more sensitive for local contrast by human visual system's characteristic, vision system is carried out to signal
During final process, there is the effect of Flanker task, human eye can be made to have the feeling of enhancing to the edge of image.
4. the bionical adaptive fuzzy edge detection method of view-based access control model characteristic according to claim 1, which is characterized in that
In step 4, inverse transformation is carried out to fuzzy set：Inverse transformation is carried out to local enhancement image, fuzzy membership matrix is converted into sky
Between area image；Calculation formula is：
。
5. the bionical adaptive fuzzy edge detection method of the view-based access control model characteristic according to claims 1, feature exist
In：According to human vision local auto-adaptive control characteristic, three Gauss models of the step 3 retinal neurons receptive field calculate
Formula is：
In formula,Represent the excited reaction size at any point in receptive field,Cardiac excitatory area, surrounding suppression in representing respectively
Disinthibite the susceptibility peak value in area on a large scale for area processed, periphery,Cardiac excitatory area, inhibition zone, periphery are gone on a large scale in representing respectively
The area coefficient of inhibition zone.
6. the bionical adaptive fuzzy edge detection method of view-based access control model characteristic according to claim 1, it is characterised in that：
Step 5, Edge extraction：The minimal operator proposed using Nakagowa, defines the edge of image, and calculation formula is：
In formula：Represent treated image,,Represent 3 × 3 window.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610010368.5A CN105654496B (en) | 2016-01-08 | 2016-01-08 | The bionical adaptive fuzzy edge detection method of view-based access control model characteristic |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610010368.5A CN105654496B (en) | 2016-01-08 | 2016-01-08 | The bionical adaptive fuzzy edge detection method of view-based access control model characteristic |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105654496A CN105654496A (en) | 2016-06-08 |
| CN105654496B true CN105654496B (en) | 2018-06-29 |
Family
ID=56490600
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610010368.5A Expired - Fee Related CN105654496B (en) | 2016-01-08 | 2016-01-08 | The bionical adaptive fuzzy edge detection method of view-based access control model characteristic |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105654496B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106530245A (en) * | 2016-10-27 | 2017-03-22 | 长安大学 | Method for enhancing frequency band of infrared image of unmanned aerial vehicle-mounted tunnel fire hazard |
| CN108053415B (en) * | 2017-12-14 | 2020-05-22 | 广西科技大学 | Bionic contour detection method based on improved non-classical receptive field |
| CN107977945A (en) * | 2017-12-18 | 2018-05-01 | 深圳先进技术研究院 | A kind of image enchancing method, system and electronic equipment |
| CN108416788B (en) * | 2018-03-29 | 2020-06-05 | 河南科技大学 | Edge detection method based on receptive field and light and shade adaptability thereof |
| CN108830806B (en) * | 2018-05-29 | 2020-12-18 | 河南科技大学 | Sensitivity of receptive field model and dynamic regulation and control method of model parameters |
| CN108932702B (en) * | 2018-06-13 | 2020-10-09 | 北京微播视界科技有限公司 | Image processing method, image processing device, electronic equipment and computer readable storage medium |
| CN112396618B (en) * | 2020-11-12 | 2022-02-18 | 北京科技大学 | Grain boundary extraction and grain size measurement method based on image processing |
| CN113128511B (en) * | 2021-03-31 | 2023-07-25 | 武汉钢铁有限公司 | Coke tissue identification method and device |
| CN114861534B (en) * | 2022-04-24 | 2024-09-24 | 昆明理工大学 | Processing method, system, equipment and medium for visual cognitive response data |
| CN116153267B (en) * | 2022-12-30 | 2024-05-31 | 嘉兴美茵智能电子有限公司 | Backlight control method for multi-contact liquid crystal display |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1489115A (en) * | 2003-08-14 | 2004-04-14 | 中国人民解放军第一军医大学 | Image optimized segmentation method based on generalized fuzzy stochastic field |
| CN102700569A (en) * | 2012-06-01 | 2012-10-03 | 安徽理工大学 | Mining electric locomotive passerby monitoring method based on image processing and alarm system |
| CN103871029A (en) * | 2014-01-28 | 2014-06-18 | 西安科技大学 | Image enhancement and partition method |
| CN105069807A (en) * | 2015-08-28 | 2015-11-18 | 西安工程大学 | Punched workpiece defect detection method based on image processing |
-
2016
- 2016-01-08 CN CN201610010368.5A patent/CN105654496B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1489115A (en) * | 2003-08-14 | 2004-04-14 | 中国人民解放军第一军医大学 | Image optimized segmentation method based on generalized fuzzy stochastic field |
| CN102700569A (en) * | 2012-06-01 | 2012-10-03 | 安徽理工大学 | Mining electric locomotive passerby monitoring method based on image processing and alarm system |
| CN103871029A (en) * | 2014-01-28 | 2014-06-18 | 西安科技大学 | Image enhancement and partition method |
| CN105069807A (en) * | 2015-08-28 | 2015-11-18 | 西安工程大学 | Punched workpiece defect detection method based on image processing |
Non-Patent Citations (2)
| Title |
|---|
| 一种改进的Pla和King模糊边缘检测算法;杨勇 等;《仪器仪表学报》;20080930;第29卷(第9期);第1918-1922页 * |
| 图象模糊边缘检测的改进算法;周德龙 等;《中国图象图形学报》;20010430;第6卷(第4期);第353-358页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105654496A (en) | 2016-06-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105654496B (en) | The bionical adaptive fuzzy edge detection method of view-based access control model characteristic | |
| Wang et al. | Adaptive image enhancement method for correcting low-illumination images | |
| Tan et al. | Exposure based multi-histogram equalization contrast enhancement for non-uniform illumination images | |
| CN105654436B (en) | A kind of backlight image enhancing denoising method based on prospect background separation | |
| CN106683080B (en) | A kind of retinal fundus images preprocess method | |
| Park et al. | A contrast enhancement method using dynamic range separate histogram equalization | |
| CN107527332A (en) | Enhancement Method is kept based on the low-light (level) image color for improving Retinex | |
| CN104574293B (en) | Multiple dimensioned Retinex image sharpenings algorithm based on bounded computing | |
| CN103345733B (en) | Based on the quick enhancement method of low-illumination image improving dark channel prior | |
| CN109685742A (en) | A kind of image enchancing method under half-light environment | |
| CN106384339A (en) | Infrared night vision image enhancement method | |
| CN111968041A (en) | Self-adaptive image enhancement method | |
| Liu et al. | EFINet: Restoration for low-light images via enhancement-fusion iterative network | |
| CN110675351B (en) | Marine image processing method based on global brightness adaptive equalization | |
| CN108257099A (en) | A kind of adaptive infrared image enhancing method of view-based access control model contrast resolution | |
| CN114331873A (en) | Non-uniform illumination color image correction method based on region division | |
| CN115797333B (en) | Personalized customized intelligent vision training method | |
| CN113837974A (en) | NSST (non-subsampled contourlet transform) domain power equipment infrared image enhancement method based on improved BEEPS (Bayesian particle swarm optimization) filtering algorithm | |
| CN113344810A (en) | Image enhancement method based on dynamic data distribution | |
| CN109087310A (en) | Dividing method, system, storage medium and the intelligent terminal of Meibomian gland texture region | |
| CN117611501A (en) | Low-illumination image enhancement method, device, equipment and readable storage medium | |
| CN114359083B (en) | High-dynamic thermal infrared image self-adaptive preprocessing method for interference environment | |
| Han et al. | Low contrast image enhancement using convolutional neural network with simple reflection model | |
| CN104616259A (en) | Non-local mean image de-noising method with noise intensity self-adaptation function | |
| Zhang et al. | Muti-scale image enhancement based on properties of human visual system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180629 Termination date: 20200108 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |