CN108053415A - Based on the bionical profile testing method for improving non-classical receptive field - Google Patents
Based on the bionical profile testing method for improving non-classical receptive field Download PDFInfo
- Publication number
- CN108053415A CN108053415A CN201711333790.5A CN201711333790A CN108053415A CN 108053415 A CN108053415 A CN 108053415A CN 201711333790 A CN201711333790 A CN 201711333790A CN 108053415 A CN108053415 A CN 108053415A
- Authority
- CN
- China
- Prior art keywords
- pixel
- receptive field
- classical receptive
- gabor
- inhibition
- 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.)
- Granted
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 13
- 230000005764 inhibitory process Effects 0.000 claims abstract description 30
- 230000004044 response Effects 0.000 claims abstract description 17
- 230000002401 inhibitory effect Effects 0.000 claims abstract description 6
- 238000001914 filtration Methods 0.000 claims description 7
- 230000001629 suppression Effects 0.000 claims description 6
- 230000009977 dual effect Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 10
- 230000007547 defect Effects 0.000 abstract description 2
- 230000000007 visual effect Effects 0.000 abstract description 2
- 238000000034 method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 241000282313 Hyaenidae Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention is intended to provide it is a kind of based on the bionical profile testing method for improving non-classical receptive field, comprise the following steps:A, image to be detected through gray proces is inputted;B, the Gabor filter functions for including multiple directions parameter are preset, carry out classical receptive field stimuli responsive, optimal direction of the corresponding direction as the pixel respectively to each pixel in image to be detected;C, built using log functions and inhibit kernel function, distance weighting function is built by inhibiting kernel function;The distance weighting function of the classical receptive field stimuli responsive of each pixel and the pixel is subjected to convolution and obtains the inhibition response of the pixel;D, the classical receptive field stimuli responsive of each pixel is subtracted into the inhibition response of the pixel and the product of default inhibition strength, and the final profile value of the pixel is calculated.The defects of detection method overcomes the prior art has the characteristics that the spatial character for meeting visual experience open country and detection result are more preferable.
Description
Technical field
The present invention relates to image processing fields, and in particular to a kind of based on the bionical contour detecting for improving non-classical receptive field
Method.
Background technology
For non-classical receptive field region, there is the model of many different inhibition situations.And traditional butterfly-type inhibits model, is
On the basis for inhibiting model in DoG, the suppression of background texture information is completed by the region of artificial limit lateral areas and petiolarea
System;It is the division by manually carrying out region that such butterfly-type, which inhibits core, it is necessary first to by ± 45 ° of directrixes to non-classical sense
Flank is carried out by open country and top area is divided, so as to show that the butterfly-type of a non-automatic defined area inhibits model.Press down in the butterfly-type
In simulation, lateral areas and petiolarea have different working rules, i.e. the calculating of lateral areas inhibition strength is based on an accurate ruler
Feature is spent come what is completed, and the calculating of petiolarea inhibition strength is then the adaptive change with the local feature on different spaces scale
's.In the local grain region that there may be effective contour, petiolarea can apply a weaker inhibition to classical receptive field,
The region of random texel is being filled on the contrary, a stronger inhibition can be applied.Traditional butterfly-type inhibits model simultaneously
It can not achieve the automatic division for inhibiting region and inhibit model and rationally rotated using the optimal direction of pixel, therefore,
Considerably increase the time cost of entire contour detecting process.
The content of the invention
It is the present invention is intended to provide a kind of based on the bionical profile testing method for improving non-classical receptive field, the detection method gram
The defects of taking the prior art has the characteristics that detection result is good, detection efficiency is high.
Technical scheme is as follows:
A kind of bionical profile testing method based on improvement non-classical receptive field, comprises the following steps:
A, image to be detected through gray proces is inputted;
B, the Gabor filter functions for including multiple directions parameter are preset, each pixel in image to be detected is distinguished
Gabor energy balanes are carried out using Gabor filter functions, obtain the Gabor energy values under all directions of each pixel;
For each pixel, the maximum in the Gabor energy values of its all directions is chosen, the classical receptive field as the pixel
Stimuli responsive, optimal direction of the corresponding direction of the maximum as the pixel;
C, structure inhibits kernel function, and distance weighting function is built by inhibiting kernel function;The classics of each pixel are felt
Convolution, which is carried out, by the distance weighting function of wild stimuli responsive and the pixel obtains the inhibition response of the pixel;
Inhibition kernel function log (x, the y;ε,σw) be:
Wherein For the optimal direction of pixel (x, y), ε=0.1,
σwTo inhibit core scale;
The classical receptive field stimuli responsive of each pixel is subtracted to the inhibition response of the pixel and default inhibition D,
The product of intensity obtains the profile response of the pixel, and profile response using non-maxima suppression and dual threshold is handled, is obtained
The final profile value of each pixel.
Preferably, the step B is specific as follows:
The expression formula of the Gabor filter functions is as follows:
Whereinγ represents oval receptive field major and minor axis ratio for one
Constant, parameter lambda is wavelength, and σ is scale, and 1/ λ is the spatial frequency of cosine function,It is phase angular dimensions, θ filters for Gabor
Directioin parameter;
Gabor energy values calculate as follows:
Wherein
Wherein θiFor a direction parameter of Gabor filtering, NθFor the number of the directioin parameter of Gabor filtering;I (x, y) is
Image to be detected, * are convolution operator;
The expression formula of classical receptive field stimuli responsive Ec (x, y) is as follows:
Preferably, the step C is specially:
The distance weighting function wσ(x,y;ε,σw) be:
Wherein,
Wherein | | | |1For (L1) norm, H (x)=max (0, x);
The inhibition response Inh (x, y) of each pixel is:
Inh (x, y)=Ec (x, y) * wσ(x,y;ε,σw) (8)。
Preferably, the step D is specially:
The profile responds R (x, y):
R (x, y)=H (Ec (x, y)-α Inh (x, y)) (9);
Wherein H (x)=max (0, x), α are inhibition strength.
The present invention then no longer needs artificially to divide non-classical receptive field region using improved inhibition model,
But by carry angle parameter log functions inhibit verification optimal direction carry out inhibit region rotation, eliminate manually into
The workload of row division, the whole operation efficiency of raising;Improved inhibition model enables the inhibition of each pixel to tie
The optimal direction of the pixel is closed to carry out, to reach optimal inhibition, while also more meets the visual characteristic of receptive field.
Description of the drawings
Fig. 1 is 1 profile testing method of embodiment and the testing result comparison diagram of 1 method of document
Specific embodiment
The present invention is illustrated with reference to the accompanying drawings and examples.
Embodiment 1
A kind of bionical profile testing method based on improvement non-classical receptive field, comprises the following steps:
A, image to be detected through gray proces is inputted;
B, the Gabor filter functions for including multiple directions parameter are preset, each pixel in image to be detected is distinguished
Gabor energy balanes are carried out using Gabor filter functions, obtain the Gabor energy values under all directions of each pixel;
For each pixel, the maximum in the Gabor energy values of its all directions is chosen, the classical receptive field as the pixel
Stimuli responsive, optimal direction of the corresponding direction of the maximum as the pixel;
The step B is specific as follows:
The expression formula of the Gabor filter functions is as follows:
Whereinγ represents oval receptive field axial ratio for one
The constant of example, parameter lambda are wavelength, and σ is scale, and 1/ λ is the spatial frequency of cosine function,It is phase angular dimensions, θ filters for Gabor
The directioin parameter of ripple;
Gabor energy values calculate as follows:
Wherein
Wherein θiFor a direction parameter of Gabor filtering, NθFor the number of the directioin parameter of Gabor filtering;I (x, y) is
Image to be detected, * are convolution operator;
The expression formula of classical receptive field stimuli responsive Ec (x, y) is as follows:
WhereinFor the optimal direction of pixel (x, y);
C, structure inhibits kernel function, and distance weighting function is built by inhibiting kernel function;The classics of each pixel are felt
Convolution, which is carried out, by the distance weighting function of wild stimuli responsive and the pixel obtains the inhibition response of the pixel;
Inhibition kernel function log (x, the y;ε,σw) be:
Whereinε=0.1, σwTo inhibit core scale;
The distance weighting function wσ(x,y;ε,σw) be:
Wherein,
Wherein, ε=0.1, σw=σ, | | | |1For (L1) norm, H (x)=max (0, x);
The inhibition response Inh (x, y) of each pixel is:
Inh (x, y)=Ec (x, y) * wσ(x,y;ε,σw) (10);
The classical receptive field stimuli responsive of each pixel is subtracted to the inhibition response of the pixel and default inhibition D,
The product of intensity obtains the profile response of the pixel, and profile response using non-maxima suppression and dual threshold is handled, is obtained
The final profile value of each pixel;
The step D is specially:
The profile responds R (x, y):
R (x, y)=H (Ec (x, y)-α Inh (x, y)) (11);
Wherein H (x)=max (0, x), α are inhibition strength;
Non-maxima suppression and binary conversion treatment involved in the present embodiment is using the method described in document 1, wherein wrapping
The two threshold value t containedh,tlIt is arranged to tl=0.5th, calculated by threshold value quantile p and obtained;
Document 1:GrigorescuC,PetkovN,WestenbergM.Contourdetectionbasedonnonclass
ical receptivefieldinhibition[J].IEEETransactionsonImageProcessing,2003,12
(7):729-739;
The contour detecting isotropic model for below providing the profile testing method of the present embodiment and document 1 carries out effective
Property comparison, wherein Performance Evaluating Indexes P uses the following standard that provides in document 1:
N in formulaTP、nFP、nFNThe number of the profile of correct profile, error profile and omission that detection obtains is represented respectively,
Evaluation metrics P values represent that the effect of contour detecting is better between [0,1], closer to 1, in addition, definition tolerance is:
The all calculations detected in the neighborhood of 5*5 correctly detect;
Choose 4 secondary classic map pictures in Fig. 1 and carry out Usefulness Pair ratio, be respectively adopted the isotropic model in document 1 and
1 method of embodiment carries out contour detecting to above-mentioned 4 width figure, and the parameter group of wherein 1 method selection of embodiment is as shown in table 1, chooses
The optimal result obtained in parameter group is compared;
1 embodiment of table, 1 parameter group table
Isotropic model in document 1 uses following parameter:α={ 1.0,1.2 };σ=1.4,1.6,1.8,2.0,
2.2,2.4,2.6,2.8};P={ 0.1,0.2,0.3,0.4,0.5 };
Fig. 1 show artwork, the reality of respectively basket, elephant_2, goat_3, hyena totally 4 secondary classic map pictures
Profile diagram, the optimal profile of 1 method of document detection, the optimal profile of 1 method of embodiment detection;It is above-mentioned 4 width figure as shown in table 2
The comparison of the optimal P values and the optimal P values of 1 method of embodiment detection of 1 method of the document detection of picture;
2 optimal P values of table compare
No matter it can be seen from the results above that from the effect of contours extract or from performance indicator parameter, implement
1 method of example is superior to the isotropic model in document 1.
Claims (4)
- It is 1. a kind of based on the bionical profile testing method for improving non-classical receptive field, it is characterised in that comprise the following steps:A, image to be detected through gray proces is inputted;B, the Gabor filter functions for including multiple directions parameter are preset, each pixel in image to be detected is utilized respectively Gabor filter functions carry out Gabor energy balanes, obtain the Gabor energy values under all directions of each pixel;For each A pixel chooses the maximum in the Gabor energy values of its all directions, and the classical receptive field as the pixel, which stimulates, to be rung Should, optimal direction of the corresponding direction of the maximum as the pixel;C, structure inhibits kernel function, and distance weighting function is built by inhibiting kernel function;By the classical receptive field of each pixel The distance weighting function of stimuli responsive and the pixel carries out convolution and obtains the inhibition response of the pixel;Inhibition kernel function log (x, the y;ε,σw) be:Wherein For the optimal direction of pixel (x, y), ε=0.1, σwFor suppression Core scale processed;The classical receptive field stimuli responsive of each pixel is subtracted to the inhibition response of the pixel and default inhibition strength D, Product, obtain the profile response of the pixel, profile response using non-maxima suppression and dual threshold handled, is obtained each The final profile value of pixel.
- 2. as described in claim 1 based on the bionical profile testing method for improving non-classical receptive field, it is characterised in that:The step B is specific as follows:The expression formula of the Gabor filter functions is as follows:Whereinγ is one and represents the normal of oval receptive field major and minor axis ratio Number, parameter lambda are wavelength, and σ is scale, and 1/ λ is the spatial frequency of cosine function,It is phase angular dimensions, θ is the side of Gabor filtering To parameter;Gabor energy values calculate as follows:WhereinWherein θiFor a direction parameter of Gabor filtering, NθFor the number of the directioin parameter of Gabor filtering;I (x, y) is to be checked Altimetric image, * are convolution operator;The expression formula of classical receptive field stimuli responsive Ec (x, y) is as follows:
- 3. as claimed in claim 2 based on the bionical profile testing method for improving non-classical receptive field, it is characterised in that:The step C is specially:The distance weighting function wσ(x,y;ε,σw) be:Wherein,Wherein | | | |1For (L1) norm, H (x)=max (0, x);The inhibition response Inh (x, y) of each pixel is:Inh (x, y)=Ec (x, y) * wσ(x,y;ε,σw) (8)。
- 4. as claimed in claim 3 based on the bionical profile testing method for improving non-classical receptive field, it is characterised in that:The step D is specially:The profile responds R (x, y):R (x, y)=H (Ec (x, y)-α Inh (x, y)) (9);Wherein H (x)=max (0, x), α are inhibition strength.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711333790.5A CN108053415B (en) | 2017-12-14 | 2017-12-14 | Bionic contour detection method based on improved non-classical receptive field |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711333790.5A CN108053415B (en) | 2017-12-14 | 2017-12-14 | Bionic contour detection method based on improved non-classical receptive field |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108053415A true CN108053415A (en) | 2018-05-18 |
CN108053415B CN108053415B (en) | 2020-05-22 |
Family
ID=62132689
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711333790.5A Active CN108053415B (en) | 2017-12-14 | 2017-12-14 | Bionic contour detection method based on improved non-classical receptive field |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108053415B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109919945A (en) * | 2019-02-01 | 2019-06-21 | 广西科技大学 | Profile testing method based on the non-linear two sides subunit response of non-classical receptive field |
CN109978898A (en) * | 2019-02-01 | 2019-07-05 | 广西科技大学 | Profile testing method based on vector field energy balane |
CN111539969A (en) * | 2020-04-23 | 2020-08-14 | 武汉铁路职业技术学院 | Image edge detection method and device, computer equipment and storage medium |
CN111968141A (en) * | 2020-06-30 | 2020-11-20 | 广西科技大学 | Non-classical receptive field contour detection method based on multi-scale superposition |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5740274A (en) * | 1991-09-12 | 1998-04-14 | Fuji Photo Film Co., Ltd. | Method for recognizing object images and learning method for neural networks |
US7433540B1 (en) * | 2002-10-25 | 2008-10-07 | Adobe Systems Incorporated | Decomposing natural image sequences |
CN101286237A (en) * | 2008-05-22 | 2008-10-15 | 重庆大学 | Movement target detection method based on visual sense bionics |
CN102254304A (en) * | 2011-06-17 | 2011-11-23 | 电子科技大学 | Method for detecting contour of target object |
CN102510368A (en) * | 2012-01-04 | 2012-06-20 | 西安电子科技大学 | Wireless orthogonal frequency division multiplexing (OFDM) signal peak-to-average ratio inhibition method based on amplitude distribution variation |
CN102750731A (en) * | 2012-07-05 | 2012-10-24 | 北京大学 | Stereoscopic vision significance calculating method based on left and right monocular receptive field and binocular fusion |
CN104318550A (en) * | 2014-09-27 | 2015-01-28 | 励盼攀 | Eight-channel multi-spectral imaging data processing method |
CN104484667A (en) * | 2014-12-30 | 2015-04-01 | 华中科技大学 | Contour extraction method based on brightness characteristic and contour integrity |
CN105261015A (en) * | 2015-09-29 | 2016-01-20 | 北京工业大学 | Automatic eyeground image blood vessel segmentation method based on Gabor filters |
CN105654496A (en) * | 2016-01-08 | 2016-06-08 | 华北理工大学 | Visual characteristic-based bionic adaptive fuzzy edge detection method |
CN106033610A (en) * | 2016-03-22 | 2016-10-19 | 广西科技大学 | Contour detection method based on non-classical receptive field space summation modulation |
CN106033608A (en) * | 2015-07-24 | 2016-10-19 | 广西科技大学 | Target contour detection method of biomimetic smooth tracking eye movement information processing mechanism |
-
2017
- 2017-12-14 CN CN201711333790.5A patent/CN108053415B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5740274A (en) * | 1991-09-12 | 1998-04-14 | Fuji Photo Film Co., Ltd. | Method for recognizing object images and learning method for neural networks |
US7433540B1 (en) * | 2002-10-25 | 2008-10-07 | Adobe Systems Incorporated | Decomposing natural image sequences |
CN101286237A (en) * | 2008-05-22 | 2008-10-15 | 重庆大学 | Movement target detection method based on visual sense bionics |
CN102254304A (en) * | 2011-06-17 | 2011-11-23 | 电子科技大学 | Method for detecting contour of target object |
CN102510368A (en) * | 2012-01-04 | 2012-06-20 | 西安电子科技大学 | Wireless orthogonal frequency division multiplexing (OFDM) signal peak-to-average ratio inhibition method based on amplitude distribution variation |
CN102750731A (en) * | 2012-07-05 | 2012-10-24 | 北京大学 | Stereoscopic vision significance calculating method based on left and right monocular receptive field and binocular fusion |
CN104318550A (en) * | 2014-09-27 | 2015-01-28 | 励盼攀 | Eight-channel multi-spectral imaging data processing method |
CN104484667A (en) * | 2014-12-30 | 2015-04-01 | 华中科技大学 | Contour extraction method based on brightness characteristic and contour integrity |
CN106033608A (en) * | 2015-07-24 | 2016-10-19 | 广西科技大学 | Target contour detection method of biomimetic smooth tracking eye movement information processing mechanism |
CN105261015A (en) * | 2015-09-29 | 2016-01-20 | 北京工业大学 | Automatic eyeground image blood vessel segmentation method based on Gabor filters |
CN105654496A (en) * | 2016-01-08 | 2016-06-08 | 华北理工大学 | Visual characteristic-based bionic adaptive fuzzy edge detection method |
CN106033610A (en) * | 2016-03-22 | 2016-10-19 | 广西科技大学 | Contour detection method based on non-classical receptive field space summation modulation |
Non-Patent Citations (4)
Title |
---|
CHUAN LIN 等: "Improved contour detection model with spatial summation properties based on nonclassical receptive field", 《JOURNAL OF ELECTRONIC IMAGING》 * |
K. GHOSH 等: "A possible mechanism of zero-crossing detection using the concept of the extended classical receptive field of retinal ganglion cells", 《BIOLOGICAL CYBERNETICS》 * |
窦燕 等: "一种视皮层非经典感受野的模型", 《燕山大学学报》 * |
陈韶斌: "基于周边抑制机理的遥感图像背景纹理抑制方法", 《计算机与数字工程》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109919945A (en) * | 2019-02-01 | 2019-06-21 | 广西科技大学 | Profile testing method based on the non-linear two sides subunit response of non-classical receptive field |
CN109978898A (en) * | 2019-02-01 | 2019-07-05 | 广西科技大学 | Profile testing method based on vector field energy balane |
CN109919945B (en) * | 2019-02-01 | 2022-03-25 | 广西科技大学 | Contour detection method based on non-classical receptive field non-linear two-side subunit response |
CN109978898B (en) * | 2019-02-01 | 2023-07-18 | 广西科技大学 | Contour detection method based on vector field energy calculation |
CN111539969A (en) * | 2020-04-23 | 2020-08-14 | 武汉铁路职业技术学院 | Image edge detection method and device, computer equipment and storage medium |
CN111539969B (en) * | 2020-04-23 | 2023-06-09 | 武汉铁路职业技术学院 | Image edge detection method, device, computer equipment and storage medium |
CN111968141A (en) * | 2020-06-30 | 2020-11-20 | 广西科技大学 | Non-classical receptive field contour detection method based on multi-scale superposition |
CN111968141B (en) * | 2020-06-30 | 2023-06-16 | 广西科技大学 | Non-classical receptive field contour detection method based on multi-scale superposition |
Also Published As
Publication number | Publication date |
---|---|
CN108053415B (en) | 2020-05-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108053415A (en) | Based on the bionical profile testing method for improving non-classical receptive field | |
CN109003240B (en) | Image denoising method based on multi-scale parallel CNN | |
EP3384429B1 (en) | Method for identification of candidate points as possible characteristic points of a calibration pattern within an image of the calibration pattern | |
CN107767387B (en) | Contour detection method based on variable receptive field scale global modulation | |
CN108875621B (en) | Image processing method, image processing device, computer equipment and storage medium | |
CN104285239B (en) | Image processing apparatus, image processing method and printed medium | |
CN106033610B (en) | Profile testing method based on the modulation of non-classical receptive field spatial summation | |
CN108022233A (en) | A kind of edge of work extracting method based on modified Canny operators | |
CN103839234B (en) | A kind of double geometry non-local mean image de-noising methods based on controlled core | |
CN109410149B (en) | CNN denoising method based on parallel feature extraction | |
CN106033608B (en) | The objective contour detection method of bionical object smooth pursuit eye movement information processing mechanism | |
CN107845086A (en) | A kind of detection method, system and the device of leather surface conspicuousness defect | |
CN103778611B (en) | Utilize the switch weight vectors median filter method of rim detection | |
CN110969606B (en) | Texture surface defect detection method and system | |
CN109410114A (en) | Compressed sensing image reconstruction algorithm based on deep learning | |
CN106204462A (en) | Non-local mean denoising method based on image multiple features fusion | |
CN108010046A (en) | Based on the bionical profile testing method for improving classical receptive field | |
CN107067407B (en) | Contour detection method based on non-classical receptive field and linear nonlinear modulation | |
CN107742302B (en) | Contour detection method based on primary visual cortex multi-scale contour fusion | |
CN111191735A (en) | Convolutional neural network image classification method based on data difference and multi-scale features | |
US20130084025A1 (en) | Method for Brightness Correction of Defective Pixels of Digital Monochrome Image | |
CN107766866A (en) | Set direction profile testing method based on receptive field subregion | |
CN106683043B (en) | Parallel image splicing method and device of multi-channel optical detection system | |
Wenshu et al. | Study on wood board defect detection based on artificial neural network | |
CN109034235B (en) | Multi-feature-based integrated SVM noise point detection method |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
EE01 | Entry into force of recordation of patent licensing contract | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20180518 Assignee: GUANGXI YINGTENG EDUCATION TECHNOLOGY Co.,Ltd. Assignor: GUANGXI University OF SCIENCE AND TECHNOLOGY Contract record no.: X2023980053979 Denomination of invention: A biomimetic contour detection method based on improved non classical receptive field Granted publication date: 20200522 License type: Common License Record date: 20231226 |