CN110458761A - A kind of brain medicine fluorescence video image restorative procedure - Google Patents
A kind of brain medicine fluorescence video image restorative procedure Download PDFInfo
- Publication number
- CN110458761A CN110458761A CN201910553524.6A CN201910553524A CN110458761A CN 110458761 A CN110458761 A CN 110458761A CN 201910553524 A CN201910553524 A CN 201910553524A CN 110458761 A CN110458761 A CN 110458761A
- Authority
- CN
- China
- Prior art keywords
- video image
- frame
- pixel value
- image
- fluorescence
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 210000004556 brain Anatomy 0.000 title claims abstract description 33
- 239000003814 drug Substances 0.000 title claims abstract description 14
- 230000008859 change Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 5
- 238000003384 imaging method Methods 0.000 description 5
- BHPQYMZQTOCNFJ-UHFFFAOYSA-N Calcium cation Chemical compound [Ca+2] BHPQYMZQTOCNFJ-UHFFFAOYSA-N 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 229910001424 calcium ion Inorganic materials 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 206010029260 Neuroblastoma Diseases 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 1
- 241000700605 Viruses Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052791 calcium Inorganic materials 0.000 description 1
- 239000011575 calcium Substances 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000000399 optical microscopy Methods 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000006467 substitution reaction 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
- 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
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The present invention relates to a kind of brain medicine fluorescence video image restorative procedure, step 1, gray value normalized to brain fluorescence video image and using total variation regularization method denoising frame by frame；Step 2 carries out the operation of morphology top cap for video image, and saves the minimum and maximum pixel value of every frame image；Step 3, using positive linear contrast stretching method, max pixel value is mapped to 1, and minimum pixel value is mapped to 0；Reference frame is arranged in step 4, carries out relative motion compensation to video image, obtains images after registration；After finally carrying out reverse contrast linear stretch, positive contrast linear stretch, the video image finally repaired are carried out using the parameter of consistency frame by frame to video image for step 5.The present invention carries out effective denoising for video image, eliminates non-homogeneous background fluorescence, contrast stretching and interframe relative motion compensation integrated treatment, significantly improves video quality, promotes the accuracy of follow-up signal treatment process.
Description
Technical field
The present invention relates to medical image computer processing technical field more particularly to a kind of brain medicine fluorescence video images
Restorative procedure.
Background technique
Specific calcium responsive probe fluorescent marker has been widely used in the method that optical microscopy imaging technology combines
Brain neuroblastoma institutional framework research.By taking the research of typical mouse brain neuronal tissue structures as an example, in mouse internal injection
GCamp6 virus, will generate change very sensitive fluorescence signal to calcium ion concentration in vivo, open mouse head is minimally invasive
Hole, insertion optical fiber simultaneously connect small-sized microscope, can the variation to mouse brain fluorescence signal acquired in real time, based on institute
The video image obtained carries out signal analysis, can obtain the real-time distribution situation of mouse brain calcium ion, thus for analysis mouse
The flow feature of brain neuroblastoma composed structure and its inner material provides foundation.
However, since the studies above method is needed using collecting fiber mouse brain fluorescence signal and inputs microscope system
System, therefore imaging system must use lesser numerical aperture, the luminous flux into imaging system be strongly limited, due to glimmering
Optical signal is weaker, it is necessary to higher sensitivity be arranged for image device, above-mentioned two aspects reason makes resulting video image easily
By noise pollution.Further, since calcium ion can generate background fluorescence heterogeneous in the widely distributed of brain, into imaging
The identification of useful signal can be equally reduced after system.Further, since what is carried out is experiment made on the living, in signal acquisition process
Mouse is in active state, and flutter easily occurs for imaging system, causes the relative translation, rotation and contracting of image interframe in video
It puts.
These above-mentioned factors all can seriously reduce video quality, influence subsequent signal analysis and processing.Therefore, using number
Word image processing techniques, which repair to resulting video image, seems particularly necessary.
Summary of the invention
The purpose of the present invention is to provide a kind of brain medicine fluorescence video image restorative procedures, can be to video using it
Image carries out effective denoising, eliminates non-homogeneous background fluorescence, contrast stretching and interframe relative motion compensation General Office
Reason significantly improves video quality, promotes the accuracy of follow-up signal treatment process.
To achieve the above object, technical scheme is as follows:
A kind of brain medicine fluorescence video image restorative procedure, includes the following steps:
Step 1 is acquired brain fluorescence video image, and is become to after the gray value normalized of video image using total
Point regularization method is to video image denoising frame by frame；
Step 2, the video image obtained based on step 1 carry out the operation of morphology top cap, remove homogeneous background fluorescence, and
Save the max pixel value and minimum pixel value of every frame image；
Step 3 stretches image degree of comparing using positive linear contrast stretching method, reflects max pixel value
It is mapped to 1, minimum pixel value is mapped to 0；
Reference frame is arranged in step 4, is carried out using enhanced cross-correlation method to the resulting video image of step 3 opposite
Motion compensation obtains images after registration；
Step 5, after carrying out reverse contrast linear stretch for registration rear video image, using the parameter of consistency to video
Image carries out positive contrast linear stretch, the video image finally repaired frame by frame.
Brain medicine fluorescence video image restorative procedure according to claim 1, it is characterised in that: the step 2
Middle video image carries out the expression formula of morphology top cap operation are as follows:Wherein, htIt indicates to remove non-homogeneous back
The video image of scape fluorescence；utIndicate the video image after total variation regularization method denoising；Indicate that morphology opens fortune
It calculates；B indicates that structural elements needed for executing top cap operation, shape are circle, and the value range of radius r is 1≤r≤100.
The expression formula of positive linear contrast stretching method in the step 3 are as follows:Wherein, ftIt indicates
Resulting video image after positive linear contrast stretching；vtAnd stRespectively indicate htIn every frame image max pixel value and
Minimum pixel value.
The expression formula of reverse contrast linear stretch in the step 5 are as follows: ct=(vt-st)ft+st, wherein ctIndicate inverse
Resulting video image after to contrast stretching；vtAnd stRespectively indicate htIn every frame image max pixel value and minimum pixel
Value；
The calculation method of the parameter of consistency are as follows: vm=max (v1,v2,…,vT), sm=min (s1,s2,…,sT), wherein vmWith
smFor two parameter of consistency；Max and min function is respectively used to calculate the maximum value and minimum value of its input；
The expression formula of positive contrast linear stretch is carried out to image using the parameter of consistency are as follows:
Wherein, vtAnd stRespectively indicate htIn every frame image max pixel value and minimum pixel value；xtIndicate the video figure finally repaired
Picture.
Brain medicine fluorescence video image restorative procedure of the invention, by video image denoising, morphological operation
The integrated application of the methods of non-homogeneous background fluorescence, enhanced cross-correlation method and contrast stretching is removed, brain can be cured
The problems such as learning noise pollution, background fluorescence, relative motion, lower contrast present in fluorescence video image carries out General Office
Reason obtains clarity height, without relative motion, the apparent video image of contrast, and writing improves video quality, to guarantee subsequent letter
The accuracy of number treatment process provides basis.
Detailed description of the invention
Fig. 1 is the flow chart of brain medicine fluorescence video image restorative procedure of the present invention；
Fig. 2 is the raw video image that the embodiment of the present invention is intercepted from mouse brain fluorescence video；
Fig. 3 is the video image after denoising of the embodiment of the present invention；
Fig. 4 is that the embodiment of the present invention removes the video image after non-homogeneous background fluorescence；
Fig. 5 is video image of the embodiment of the present invention after positive linear contrast stretching；
Fig. 6 is that the enhanced cross-correlation method of the embodiment of the present invention carries out the video image after motion compensation；
Fig. 7 is video image of the embodiment of the present invention after reverse linear contrast stretches；
Fig. 8 is that the embodiment of the present invention carries out the final restored video figure after positive linear contrast stretching using the parameter of consistency
Picture.
Specific embodiment
Technical solution of the present invention is described in further detail with reference to the accompanying drawings and examples.
Such as Fig. 1, a kind of brain medicine fluorescence video image restorative procedure of the invention includes the following steps:
Step 1 is acquired brain fluorescence video image, and is become to after the gray value normalized of video image using total
Point regularization method is to video image denoising frame by frame；
Step 2, the video image obtained based on step 1 carry out the operation of morphology top cap, remove homogeneous background fluorescence, and
Save the max pixel value v of every frame imagetWith minimum pixel value st；
Step 3 stretches image degree of comparing using positive linear contrast stretching method, makes max pixel value vt
It is mapped to 1, minimum pixel value stIt is mapped to 0；
Reference frame is arranged in step 4, is carried out using enhanced cross-correlation method to the resulting video image of step 3 opposite
Motion compensation obtains images after registration；
Step 5, after carrying out reverse contrast linear stretch for registration rear video image, using the parameter of consistency to video
Image carries out positive contrast linear stretch, the video image finally repaired frame by frame.
In the minimally invasive aperture of mouse head, it is inserted into optical fiber and connects small-sized microscope, the variation to mouse brain fluorescence signal
It is acquired in real time, the video image based on acquisition carries out signal analysis, to obtain the real-time distribution of mouse brain calcium ion
Situation is illustrated in figure 2 the raw video image that a width is intercepted from mouse brain fluorescence video.
The intensity value ranges of raw video image are normalized to [0,1] by [0,255] first, then used by step 1
Total variation regularization method carries out denoising frame by frame to the image in video, obtain Fig. 3 be shown in as a result, total variation canonical
The expression formula for changing denoising method is as follows:
Wherein, gtAnd utVideo image after respectively indicating video original image and denoising；T is indicated in video image
Frame index, value range t=1,2 ..., T, T indicate the sum of image in video；I indicates the pixel rope in every frame image
Draw；N indicates sum of all pixels；WithRespectively indicate First-order Gradient operator both horizontally and vertically；λ indicates denoising canonical
Change coefficient, is 1≤λ≤1000 in range, the setting value of mouse brain video image λ is 100 in the present embodiment.
Step 2, the video image based on Fig. 3 carry out the operation of morphology top cap, remove homogeneous background fluorescence, obtain such as Fig. 4
Shown in video image, and save the max pixel value v of every frame imagetWith minimum pixel value st；Wherein, the calculating of top cap operation
Mode are as follows:
Wherein, htIndicate the image of the non-homogeneous background fluorescence of removal；utIt indicates after total variation regularization method denoising
Video image；Indicate morphology opening operation；B indicates that structural elements needed for executing top cap operation, shape are circle, radius r
Value range be 1≤r≤100, in the present embodiment the r setting value of Fig. 3 video image be 10.
Step 3, the video image based on Fig. 4, using positive linear contrast stretching method, max pixel value vtMapping
To 1, minimum pixel value stIt is mapped to 0, obtains view image as shown in Figure 5；The calculating formula that positive Linear Comparison stretches are as follows:
Wherein, f indicates the resulting image after positive linear contrast stretching；vtAnd stRespectively indicate htMiddle pixel is most
Big value and minimum value.
It is resulting as a result, eliminating adjacent to carry out relative motion compensation to Fig. 5 using enhanced cross-correlation method for step 4
Relative displacement, rotation and the scaling of interframe obtain registration rear video image, as shown in fig. 6, specifically executing step are as follows:
1) reference frame f is selectedm, wherein m >=1, m=1 in the present embodiment；
2) as t=m, rt=fm；
3) as t > m, circulation executes following steps until t=T terminates；
4) as t < m, circulation executes following steps until t=1 terminates；
Wherein, r indicates the image after motion compensation, PtIndicate the Affine operator of adjacent interframe.
Step 5 carries out reverse linear contrast's stretching based on registration rear video image, obtains video figure as shown in Figure 7
Picture, the expression formula that specific reverse linear contrast stretches are as follows:
ct=(vt-st)ft+st (6)
Wherein, c indicates resulting video image after reverse contrast stretching.
Calculate the parameter of consistency of contrast stretching, expression formula are as follows:
vm=max (v1,v2,…,vT), sm=min (s1,s2,…,sT) (7)
Wherein, vmAnd smIt is two parameter of consistency；Max and min function be respectively used to calculate its input variable maximum value and
Minimum value.
Positive linear contrast stretching is carried out using video image of the parameter of consistency to Fig. 7, obtains video as shown in Figure 8
Image, the expression formula of specific positive linear contrast stretching are as follows:
Wherein, vtAnd stRespectively indicate htIn every frame image max pixel value and minimum pixel value；xtIt indicates final to repair
Video image.
Brain fluorescence video image restorative procedure of the invention, can effectively denoise video image using it
Sound eliminates non-homogeneous background fluorescence, contrast stretching and interframe relative motion compensation integrated treatment, significantly improves video quality,
Promote the accuracy of follow-up signal treatment process.The original view that the mouse brain of the final video image of Fig. 8 and Fig. 2 are acquired
Frequency image compares, can Fig. 8 see that contrast is obviously improved, image detail has obtained effective enhancing, image matter greatly improved
Amount.
Above-described specific embodiment has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that being not intended to limit the present invention the foregoing is merely a specific embodiment of the invention
Protection scope, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all be contained in
Within protection scope of the present invention.
Claims (4)
1. a kind of brain medicine fluorescence video image restorative procedure, which comprises the steps of:
Step 1 acquires brain fluorescence video image, and is using total variation just to after the gray value normalized of video image
Then change method to video image denoising frame by frame；
Step 2, the video image obtained based on step 1 are carried out the operation of morphology top cap, remove homogeneous background fluorescence, and save
The max pixel value and minimum pixel value of every frame image；
Step 3 stretches picture contrast using positive linear contrast stretching method, is mapped to max pixel value
1, minimum pixel value is mapped to 0；
Reference frame is arranged in step 4, carries out relative motion to the resulting video image of step 3 using enhanced cross-correlation method
Compensation obtains registration rear video image；
Step 5, after carrying out reverse contrast linear stretch for registration rear video image, using the parameter of consistency to video image
Positive contrast linear stretch, the video image finally repaired are carried out frame by frame.
2. brain medicine fluorescence video image restorative procedure according to claim 1, it is characterised in that: in the step 2
The expression formula of video image progress morphology top cap operation are as follows:Wherein, htIt indicates to remove non-homogeneous background
The video image of fluorescence；utIndicate the video image after total variation regularization method denoising；Indicate morphology opening operation；b
Indicate that structural elements needed for executing top cap operation, shape are circle, the value range of radius r is 1≤r≤100.
3. brain medicine fluorescence video image restorative procedure according to claim 1, it is characterised in that: in the step 3
The expression formula of positive linear contrast stretching method are as follows:Wherein, ftAfter indicating positive linear contrast stretching
Resulting video image；vtAnd stRespectively indicate htIn every frame image max pixel value and minimum pixel value.
4. brain medicine fluorescence video image restorative procedure according to claim 1, it is characterised in that: in the step 5
The expression formula of reverse contrast linear stretch are as follows: ct=(vt-st)ft+st, wherein ctIndicate resulting after reverse contrast stretching
Video image；vtAnd stRespectively indicate htIn every frame image max pixel value and minimum pixel value；
The calculation method of the parameter of consistency are as follows: vm=max (v1,v2,…,vT), sm=min (s1,s2,…,sT), wherein vmAnd smFor
Two parameter of consistency；Max and min function is respectively used to calculate the maximum value and minimum value of its input；
The expression formula of positive contrast linear stretch is carried out to image using the parameter of consistency are as follows:
Wherein, vtAnd stRespectively indicate htIn every frame image max pixel value and minimum pixel value；xtIndicate the video figure finally repaired
Picture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910553524.6A CN110458761B (en) | 2019-06-25 | 2019-06-25 | Brain medical fluorescence video image restoration method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910553524.6A CN110458761B (en) | 2019-06-25 | 2019-06-25 | Brain medical fluorescence video image restoration method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110458761A true CN110458761A (en) | 2019-11-15 |
| CN110458761B CN110458761B (en) | 2023-05-23 |
Family
ID=68480829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910553524.6A Active CN110458761B (en) | 2019-06-25 | 2019-06-25 | Brain medical fluorescence video image restoration method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110458761B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103456021A (en) * | 2013-09-24 | 2013-12-18 | 苏州大学 | Piece goods blemish detecting method based on morphological analysis |
| CN104933682A (en) * | 2015-06-03 | 2015-09-23 | 浙江大学 | Integrated denoising method of inscription-like images |
| CN105893960A (en) * | 2016-03-31 | 2016-08-24 | 杭州电子科技大学 | Road traffic sign detecting method based on phase symmetry |
| CN106355584A (en) * | 2016-08-30 | 2017-01-25 | 上海交通大学 | Automatic detection method for microaneurysm in eye fundus image on basis of local entropy determining threshold |
| CN109685742A (en) * | 2018-12-29 | 2019-04-26 | 哈尔滨理工大学 | A kind of image enchancing method under half-light environment |
-
2019
- 2019-06-25 CN CN201910553524.6A patent/CN110458761B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103456021A (en) * | 2013-09-24 | 2013-12-18 | 苏州大学 | Piece goods blemish detecting method based on morphological analysis |
| CN104933682A (en) * | 2015-06-03 | 2015-09-23 | 浙江大学 | Integrated denoising method of inscription-like images |
| CN105893960A (en) * | 2016-03-31 | 2016-08-24 | 杭州电子科技大学 | Road traffic sign detecting method based on phase symmetry |
| CN106355584A (en) * | 2016-08-30 | 2017-01-25 | 上海交通大学 | Automatic detection method for microaneurysm in eye fundus image on basis of local entropy determining threshold |
| CN109685742A (en) * | 2018-12-29 | 2019-04-26 | 哈尔滨理工大学 | A kind of image enchancing method under half-light environment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110458761B (en) | 2023-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111583227B (en) | Method, device, equipment and medium for automatically counting fluorescent cells | |
| Nasir et al. | Unsupervised colour segmentation of white blood cell for acute leukaemia images | |
| Li et al. | Robust retinal image enhancement via dual-tree complex wavelet transform and morphology-based method | |
| US8351667B2 (en) | Methods of contrast enhancement for images having blood vessel structures | |
| CN116645384B (en) | Stem cell area rapid segmentation method based on artificial intelligence | |
| CN107358612A (en) | A kind of retinal vessel segmenting system combined based on fractal dimension with gaussian filtering and method | |
| CN114937024A (en) | Image evaluation method and device and computer equipment | |
| CN106548491A (en) | A kind of method for registering images, its image interfusion method and its device | |
| Dammers et al. | Automatic identification of gray and white matter components in polarized light imaging | |
| Huo et al. | Recognition of parasite eggs in microscopic medical images based on YOLOv5 | |
| Herold et al. | Automated detection and quantification of fluorescently labeled synapses in murine brain tissue sections for high throughput applications | |
| CN110458761A (en) | A kind of brain medicine fluorescence video image restorative procedure | |
| CN111292285B (en) | Automatic screening method for diabetes mellitus based on naive Bayes and support vector machine | |
| CN109064468A (en) | A method of using MATLAB quantitative analysis eyelid Meibomian gland form and area | |
| CN109646777A (en) | Auxiliary instrument self-adaptive switch mechanism | |
| Zhang et al. | Deep learning for three types of keratitis classification based on confocal microscopy images | |
| Tie-Rui et al. | The research of X-ray bone fracture image enhancement algorithms | |
| Ji et al. | Research on high-accuracy biological microscopic imaging and cell counting system | |
| Lu et al. | An improved quantitative analysis method for plant cortical microtubules | |
| CN111242014A (en) | Liquid drop imaging method and device for urinary sediment cell microscopic image | |
| Shi et al. | A segmentation-oriented inter-class transfer method: Application to retinal vessel segmentation | |
| CN117541800B (en) | Laryngoscope image-based laryngeal anomaly segmentation method | |
| Annunziata et al. | Combining efficient hand-crafted features with learned filters for fast and accurate corneal nerve fibre centreline detection | |
| Lakhani et al. | A novel method using SOM for recognizing patterns in dental radiographs-a conceptual approach | |
| Dai et al. | The Research of Multi-Modality Parkinson's Disease Image Based on Cross-Layer Convolutional Neural Network |
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 |