CN107093166A - The seamless joint method of low coincidence factor micro-image - Google Patents
The seamless joint method of low coincidence factor micro-image Download PDFInfo
- Publication number
- CN107093166A CN107093166A CN201710212589.5A CN201710212589A CN107093166A CN 107093166 A CN107093166 A CN 107093166A CN 201710212589 A CN201710212589 A CN 201710212589A CN 107093166 A CN107093166 A CN 107093166A
- Authority
- CN
- China
- Prior art keywords
- image
- matching
- pair
- spliced
- roi
- 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 66
- 238000012986 modification Methods 0.000 claims abstract description 6
- 230000004048 modification Effects 0.000 claims abstract description 6
- 238000000605 extraction Methods 0.000 claims abstract description 5
- 230000007812 deficiency Effects 0.000 claims abstract description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 230000000750 progressive effect Effects 0.000 claims description 3
- 230000005477 standard model Effects 0.000 claims description 2
- 238000013461 design Methods 0.000 description 6
- 238000000386 microscopy Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 241000193830 Bacillus <bacterium> Species 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 101100001674 Emericella variicolor andI gene Proteins 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000011882 arthroplasty Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000002500 effect on skin Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 210000003491 skin Anatomy 0.000 description 1
- 210000004927 skin cell Anatomy 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
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention discloses a kind of seamless joint method of low coincidence factor micro-image, the described method comprises the following steps:The region of interest ROI with reference to figure and figure to be spliced is chosen, ROI is pre-processed;ROI SURF characteristic points are extracted, characteristic point is slightly matched using FLANN methods;The excessive matching pair of space length is rejected according to the deviation range of two images;The remaining matching of statistics to space length discrete distribution, to be maximally distributed the interval corresponding to probability for critical field, further reject error hiding pair, if matching is to deficiency, abovementioned steps, modification feature extraction parameter and match parameter are returned to, to obtain more matchings pair;According to remainder matching pair, the position relationship of two images is calculated;Treat spliced map and carry out brightness adjustment, take weighted mean method to merge image.This method is based on improved SURF Characteristic points matchs method, characteristic matching precision and efficiency is effectively improved in the case of the low Duplication of image, so as to improve the quality and speed of image mosaic.
Description
Technical field
It is seamless under more particularly to a kind of low coincidence factor of adjacent micro-image the present invention relates to digital image processing techniques field
The method of splicing.
Background technology
The problem of there is very time-consuming and inefficiency always in the microscope inspection observation of biological specimen, current full-automatic microscopy
Platform progressively replaces original cervical arthroplasty, and this cost savings manpower.In order to obtain the micro-image of big visual field large scene,
Need to splice the image under many scenes.If full-automatic microscopy machine needs the big field-of-view image under N number of different low coverages, this
Need effectively this N number of Microscopic Image Mosaicing into a secondary seamless image, in case follow-up automatic classification, the knowledge for realizing biological specimen
Not with counting.
Image mosaic is applied to commercial measurement, and its core technology is image registration techniques, including template method for registering, phase
Degree of correlation method and characteristic matching method.These methods are using the overlapping region of adjacent image as registering basis, dependent on image in itself
Feature carries out registration, therefore splicing precision is not high, and amount of calculation is very big, and the overlap proportion to overlapping region requires higher, has
Even to reach more than 50% overlap proportion.When measurement object lens multiple is higher, measurement visual field is smaller in itself
In the case of, big overlap proportion seriously constrains expansion of the splicing to measurement visual field area, particularly when overlapping region is not bright
During aobvious feature, or even situation about can not match occurs.
The content of the invention
It is an object of the invention to provide a kind of seamless joint method of low coincidence factor micro-image, this method can be effective
Improve the precision and speed of many scene hypograph splicings in ground.
Realize the technical scheme is that:
A kind of seamless joint method of low coincidence factor micro-image, this method comprises the following steps:
Step 1:Choose with reference to figure and the area-of-interest of figure to be spliced(ROI), ROI is pre-processed;
Step 2:ROI SURF (Speed-up robust feature) characteristic point is extracted, using FLANN (Fast Library
Approximate Nearest Neighbors) method slightly matched to characteristic point;
Step 3:The excessive matching pair of space length is rejected according to the deviation range of two images;
Step 4:The remaining matching of statistics to space length discrete distribution, to be maximally distributed the interval corresponding to probability for standard
Scope, further rejects error hiding pair;If matching is to deficiency, abovementioned steps, modification feature extraction parameter and match parameter are returned,
To obtain more matchings pair;
Step 5:According to remainder matching pair, the position relationship of two images is calculated;
Step 6:Treat spliced map and carry out brightness adjustment, take weighted mean method to merge image;Wherein:
The low coincidence factor is the coincidence factor between adjacent image between 3%~11%.
The step 1 is specially:
Read reference pictureI 0(x, y) and image to be splicedI 1(x, y), choose in two width figures and to close on area comprising lap
Domain removes the noise spot in ROI as region of interest ROI using median filtering method, wherein, filter window is dimensioned to 3
×3;
Using the method for histogram equalization, expand its dynamic range, to strengthen the contrast of image.
The step 2 is specially:
The SURF characteristic points in ROI are extracted respectively, and each characteristic point is described with an isometric characteristic vector, the feature extracted
Point set is designated as F0 and F1 respectively;
Using FLANN methods, for each characteristic point in F0, K minimum point of characteristic vector distance therewith is found out in F1,
K=2, if minimum range and the ratio of time small distance are less than certain threshold value, then it is assumed that the point corresponding to minimum range is matching;
Otherwise it is assumed that this feature point in F0 is without matched characteristic point in F1;Wherein, certain threshold value initial value is set to
0.5。
The step 3 is specially:
According to the feature of multiple gathered image pattern, image Duplication is between 3% ~ 11%, and the offset of vertical direction is 5%
Within, larger boundary 11% and 5% is taken, corresponding boundary shifts amount is drawn, as thresholding, to each pair in thick matching result
With point, judge whether its space length meets the threshold condition, satisfaction then retains;It is unsatisfactory for, is considered as error hiding and is removed.
The step 4 is specially:
The space length of matching double points is divided into the equal interval of multiple step-lengths, by space length discretization;To previous step institute
All matchings pair remained, calculate discrete distribution situation of the matching to space length;If secondary maximum probability and maximum probability
Ratio be less than certain threshold value T, then it is critical field to choose interval corresponding to maximum probability;If the ratio is more than certain threshold value,
And secondary maximum probability is adjacent with interval corresponding to maximum probability, then chooses the interlude of the two adjacent intervals as standard model
Enclose;Other situations, then return to step 2, change the extracting parameter of SURF characteristic points, and the parameter that FLANN is matched, to obtain more
Many matching double points;Judge whether the space length of the matching double points remained for every a pair meets the critical field successively, it is full
Correctly matching is to retaining for the conduct of sufficient condition, and the ungratified error hiding that is considered as is to being removed;Judge the matching finally remained
Whether logarithm reaches certain amount, if lazy weight, return to step 2, changes the extracting parameter of SURF characteristic points, and FLANN
The parameter of matching, to obtain more matching double points;Wherein, certain threshold value T spans are 0.4 ~ 0.6.
The step 5 is specially:
To the matching double points finally remained, according to the locus of match point, reference picture is asked for using the method for average and treated
The spatial offset of stitching image, it is determined that position relationship between the two.
The step 6 is specially:
The relative position relation of the two images drawn according to previous step, determines the real overlapping region of two images;
The RGB color average of overlapping region between reference picture and image to be spliced is calculated respectively, obtains each color of reference picture
Component average R0, G0, B0, and image to be spliced each color component average R1, G1, B1;
The color average of image to be spliced subtracts the color average of reference picture, obtains color difference Dr, Dg, Db, in this, as
The overall brightness difference of two images;
Each pixel of stitching image is treated, each color component adds Dr, Dg, Db, its luminance level is adjusted to respectively
It is consistent with reference picture;
Each pixel of image overlapping region to be spliced to reference picture and by brightness adjustment, according to its position,
Different weights are set, with the progressive weighted average method gradually gone out, overlapping region merged, non-overlapped area is then directly replicated
Artwork.
The beneficial effects of the invention are as follows:The seamless spliced side of micro-image under a kind of low coincidence factor proposed by the invention
Method, improved SURF Characteristic points matchs method is used in the case of the low Duplication of adjacent image, effectively characteristics of image is extracted simultaneously
The efficiency and precision of characteristic matching are improved, so as to improve the quality and splicing speed of image mosaic.
Brief description of the drawings
The image sequence schematic diagram for the acquisition that Fig. 1 provides for the present invention;
Fig. 2 is flow chart of the invention;
Fig. 3 is the image split-joint method flow chart of improved distinguished point based of the invention;
Influence schematic diagrames of the Fig. 4 for the image enhaucament of the invention provided to feature point extraction effect;Fig. 4 (a) is not carry out image
The characteristic point that enhancing is extracted using SURF algorithm;Fig. 4 (b) is that the characteristic point that SURF algorithm is extracted is used to image enhaucament;
Method and the effect contrast figure of other matching process that Fig. 5 provides for the present invention;Fig. 5 (a) is the effect that FLANN is slightly matched
Fruit figure, Fig. 5 (b) are to use RANSAC algorithms to be to use to improve to the design sketch after Fig. 5 (a) progress error hiding rejectings, Fig. 5 (c)
Characteristic point matching method to Fig. 5 (a) reject part error hiding after design sketch;
The design sketch that Fig. 6 is lifted for the use brightness adjustment that the present invention is provided to fusion mass;Fig. 6 (a) is reference picture, 6 (b)
It is that image to be spliced, 6 (c) are that not carry out brightness adjustment directly to the design sketch after image co-registration, 6 (d) be to carry out brightness adjustment
Then to the design sketch after image co-registration;
Fig. 7 is the design sketch spliced for 4 × 4 collection image using image split-joint method of the invention;Fig. 7 (a) is
Dermal harvest image, 7 (b) of original 4 × 4 are original 4 × 4 tubercle bacillus collection images;Fig. 7 (c) is spliced
Skin image, 7 (d) are spliced tubercle bacillus images.
Embodiment
Illustrate technological means of the present invention, technological improvement and beneficial effect in order to be more clearly understood, tie below
Closing accompanying drawing, the present invention will be described in detail.
The motion of step motor control objective table being used automatic microscopy platform, because stepper motor is in the spy of precision aspect more
The image collected after property and the return difference problem present in motion process, continuous translation is not ensured that in X-axis and Y-axis
Definitely alignment, total slightly deviation, Fig. 1 is the image sequence schematic diagram that automatic microscopy machine is obtained;But stepper motor is generally controlled
Precision is still very high, therefore the Microscopic Image Mosaicing problem for being obtained under automatic microscopy machine, one kind provided by the present invention
Based on the micro-image seamless joint method under low coincidence factor, referring to Fig. 2 and Fig. 3, including following steps:
S101:Choose with reference to figure and the area-of-interest of figure to be spliced(ROI), ROI is pre-processed.
The step is specially:
Read reference pictureI 0(x, y) and image to be splicedI 1(x, y);
ChooseI 0(x, y) andI 1(x, y) include adjacent domain including overlay region as area-of-interest(ROI), it is designated asI R0 WithI R1 ;
Using median filtering method pairI R0 WithI R1 It is filtered to remove abnormity point, the window size of wherein medium filtering is set to 3
× 3, the image after processing is designated asI R0 ’ WithI R1 ’ ;
It is rightI R0 ’ WithI R1 ’ , using the method for histogram equalization, expand its dynamic range, to strengthen the contrast of image, processing
Image afterwards is designated asI R0 ’’ WithI R1 ’’ 。
S102:ROI SURF characteristic points are extracted, characteristic point is slightly matched using FLANN methods.
The step is specially:
Extract respectivelyI R0 ’’ WithI R1 ’’ In SURF characteristic points, the feature point set extracted is designated as F respectively0And F1;
Using FLANN methods, for each characteristic point in F0, the minimum K of characteristic vector distance therewith is found out in F1(K can
It is set to 2)It is individual, if minimum range and the ratio of time small distance are less than certain threshold value(Initial value is set to 0.5), then it is assumed that most narrow spacing
It is matching from corresponding point;Otherwise it is assumed that this feature point in F0 is without matched characteristic point in F1;Matching
M is designated as to set1。
S103:The excessive matching pair of space length is rejected according to the deviation range of two images.
The step is specially:
According to the feature of multiple gathered image pattern, image Duplication is between 3% ~ 11%, and the offset of vertical direction is 5%
Within, larger boundary 11% and 5% is taken, corresponding boundary shifts amount is drawn, as thresholding, to M1Middle each pair match point, judges
Whether its space length meets the threshold condition, and satisfaction then retains;It is unsatisfactory for, is considered as error hiding and is removed.Remained
The set being composed of is designated as M2。
S104:The remaining matching of statistics to space length discrete distribution, using be maximally distributed the interval corresponding to probability as
Critical field, further rejects error hiding pair;If matching is to deficiency, S102, modification feature extraction parameter and match parameter are returned,
To obtain more matchings pair.
The step is specially:
By M2The space length of middle matching double points is divided into the equal interval d of multiple step-lengths1, d2, d3,…dn, by space length
Discretization;
To M2In all matching double points, calculate the discrete distribution situation of its space length, that is, fall in each interval probability;
Maximum probability is designated as P1, secondary maximum probability is designated as P2, P2With P1Ratio be designated as Ratio;
If Ratio value is less than certain threshold value(Span is 0.4 ~ 0.6), choose P1Corresponding is interval interval as standard
ds;If Ratio is more than certain threshold value, and P1With P2Corresponding is interval adjacent, then chooses the two interval interludes as mark
Quasi- interval ds;Other situations, then return to step S102, changes the extracting parameter of SURF characteristic points, and the ginseng that FLANN is matched
Number, to obtain more matching double points;
M is judged successively2In the space lengths of every a pair of matching double points whether belong to standard interval ds, belong to dsCorrect of conduct
Pairing retain, what is be not belonging to is considered as error hiding to being removed, the matching remained to set be designated as M3;
Judge M3In matching logarithm whether reach certain amount, if lazy weight, return to step S102, change SURF characteristic points
Extracting parameter, and FLANN matching parameter, to obtain more matching double points.
S105:According to the matching double points finally remained, the position relationship between reference picture and image to be spliced is calculated.
The step is specially:
To M3In matching double points, according to the locus of match point, reference picture and image to be spliced are asked for using the method for average
Spatial offset, determine reference picture and matching image between position relationship.
S106:Treat stitching image and carry out brightness adjustment, take weighted mean method to carry out splicing fusion to image.
The step is specially:
The relative position relation of the two images drawn according to previous step, determines the real overlapping region of two images,I 0(x,y) in overlay region be designated as r0, I 1(x, y) in overlay region be designated as r1;
R is calculated respectively0And r1RGB color average, obtain r0Each color component average R0, G0, B0, and r1Each color point
Measure average R1, G1, B1;
R1, G1, B1With R0, G0, B0It is poor to make respectively, obtains color difference Dr, Dg, Db, the entirety in this, as two images is bright
Spend difference;
Treat stitching imageI 1(x, y) each pixel, each color component respectively add Dr, Dg, Db, be as a result designated asI 1 ’
(x, y), willI 1(x, y) luminance level be adjusted to and reference pictureI 0(x, y) consistent;
It is rightI 0(x, y) andI 1 ’(x, y) overlapping region each pixel, according to its position, different weights are set, used
The progressive weighted average method gradually gone out, is merged to overlapping region, and artwork is then directly replicated in non-overlapped area, obtains stitching imageI mosaic。
When application the inventive method and application RANSAC methods that table 1 provides for the present invention are improved spent by matching precision
Between comparison diagram.
Table 1
Smart matching process | RANSAC (s) | The method (s) that the present invention is provided |
Skin Cell figure | 0.140 | 0.027 |
Tubercle bacillus is schemed | 0.513 | 0.021 |
In summary, under a kind of micro-image proposed by the invention low coincidence factor image seamless joining method, in registration side
SURF characteristic points are based in method, the contrast of image is further improved by image enchancing method, makes the feature of image more prominent
Go out, the characteristic point extracted is slightly matched using FLANN algorithms, then using based on space length feature between match point
Method, progressively reject the Mismatching point pair in thick matching result;, can be by adjusting if the correct matching double points remained are not enough
The extracting parameter of whole SURF characteristic points, and the parameter that FLANN is matched, to obtain more matching double points, so as to improve registration
Precision;Because reference picture and image to be spliced have certain aberration, image can be increased substantially by brightness of image adjustment
Effect after fusion.Fabric analysis is carried out for the wide-field micro-image of later use significant figure is provided using the inventive method
According to.According to different application backgrounds, the present invention is equally applicable to the image mosaic of other association areas by appropriate modification.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc. should be included in the scope of the protection.
Claims (7)
1. a kind of seamless joint method of low coincidence factor micro-image, it is characterised in that this method comprises the following steps:
Step 1:Selection is ROI with reference to the area-of-interest of figure and figure to be spliced, and ROI is pre-processed;
Step 2:ROI SURF characteristic points are extracted, characteristic point is slightly matched using FLANN methods;
Step 3:The excessive matching pair of space length is rejected according to the deviation range of two images;
Step 4:The remaining matching of statistics to space length discrete distribution, to be maximally distributed the interval corresponding to probability for standard
Scope, further rejects error hiding pair;If matching is to deficiency, abovementioned steps, modification feature extraction parameter and match parameter are returned,
To obtain more matchings pair;
Step 5:According to remainder matching pair, the position relationship of two images is calculated;
Step 6:Treat spliced map and carry out brightness adjustment, take weighted mean method to merge image;Wherein:
The low coincidence factor is the coincidence factor between adjacent image between 3%~11%.
2. the micro-image seamless joint method under low coincidence factor according to claim 1, it is characterised in that the step
1 is specially:
Read reference pictureI 0(x, y) and image to be splicedI 1(x, y), choose in two width figures and to close on area comprising lap
Domain removes the noise spot in ROI as region of interest ROI using median filtering method, wherein, filter window is dimensioned to 3
×3;
Using the method for histogram equalization, expand its dynamic range, to strengthen the contrast of image.
3. the micro-image seamless joint method under low coincidence factor according to claim 1, it is characterised in that the step
2 are specially:
The SURF characteristic points in ROI are extracted respectively, and each characteristic point is described with an isometric characteristic vector, the feature extracted
Point set is designated as F0 and F1 respectively;
Using FLANN methods, for each characteristic point in F0, K minimum point of characteristic vector distance therewith is found out in F1,
K=2, if minimum range and the ratio of time small distance are less than certain threshold value, then it is assumed that the point corresponding to minimum range is matching;
Otherwise it is assumed that this feature point in F0 is without matched characteristic point in F1;Wherein, certain threshold value initial value is set to
0.5。
4. the micro-image seamless joint method under low coincidence factor according to claim 1, it is characterised in that the step
3 are specially:
According to the feature of multiple gathered image pattern, image Duplication is between 3% ~ 11%, and the offset of vertical direction is 5%
Within, larger boundary 11% and 5% is taken, corresponding boundary shifts amount is drawn, as thresholding, to each pair in thick matching result
With point, judge whether its space length meets the threshold condition, satisfaction then retains;It is unsatisfactory for, is considered as error hiding and is removed.
5. the micro-image seamless joint method under low coincidence factor according to claim 1, it is characterised in that the step
4 are specially:
The space length of matching double points is divided into the equal interval of multiple step-lengths, by space length discretization;To previous step institute
All matchings pair remained, calculate discrete distribution situation of the matching to space length;If secondary maximum probability and maximum probability
Ratio be less than certain threshold value T, then it is critical field to choose interval corresponding to maximum probability;If the ratio is more than certain threshold value,
And secondary maximum probability is adjacent with interval corresponding to maximum probability, then chooses the interlude of the two adjacent intervals as standard model
Enclose;Other situations, then return to step 2, change the extracting parameter of SURF characteristic points, and the parameter that FLANN is matched, to obtain more
Many matching double points;Judge whether the space length of the matching double points remained for every a pair meets the critical field successively, it is full
Correctly matching is to retaining for the conduct of sufficient condition, and the ungratified error hiding that is considered as is to being removed;Judge the matching finally remained
Whether logarithm reaches certain amount, if lazy weight, return to step 2, changes the extracting parameter of SURF characteristic points, and FLANN
The parameter of matching, to obtain more matching double points;Wherein, certain threshold value T spans are 0.4 ~ 0.6.
6. the micro-image seamless joint method under low coincidence factor according to claim 1, it is characterised in that the step
5 are specially:
To the matching double points finally remained, according to the locus of match point, reference picture is asked for using the method for average and treated
The spatial offset of stitching image, it is determined that position relationship between the two.
7. the micro-image seamless joint method under low coincidence factor according to claim 1, it is characterised in that the step
6 are specially:
The relative position relation of the two images drawn according to previous step, determines the real overlapping region of two images;
The RGB color average of overlapping region between reference picture and image to be spliced is calculated respectively, obtains each color of reference picture
Component average R0, G0, B0, and image to be spliced each color component average R1, G1, B1;
The color average of image to be spliced subtracts the color average of reference picture, obtains color difference Dr, Dg, Db, in this, as
The overall brightness difference of two images;
Each pixel of stitching image is treated, each color component adds Dr, Dg, Db, its luminance level is adjusted to respectively
It is consistent with reference picture;
Each pixel of image overlapping region to be spliced to reference picture and by brightness adjustment, according to its position,
Different weights are set, with the progressive weighted average method gradually gone out, overlapping region merged, non-overlapped area is then directly replicated
Artwork.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710212589.5A CN107093166B (en) | 2017-04-01 | 2017-04-01 | The seamless joint method of low coincidence factor micro-image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710212589.5A CN107093166B (en) | 2017-04-01 | 2017-04-01 | The seamless joint method of low coincidence factor micro-image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107093166A true CN107093166A (en) | 2017-08-25 |
CN107093166B CN107093166B (en) | 2019-07-05 |
Family
ID=59648929
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710212589.5A Active CN107093166B (en) | 2017-04-01 | 2017-04-01 | The seamless joint method of low coincidence factor micro-image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107093166B (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108109112A (en) * | 2018-01-16 | 2018-06-01 | 上海同岩土木工程科技股份有限公司 | A kind of tunnel spread figure splicing parameter processing method based on Sift features |
CN109559275A (en) * | 2018-11-07 | 2019-04-02 | 苏州迈瑞科技有限公司 | A kind of Urine Analyzer MIcrosope image joining method |
CN110599404A (en) * | 2019-09-24 | 2019-12-20 | 陕西晟思智能测控有限公司 | Circuit board microscopic image splicing method and device and information data processing terminal |
CN110689511A (en) * | 2019-09-19 | 2020-01-14 | 华东师范大学 | Optimization method for large-visual-field image splicing path |
CN110706191A (en) * | 2019-10-14 | 2020-01-17 | 中国空气动力研究与发展中心超高速空气动力研究所 | High-pressure container detection method based on infrared image splicing fusion algorithm |
CN110738695A (en) * | 2019-10-12 | 2020-01-31 | 哈尔滨工业大学 | image feature point mismatching and removing method based on local transformation model |
CN111105346A (en) * | 2019-11-08 | 2020-05-05 | 同济大学 | Full-scanning microscopic image splicing method based on peak value search and gray template registration |
CN111179170A (en) * | 2019-12-18 | 2020-05-19 | 深圳北航新兴产业技术研究院 | Rapid panoramic stitching method for microscopic blood cell images |
CN111260561A (en) * | 2020-02-18 | 2020-06-09 | 中国科学院光电技术研究所 | Rapid multi-graph splicing method for mask defect detection |
CN111882484A (en) * | 2020-06-16 | 2020-11-03 | 河北汉光重工有限责任公司 | Servo control method in high-speed seamless image splicing of submersible imaging system |
CN112164001A (en) * | 2020-09-29 | 2021-01-01 | 南京理工大学智能计算成像研究院有限公司 | Digital microscope image rapid splicing and fusing method |
CN113012030A (en) * | 2019-12-20 | 2021-06-22 | 北京金山云网络技术有限公司 | Image splicing method, device and equipment |
CN113205457A (en) * | 2021-05-11 | 2021-08-03 | 华中科技大学 | Microscopic image splicing method and system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104036480A (en) * | 2014-06-20 | 2014-09-10 | 天津大学 | Surf algorithm based quick mismatching point eliminating method |
CN104851094A (en) * | 2015-05-14 | 2015-08-19 | 西安电子科技大学 | Improved method of RGB-D-based SLAM algorithm |
CN104966270A (en) * | 2015-06-26 | 2015-10-07 | 浙江大学 | Multi-image stitching method |
CN105608689A (en) * | 2014-11-20 | 2016-05-25 | 深圳英飞拓科技股份有限公司 | Method and device for eliminating image feature mismatching for panoramic stitching |
CN105869120A (en) * | 2016-06-16 | 2016-08-17 | 哈尔滨工程大学 | Image stitching real-time performance optimization method |
CN105957007A (en) * | 2016-05-05 | 2016-09-21 | 电子科技大学 | Image stitching method based on characteristic point plane similarity |
-
2017
- 2017-04-01 CN CN201710212589.5A patent/CN107093166B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104036480A (en) * | 2014-06-20 | 2014-09-10 | 天津大学 | Surf algorithm based quick mismatching point eliminating method |
CN105608689A (en) * | 2014-11-20 | 2016-05-25 | 深圳英飞拓科技股份有限公司 | Method and device for eliminating image feature mismatching for panoramic stitching |
CN104851094A (en) * | 2015-05-14 | 2015-08-19 | 西安电子科技大学 | Improved method of RGB-D-based SLAM algorithm |
CN104966270A (en) * | 2015-06-26 | 2015-10-07 | 浙江大学 | Multi-image stitching method |
CN105957007A (en) * | 2016-05-05 | 2016-09-21 | 电子科技大学 | Image stitching method based on characteristic point plane similarity |
CN105869120A (en) * | 2016-06-16 | 2016-08-17 | 哈尔滨工程大学 | Image stitching real-time performance optimization method |
Non-Patent Citations (3)
Title |
---|
LI JUNFEI 等: "Improved SURF Detection combined with Dual FLANN Matching and Clustering Analysis", 《APPLIED MECHANICS AND MATERIALS VOLS》 * |
冯亦东 等: "基于SURF特征提取和FLANN搜索的图像匹配搜索", 《图学学报》 * |
宋璐: "基于单目视觉的全景拼接技术研究及安卓平台实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108109112B (en) * | 2018-01-16 | 2021-07-20 | 上海同岩土木工程科技股份有限公司 | Tunnel layout graph splicing parameter processing method based on Sift characteristic |
CN108109112A (en) * | 2018-01-16 | 2018-06-01 | 上海同岩土木工程科技股份有限公司 | A kind of tunnel spread figure splicing parameter processing method based on Sift features |
CN109559275A (en) * | 2018-11-07 | 2019-04-02 | 苏州迈瑞科技有限公司 | A kind of Urine Analyzer MIcrosope image joining method |
CN109559275B (en) * | 2018-11-07 | 2024-05-21 | 深圳迈瑞生物医疗电子股份有限公司 | Microscopic image stitching method of urine analyzer |
CN110689511A (en) * | 2019-09-19 | 2020-01-14 | 华东师范大学 | Optimization method for large-visual-field image splicing path |
CN110689511B (en) * | 2019-09-19 | 2023-02-03 | 华东师范大学 | Optimization method for large-visual-field image splicing path |
CN110599404A (en) * | 2019-09-24 | 2019-12-20 | 陕西晟思智能测控有限公司 | Circuit board microscopic image splicing method and device and information data processing terminal |
CN110738695A (en) * | 2019-10-12 | 2020-01-31 | 哈尔滨工业大学 | image feature point mismatching and removing method based on local transformation model |
CN110738695B (en) * | 2019-10-12 | 2021-08-13 | 哈尔滨工业大学 | Image feature point mismatching and removing method based on local transformation model |
CN110706191B (en) * | 2019-10-14 | 2022-09-20 | 中国空气动力研究与发展中心超高速空气动力研究所 | High-pressure container detection method based on infrared image splicing fusion algorithm |
CN110706191A (en) * | 2019-10-14 | 2020-01-17 | 中国空气动力研究与发展中心超高速空气动力研究所 | High-pressure container detection method based on infrared image splicing fusion algorithm |
CN111105346A (en) * | 2019-11-08 | 2020-05-05 | 同济大学 | Full-scanning microscopic image splicing method based on peak value search and gray template registration |
CN111179170A (en) * | 2019-12-18 | 2020-05-19 | 深圳北航新兴产业技术研究院 | Rapid panoramic stitching method for microscopic blood cell images |
CN111179170B (en) * | 2019-12-18 | 2023-08-08 | 深圳北航新兴产业技术研究院 | Rapid panoramic stitching method for microscopic blood cell images |
CN113012030A (en) * | 2019-12-20 | 2021-06-22 | 北京金山云网络技术有限公司 | Image splicing method, device and equipment |
CN111260561A (en) * | 2020-02-18 | 2020-06-09 | 中国科学院光电技术研究所 | Rapid multi-graph splicing method for mask defect detection |
CN111882484A (en) * | 2020-06-16 | 2020-11-03 | 河北汉光重工有限责任公司 | Servo control method in high-speed seamless image splicing of submersible imaging system |
CN111882484B (en) * | 2020-06-16 | 2024-04-16 | 河北汉光重工有限责任公司 | Servo control method in high-speed seamless image stitching of diving imaging system |
CN112164001A (en) * | 2020-09-29 | 2021-01-01 | 南京理工大学智能计算成像研究院有限公司 | Digital microscope image rapid splicing and fusing method |
CN112164001B (en) * | 2020-09-29 | 2024-06-07 | 南京理工大学智能计算成像研究院有限公司 | Digital microscope image rapid splicing and fusion method |
CN113205457A (en) * | 2021-05-11 | 2021-08-03 | 华中科技大学 | Microscopic image splicing method and system |
Also Published As
Publication number | Publication date |
---|---|
CN107093166B (en) | 2019-07-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107093166A (en) | The seamless joint method of low coincidence factor micro-image | |
US8913848B2 (en) | Microscopic image fusion method based on region growing | |
CN109754377B (en) | Multi-exposure image fusion method | |
CN106650794B (en) | A kind of image bloom removing method influenced by body surface high light reflectivity and system | |
CN104749184B (en) | Automatic optical detection method and system | |
CN103679636B (en) | Based on point, the fast image splicing method of line double characteristic | |
US7058233B2 (en) | Systems and methods for constructing an image having an extended depth of field | |
TWI351654B (en) | Defect detecting device, image sensor device, imag | |
CN106650737B (en) | Automatic image cutting method | |
CN111199524B (en) | Purple edge correction method for image of adjustable aperture optical system | |
CN110647875B (en) | Method for segmenting and identifying model structure of blood cells and blood cell identification method | |
CN103548056B (en) | Image-processing device, image-capturing device, and image-processing method | |
CN105741231B (en) | The skin makeup treating method and apparatus of image | |
CN111931751B (en) | Deep learning training method, target object identification method, system and storage medium | |
CN110264426A (en) | Image distortion correction method and apparatus | |
CN101487838A (en) | Extraction method for dimension shape characteristics of profiled fiber | |
CN107644418A (en) | Optic disk detection method and system based on convolutional neural networks | |
CN106033535A (en) | Electronic paper marking method | |
CN109948393A (en) | A kind of localization method and device of bar code | |
CN110705634B (en) | Heel model identification method and device and storage medium | |
CN111105346A (en) | Full-scanning microscopic image splicing method based on peak value search and gray template registration | |
CN104411229B (en) | Image processing device and image processing method | |
CN105631890B (en) | Picture quality evaluation method out of focus based on image gradient and phase equalization | |
CN115731146A (en) | Multi-exposure image fusion method based on color gradient histogram feature light stream estimation | |
CN109360145A (en) | One kind is based on vortex pulsed infrared thermal image joining 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 |