CN107194424A - A kind of image similar block method for fast searching - Google Patents
A kind of image similar block method for fast searching Download PDFInfo
- Publication number
- CN107194424A CN107194424A CN201710358857.4A CN201710358857A CN107194424A CN 107194424 A CN107194424 A CN 107194424A CN 201710358857 A CN201710358857 A CN 201710358857A CN 107194424 A CN107194424 A CN 107194424A
- Authority
- CN
- China
- Prior art keywords
- image block
- image
- block
- similar
- mrow
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of image similar block method for fast searching, using each pixel and its neighborhood territory pixel, determines the image block corresponding to each pixel；Using the similarity and the gray value of image block of image block in neighborhood, it is determined that representing the characteristic vector of each image block；Uniform down-sampling is carried out by the pixel to entire image, a small-scale thumbnail set of blocks is determined；Using thumbnail set of blocks, construction one represents the K Wei Shu of the image block set, entire image is divided into 9 width subgraphs without overlapping；Using the image block contained by every width subgraph, construction one represents the K Wei Shu of the subgraph, treats search image block, it is determined that image block similar to its in index K dimension trees；It is determined that containing the most subgraph K Wei Shu of similar image block number mesh, it is determined that target subgraph K dimension tree in search out the image block similar to its, the similar image block is the image block similar to image block to be searched, realizes the fast search of similar image block inside image.
Description
Technical field
The present invention relates to image procossing and technical field of computer vision, more particularly to a kind of image similar block fast search
Method.
Background technology
Image procossing is widely used to the fields such as public safety, medical diagnosis, military and national defense and daily life.So
And, limited by imaging device and external environment condition disturbed, image acquired in imaging device usually contain certain noise or
Person's resolution ratio is relatively low, so as to influence the accuracy of subsequent treatment.For this reason, it may be necessary on the premise of image-forming condition is not changed, utilize
Image filtering technology is handled image, to reach the purpose for suppressing noise or increase resolution ratio.
Image itself implies substantial amounts of redundancy, and its form of expression is：Image memory in many similar image blocks, this
A little similar image blocks, which are likely located at same region, may also be distributed in the diverse location of image.Utilize these similar image blocks
Image denoising and super-resolution can be realized.Conventional image filtering technology includes part filter and non local filtering.Local filter
Similitude of the Pohle between pending image block image block adjacent thereto, by being added to the image block in these regional areas
Weight average obtains filtered pixel.Non local filtering is in entire image, to search out all similar to pending image block
Image block, then generate filtered pixel by these image block weighted averages.The treatment effect of part filter is generally poor,
Rather than although part filter effect is better than part filter, computation complexity is very high, and its Calculation bottleneck essentially consists in similar diagram
As the search of block.
The content of the invention
In order to overcome above-mentioned deficiency of the prior art, the present invention provides a kind of image similar block method for fast searching, searched
Suo Fangfa includes：
Step 1：Using each pixel and its neighborhood territory pixel, the image block corresponding to each pixel is determined；
Step 2：Using the similarity and the gray value of image block of image block in neighborhood, it is determined that representing the feature of each image block
Vector；
Step 3：Uniform down-sampling is carried out by the pixel to entire image, a small-scale thumbnail block collection is determined
Close；
Step 4：Using thumbnail set of blocks, construction one represents the K Wei Shu of the image block set, is designated as index K dimensions
Tree；
Step 5：Entire image is divided into 9 width subgraphs without overlapping；
Step 6：Using the image block contained by every width subgraph, construction one represents the K Wei Shu of the subgraph, is designated as subgraph K dimensions
Tree；
Step 7：Search image block is treated, it is determined that image block similar to its in index K dimension trees；
Step 8：It is determined that containing the most subgraph K Wei Shu of similar image block number mesh, referred to as target subgraph K Wei Shu；
Step 9：The image block similar to its, the similar diagram are searched out in target subgraph K dimensions tree determined by step 7
As block is the image block similar to image block to be searched.
Preferably, the image block corresponding to each pixel of the step 1 determines that method is as follows：Each pixel and its 5 × 5 is adjacent
Pixel definition in domain is an image block.
Preferably, the characteristic vector of each image block of the step 2 determines that method is as follows：
(1) each image block contains 25 pixels, is designated as p1,p2,…,p25；
(2) using formula (1) calculate each image block and around it 8 image blocks similarity, be designated as s1,s2,…,s8；
A is control parameter in formula, and P is pending image block, PiFor i-th of image block around P；
(3) similarity of 25 pixels and image block 8 image blocks adjacent thereto of combination image block, and carry out normalizing
Change is handled, and is formed 33 dimensional feature vectors of an expression image block, is designated as PF=(p1,p2,...,p25,s1,s2,...,s8)。
Preferably, the step 3 determines that the method for thumbnail set of blocks is as follows by entire image：From the image upper left corner
1st pixel starts in both the horizontal and vertical directions, every 3 pixel samplings, 1 pixel, the right side until sampling image
Untill inferior horn；It regard the image block using centered on sampled pixel as thumbnail block.
Preferably, described step 4 index K Wei Shu building method is as follows：
(1) to the characteristic vector of all image blocks in thumbnail set of blocks, the side per one-dimensional characteristic is calculated by formula (2)
Difference
V in formulaiIt is characterized value,For the average of the dimensional feature, m is the number of thumbnail block；
(2) the maximum feature dimensions of variance are chosen, and obtain the intermediate value of the dimension；
(3) K Wei Shu root node is used as using the image block corresponding to the intermediate value；
(4) intermediate value calculated using maximum variance feature dimensions, two parts are divided into by thumbnail set of blocks, the dimension
Characteristic value is less than the image block of intermediate value and is located in the left subtree of root node, and the image block that the dimensional feature value is more than intermediate value is then located at root
In the right subtree of node；
(5) to image block contained by the subtree of left and right, above-mentioned steps (2) to (4) are repeated respectively, until thumbnail set of blocks not
Untill energy is subdivided.
Preferably, described step 6 subgraph K Wei Shu building method is as follows：
(1) to the characteristic vector of all images block contained by subgraph, the variance per one-dimensional characteristic is calculated by formula (2)；
(2) the maximum feature dimensions of variance are chosen, and obtain the intermediate value of the dimension；
(3) K Wei Shu root node is used as using the image block corresponding to the intermediate value；
(4) intermediate value calculated using maximum variance feature dimensions, two parts are divided into by all images block contained by subgraph,
The dimensional feature value is less than the image block of intermediate value and is located in the left subtree of root node, and the dimensional feature value is more than the image block then position of intermediate value
In the right subtree of root node；
(5) to image block contained by the subtree of left and right, above-mentioned steps (2) to (4) are repeated respectively, until subgraph image block set not
Untill energy is subdivided.
Preferably, described step 7 index K ties up the determination method of image block similar to image block to be searched in tree such as
Under：
(1) since index K Wei Shu root node, in characteristic vector and tree that image block to be searched is calculated using formula (3)
The similarity of present node characteristic vector
PF is the characteristic vector of image block to be searched, PF in formulaiThe characteristic vector of tree present node is tieed up for K, b joins for control
Number；
(2) for threshold value λ set in advance, if sfi>λ then continues to search in the subtree of the root node of present node
Rope；Otherwise, present node and its all child nodes are regard as the image block similar to image block to be searched.
Preferably, described step 8 target subgraph K Wei Shu determination method is as follows：Statistics is included per stalk figure K dimension trees
Similar image block number mesh, maximum that stalk figure K Wei Shu of the contained number of selection are target subgraph K Wei Shu to be determined.
Preferably, the determination method of image block similar to image block to be searched described step 9 target subgraph K Wei Shu is such as
Under：
(1) since target subgraph K Wei Shu root node, using formula (3) calculate the characteristic vector of image block to be searched with
The similarity of present node characteristic vector in tree；
(2) for threshold value λ set in advance, if sfi>λ then continues to search in the subtree of the root node of present node
Rope；Otherwise, present node and its all child nodes are regard as the image block similar to image block to be searched.
As can be seen from the above technical solutions, the present invention has advantages below：
Image similar block method for fast searching can realize the fast search of similar image block inside image, it is to avoid part
The poor processing effect of filtering, the high technical problem of non local filtering computation complexity.
Brief description of the drawings
In order to illustrate more clearly of technical scheme, it will make simple to the required accompanying drawing used in description below
Introduce on ground, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for ordinary skill
For personnel, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is the flow chart of the present invention；
Fig. 2 is image block and 8 tile location schematic diagrames around it；
Fig. 3 is image uniform down-sampling schematic diagram；
Fig. 4 is K dimension tree construction process schematic diagrames；
Fig. 5 be image it is non-overlapping be divided into 9 width subgraph schematic diagrames.
Embodiment
, below will be with specific to enable goal of the invention, feature, the advantage of the present invention more obvious and understandable
Embodiment and accompanying drawing, the technical scheme that the present invention is protected are clearly and completely described, it is clear that implementation disclosed below
Example is only a part of embodiment of the invention, and not all embodiment.Based on the embodiment in this patent, the common skill in this area
All other embodiment that art personnel are obtained under the premise of creative work is not made, belongs to the model of this patent protection
Enclose.
The present invention provides a kind of image similar block method for fast searching, with reference to Fig. 1 descriptions, the image phase of the embodiment of the present invention
Like block method for fast searching, comprise the following steps：
Step 1：To the given image I containing n pixel, it is by the pixel definition in each pixel and its 5 × 5 neighborhoods
One image block, has n image block, is designated as Pi, (i=1 ..., n)；
Step 2：To arbitrary image block Pi, with reference to Fig. 2 describe adjacent image block between position relationship, utilize formula (4) meter
Calculate it and around it 8 image blocks similarity s1,s2,...,s8,
A is control parameter in formula, and P is pending image block, PiFor i-th of image block around P, by Similarity value s1,
s2,...,s8With image block PiComprising 25 pixel ps1,p2,...,p25It is normalized, obtains an expression image
33 dimensional feature vector PF=(p of block1,p2,...,p25,s1,s2,...,s8)；
Step 3：Described with reference to Fig. 3, since the 1st pixel in the image I upper left corners in both the horizontal and vertical directions,
Every 3 pixel samplings, 1 pixel, untill sampling the lower right corner of image, by the image block centered on sampled pixel
It is used as thumbnail block.
Step 4：To the characteristic vector of all image blocks in thumbnail set of blocks, calculated by formula (5) per one-dimensional characteristic
Variance, choose the maximum feature dimensions of variance and simultaneously calculate its intermediate value,
V in formulaiIt is characterized value,For the average of the dimensional feature, m is the number of thumbnail block, with reference to Fig. 4 descriptions with this
Thumbnail set of blocks is divided into two parts by the image block corresponding to intermediate value as K Wei Shu root node, and the dimensional feature value is small
It is located in the image block of intermediate value in the left subtree of root node, the dimensional feature value is more than the image block of intermediate value then positioned at the right side of root node
In subtree, 1 index K Wei Shu is obtained；
Step 5：With reference to Fig. 5 description, by image I it is non-overlapping be divided into 9 width subgraphs；
Step 6：To the characteristic vector of image block contained by each subgraph, the variance per one-dimensional characteristic is calculated by formula (5), chosen
The maximum feature dimensions of variance simultaneously calculate its intermediate value, and the root section using the image block corresponding to the intermediate value as K Wei Shu is described with reference to Fig. 4
Point, two parts are divided into by thumbnail set of blocks, and the dimensional feature value is less than left subtree of the image block positioned at root node of intermediate value
In, the dimensional feature value is more than the image block of intermediate value and is then located in the right subtree of root node, and 9 stalk figure K Wei Shu are obtained；
Step 7：Since index K Wei Shu root node, characteristic vector and the tree of image block to be searched are calculated using formula (6)
The similarity of middle present node characteristic vector,
PF is the characteristic vector of image block to be searched, PF in formulaiThe characteristic vector of tree present node is tieed up for K, b joins for control
Number, for threshold value λ set in advance, if sfi>λ is then continued search in the subtree of the root node of present node, otherwise will
Present node and its all child nodes are used as the image block similar to image block to be searched；
Step 8：The every stalk figure K dimensions of statistics set included similar image block number mesh, select contained number maximum that
Subgraph K Wei Shu are used as target subgraph K Wei Shu；
Step 9：Since target subgraph K Wei Shu root node, the characteristic vector of image block to be searched is calculated using formula (3)
With the similarity of present node characteristic vector in tree；For threshold value λ set in advance, if sfi>λ is then with present node
Continued search in the subtree of root node；Otherwise, using present node and its all child nodes as similar to image block to be searched
Image block.The similar image block that described step 9 is obtained is the image block similar to image block to be searched.
The foregoing description of the disclosed embodiments, enables professional and technical personnel in the field to realize or using the present invention.
A variety of modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, it is of the invention
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope caused.
Claims (9)
1. a kind of image similar block method for fast searching, it is characterised in that searching method includes：
Step 1：Using each pixel and its neighborhood territory pixel, the image block corresponding to each pixel is determined；
Step 2：Using the similarity and the gray value of image block of image block in neighborhood, it is determined that represent the feature of each image block to
Amount；
Step 3：Uniform down-sampling is carried out by the pixel to entire image, a small-scale thumbnail set of blocks is determined；
Step 4：Using thumbnail set of blocks, construction one represents the K Wei Shu of the image block set, is designated as index K Wei Shu；
Step 5：Entire image is divided into 9 width subgraphs without overlapping；
Step 6：Using the image block contained by every width subgraph, construction one represents the K Wei Shu of the subgraph, is designated as subgraph K Wei Shu；
Step 7：Search image block is treated, it is determined that image block similar to its in index K dimension trees；
Step 8：It is determined that containing the most subgraph K Wei Shu of similar image block number mesh, referred to as target subgraph K Wei Shu；
Step 9：The image block similar to its, the similar image block are searched out in target subgraph K dimensions tree determined by step 7
The as image block similar to image block to be searched.
2. image similar block method for fast searching according to claim 1, it is characterised in that
Image block corresponding to each pixel of step 1 determines that method is as follows：By the pixel in each pixel and its 5 × 5 neighborhoods
It is defined as an image block.
3. image similar block method for fast searching according to claim 1, it is characterised in that
The characteristic vector of each image block of step 2 determines that method is as follows：
(1) each image block contains 25 pixels, is designated as p1,p2,…,p25；
(2) using formula (1) calculate each image block and around it 8 image blocks similarity, be designated as s1,s2,…,s8；
<mrow>
<msub>
<mi>s</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<mo>-</mo>
<mfrac>
<mrow>
<mo>|</mo>
<mo>|</mo>
<mi>P</mi>
<mo>-</mo>
<msub>
<mi>P</mi>
<mi>i</mi>
</msub>
<mo>|</mo>
<msubsup>
<mo>|</mo>
<mn>2</mn>
<mn>2</mn>
</msubsup>
</mrow>
<mi>a</mi>
</mfrac>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
A is control parameter in formula, and P is pending image block, PiFor i-th of image block around P；
(3) similarity of 25 pixels and image block 8 image blocks adjacent thereto of combination image block, and place is normalized
Reason, forms 33 dimensional feature vectors of an expression image block, is designated as PF=(p1,p2,…,p25,s1,s2,…,s8)。
4. image similar block method for fast searching according to claim 1, it is characterised in that
The step 3 determines that the method for thumbnail set of blocks is as follows by entire image：Opened from the 1st pixel in the image upper left corner
Begin in both the horizontal and vertical directions, every 3 pixel samplings, 1 pixel, untill sampling the lower right corner of image；Will
Image block using centered on sampled pixel is used as thumbnail block.
5. image similar block method for fast searching according to claim 1, it is characterised in that
Described step 4 index K Wei Shu building method is as follows：
(1) to the characteristic vector of all image blocks in thumbnail set of blocks, the variance per one-dimensional characteristic is calculated by formula (2)
<mrow>
<mi>&sigma;</mi>
<mo>=</mo>
<msqrt>
<mfrac>
<mrow>
<mi>&Sigma;</mi>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>v</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mover>
<mi>v</mi>
<mo>&OverBar;</mo>
</mover>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
<mi>m</mi>
</mfrac>
</msqrt>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
V in formulaiIt is characterized value,For the average of the dimensional feature, m is the number of thumbnail block；
(2) the maximum feature dimensions of variance are chosen, and obtain the intermediate value of the dimension；
(3) K Wei Shu root node is used as using the image block corresponding to the intermediate value；
(4) intermediate value calculated using maximum variance feature dimensions, two parts are divided into by thumbnail set of blocks, the dimensional feature
Value is located in the left subtree of root node less than the image block of intermediate value, and the image block that the dimensional feature value is more than intermediate value is then located at root node
Right subtree in；
(5) to image block contained by the subtree of left and right, above-mentioned steps (2) to (4) are repeated respectively, until thumbnail set of blocks can not be again
Untill division.
6. image similar block method for fast searching according to claim 1, it is characterised in that
Described step 6 subgraph K Wei Shu building method is as follows：
(1) to the characteristic vector of all images block contained by subgraph, the variance per one-dimensional characteristic is calculated by formula (2)；
(2) the maximum feature dimensions of variance are chosen, and obtain the intermediate value of the dimension；
(3) K Wei Shu root node is used as using the image block corresponding to the intermediate value；
(4) intermediate value calculated using maximum variance feature dimensions, is divided into two parts, the dimension by all images block contained by subgraph
Characteristic value is less than the image block of intermediate value and is located in the left subtree of root node, and the image block that the dimensional feature value is more than intermediate value is then located at root
In the right subtree of node；
(5) to image block contained by the subtree of left and right, above-mentioned steps (2) to (4) are repeated respectively, until subgraph image block set can not be again
Untill division.
7. image similar block method for fast searching according to claim 1, it is characterised in that
The determination method of the image block similar to image block to be searched is as follows in described step 7 index K dimension trees：
(1) since index K Wei Shu root node, using formula (3) calculate image block to be searched characteristic vector and tree in it is current
The similarity of node diagnostic vector
<mrow>
<msub>
<mi>sf</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<mo>-</mo>
<mfrac>
<mrow>
<mo>|</mo>
<mo>|</mo>
<mi>P</mi>
<mi>F</mi>
<mo>-</mo>
<msub>
<mi>PF</mi>
<mi>i</mi>
</msub>
<mo>|</mo>
<msubsup>
<mo>|</mo>
<mn>2</mn>
<mn>2</mn>
</msubsup>
</mrow>
<mi>b</mi>
</mfrac>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
PF is the characteristic vector of image block to be searched, PF in formulaiThe characteristic vector of tree present node is tieed up for K, b is control parameter；
(2) for threshold value λ set in advance, if sfi>λ is then continued search in the subtree of the root node of present node；It is no
Then, present node and its all child nodes are regard as the image block similar to image block to be searched.
8. image similar block method for fast searching according to claim 1, it is characterised in that
Described step 8 target subgraph K Wei Shu determination method is as follows：Statistics is per the included similar image of stalk figure K dimension trees
Block number mesh, maximum that stalk figure K Wei Shu of the contained number of selection are target subgraph K Wei Shu to be determined.
9. image similar block method for fast searching according to claim 1, it is characterised in that
The determination method of image block similar to image block to be searched described step 9 target subgraph K Wei Shu is as follows：
(1) since target subgraph K Wei Shu root node, in characteristic vector and tree that image block to be searched is calculated using formula (3)
The similarity of present node characteristic vector；
(2) for threshold value λ set in advance, if sfi>λ is then continued search in the subtree of the root node of present node；It is no
Then, present node and its all child nodes are regard as the image block similar to image block to be searched.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710358857.4A CN107194424B (en) | 2017-05-19 | 2017-05-19 | A kind of image similar block method for fast searching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710358857.4A CN107194424B (en) | 2017-05-19 | 2017-05-19 | A kind of image similar block method for fast searching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107194424A true CN107194424A (en) | 2017-09-22 |
| CN107194424B CN107194424B (en) | 2019-08-27 |
Family
ID=59874130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710358857.4A Active CN107194424B (en) | 2017-05-19 | 2017-05-19 | A kind of image similar block method for fast searching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107194424B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019214565A1 (en) * | 2018-05-07 | 2019-11-14 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for image searching |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101976256A (en) * | 2010-11-01 | 2011-02-16 | 重庆大学 | Double nearest neighbour first searching method in point feature image registration |
| CN102129451A (en) * | 2011-02-17 | 2011-07-20 | 上海交通大学 | Method for clustering data in image retrieval system |
| CN104182974A (en) * | 2014-08-12 | 2014-12-03 | 大连理工大学 | A speeded up method of executing image matching based on feature points |
| CN104778281A (en) * | 2015-05-06 | 2015-07-15 | 苏州搜客信息技术有限公司 | Image index parallel construction method based on community analysis |
| CN106485651A (en) * | 2016-10-11 | 2017-03-08 | 中国人民解放军军械工程学院 | The image matching method of fast robust Scale invariant |
-
2017
- 2017-05-19 CN CN201710358857.4A patent/CN107194424B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101976256A (en) * | 2010-11-01 | 2011-02-16 | 重庆大学 | Double nearest neighbour first searching method in point feature image registration |
| CN102129451A (en) * | 2011-02-17 | 2011-07-20 | 上海交通大学 | Method for clustering data in image retrieval system |
| CN104182974A (en) * | 2014-08-12 | 2014-12-03 | 大连理工大学 | A speeded up method of executing image matching based on feature points |
| CN104778281A (en) * | 2015-05-06 | 2015-07-15 | 苏州搜客信息技术有限公司 | Image index parallel construction method based on community analysis |
| CN106485651A (en) * | 2016-10-11 | 2017-03-08 | 中国人民解放军军械工程学院 | The image matching method of fast robust Scale invariant |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019214565A1 (en) * | 2018-05-07 | 2019-11-14 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for image searching |
| US11409984B2 (en) | 2018-05-07 | 2022-08-09 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for image searching |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107194424B (en) | 2019-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11120270B2 (en) | Spatiotemporal action detection method | |
| Yan et al. | Single image superresolution based on gradient profile sharpness | |
| US9076234B2 (en) | Super-resolution method and apparatus for video image | |
| CN111126287B (en) | Remote sensing image dense target deep learning detection method | |
| CN105118090B (en) | A kind of point cloud filtering method of adaptive complicated landform structure | |
| CN108510504A (en) | Image partition method and device | |
| CN102005054A (en) | Real-time infrared image target tracking method | |
| CN103455991A (en) | Multi-focus image fusion method | |
| CN113222819B (en) | Remote sensing image super-resolution reconstruction method based on deep convolution neural network | |
| JP7344987B2 (en) | Convolutional neural network construction method and system based on farmland images | |
| CN108665509A (en) | A kind of ultra-resolution ratio reconstructing method, device, equipment and readable storage medium storing program for executing | |
| Wang et al. | FusionGRAM: An infrared and visible image fusion framework based on gradient residual and attention mechanism | |
| CN109785246A (en) | A kind of noise-reduction method of non-local mean filtering, device and equipment | |
| Song et al. | Automatic detection and image recognition of precision agriculture for citrus diseases | |
| CN111105452A (en) | High-low resolution fusion stereo matching method based on binocular vision | |
| CN116977674A (en) | Image matching method, related device, storage medium and program product | |
| Zhu et al. | Multiscale channel attention network for infrared and visible image fusion | |
| CN107194424A (en) | A kind of image similar block method for fast searching | |
| Wu et al. | SAR-DRDNet: A SAR image despeckling network with detail recovery | |
| Zhu et al. | Image interpolation based on non-local geometric similarities | |
| CN105303544A (en) | Video splicing method based on minimum boundary distance | |
| CN116665156A (en) | Multi-scale attention-fused traffic helmet small target detection system and method | |
| Jia et al. | Semantic segmentation of deep learning remote sensing images based on band combination principle: Application in urban planning and land use | |
| CN104299223A (en) | Different-source image matching method based on Gabor coding | |
| CN112149463B (en) | Image processing method and device |
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 |