CN108052962A - A kind of Spectral matching algorithm based on improved edit-distance - Google Patents
A kind of Spectral matching algorithm based on improved edit-distance Download PDFInfo
- Publication number
- CN108052962A CN108052962A CN201711227706.1A CN201711227706A CN108052962A CN 108052962 A CN108052962 A CN 108052962A CN 201711227706 A CN201711227706 A CN 201711227706A CN 108052962 A CN108052962 A CN 108052962A
- Authority
- CN
- China
- Prior art keywords
- spectral
- distance
- pigment
- reflectivity
- spectral reflectivity
- 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.)
- Pending
Links
- 230000003595 spectral effect Effects 0.000 title claims abstract description 75
- 239000000049 pigment Substances 0.000 claims abstract description 54
- 238000002310 reflectometry Methods 0.000 claims abstract description 50
- 238000010422 painting Methods 0.000 claims abstract description 26
- 239000003973 paint Substances 0.000 claims abstract description 22
- VTYYLEPIZMXCLO-UHFFFAOYSA-L Calcium carbonate Chemical compound [Ca+2].[O-]C([O-])=O VTYYLEPIZMXCLO-UHFFFAOYSA-L 0.000 claims description 10
- 238000001035 drying Methods 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 229910000019 calcium carbonate Inorganic materials 0.000 claims description 5
- 239000000446 fuel Substances 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 239000000758 substrate Substances 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 2
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 claims 1
- 108010010803 Gelatin Proteins 0.000 claims 1
- 210000000481 breast Anatomy 0.000 claims 1
- 229910052791 calcium Inorganic materials 0.000 claims 1
- 239000011575 calcium Substances 0.000 claims 1
- BVKZGUZCCUSVTD-UHFFFAOYSA-N carbonic acid Chemical compound OC(O)=O BVKZGUZCCUSVTD-UHFFFAOYSA-N 0.000 claims 1
- 229920000159 gelatin Polymers 0.000 claims 1
- 239000008273 gelatin Substances 0.000 claims 1
- 235000019322 gelatine Nutrition 0.000 claims 1
- 235000011852 gelatine desserts Nutrition 0.000 claims 1
- 238000001228 spectrum Methods 0.000 description 20
- 239000011159 matrix material Substances 0.000 description 10
- 238000000034 method Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000003292 glue Substances 0.000 description 2
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 239000004570 mortar (masonry) Substances 0.000 description 2
- 238000004611 spectroscopical analysis Methods 0.000 description 2
- 108091005950 Azurite Proteins 0.000 description 1
- 241000598860 Garcinia hanburyi Species 0.000 description 1
- 241001446187 Kermes Species 0.000 description 1
- YFVOQMWSMQHHKP-UHFFFAOYSA-N cobalt(2+);oxygen(2-);tin(4+) Chemical compound [O-2].[O-2].[O-2].[Co+2].[Sn+4] YFVOQMWSMQHHKP-UHFFFAOYSA-N 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- YQGOJNYOYNNSMM-UHFFFAOYSA-N eosin Chemical compound [Na+].OC(=O)C1=CC=CC=C1C1=C2C=C(Br)C(=O)C(Br)=C2OC2=C(Br)C(O)=C(Br)C=C21 YQGOJNYOYNNSMM-UHFFFAOYSA-N 0.000 description 1
- 229940117709 gamboge Drugs 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- YOBAEOGBNPPUQV-UHFFFAOYSA-N iron;trihydrate Chemical compound O.O.O.[Fe].[Fe] YOBAEOGBNPPUQV-UHFFFAOYSA-N 0.000 description 1
- CXORMDKZEUMQHX-UHFFFAOYSA-N kermesic acid Chemical compound O=C1C2=C(O)C(O)=CC(O)=C2C(=O)C2=C1C=C(O)C(C(O)=O)=C2C CXORMDKZEUMQHX-UHFFFAOYSA-N 0.000 description 1
- FDZZZRQASAIRJF-UHFFFAOYSA-M malachite green Chemical compound [Cl-].C1=CC(N(C)C)=CC=C1C(C=1C=CC=CC=1)=C1C=CC(=[N+](C)C)C=C1 FDZZZRQASAIRJF-UHFFFAOYSA-M 0.000 description 1
- 229940107698 malachite green Drugs 0.000 description 1
- 235000012736 patent blue V Nutrition 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- ANRHNWWPFJCPAZ-UHFFFAOYSA-M thionine Chemical compound [Cl-].C1=CC(N)=CC2=[S+]C3=CC(N)=CC=C3N=C21 ANRHNWWPFJCPAZ-UHFFFAOYSA-M 0.000 description 1
- GWBUNZLLLLDXMD-UHFFFAOYSA-H tricopper;dicarbonate;dihydroxide Chemical compound [OH-].[OH-].[Cu+2].[Cu+2].[Cu+2].[O-]C([O-])=O.[O-]C([O-])=O GWBUNZLLLLDXMD-UHFFFAOYSA-H 0.000 description 1
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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Pure & Applied Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Algebra (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Evolutionary Computation (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
The invention discloses a kind of Spectral matching algorithms based on improved edit-distance, comprise the following steps：1) normal pigment block is made；2) spectral reflectivity of mural painting paint and the spectral reflectivity of normal pigment block are gathered；3) spectral reflectivity of the spectral reflectivity of the mural painting paint obtained using the Spectral matching algorithm of improved edit-distance to step 2) and normal pigment block carries out Spectral matching, the Spectral matching based on improved edit-distance is completed, the Spectral matching result precision of the algorithm is higher.
Description
Technical field
The invention belongs to digital image processing fields, are related to a kind of Spectral matching algorithm based on improved edit-distance.
Background technology
Spectral Matching Technique is exactly by by existing number in measured spectral reflectivity and spectral reflectance data storehouse
According to being compared, the technology of the similitude or otherness between two curves is acquired, which can accurately know on the image
Other pixel.In the pigment material identification of mural painting, by the spectral reflectivity of unknown pigment in mural painting and normal pigment spectroscopic data
The spectral reflectivity of each sample pigment is matched in storehouse, final to obtain one most like with the unknown pigment reflectivity
Spectral reflectivity curve.It is considered that the most matched pigment provided in the feature and library of spectra of this unknown pigment is consistent
, i.e., the corresponding sample pigment of most like reflectance curve is exactly the recognition result of unknown pigment, thus in mural painting
Unknown pigment has carried out more accurate lossless identification, with the fast development of Spectral Matching Technique, has multiple spectrum
It is used for solving practical problems with algorithm, such as：Spectroscopic data codes match algorithm, spectrum angle matching algorithm, spectral information dissipate
Degree method, spectrum similarity mode algorithm etc..However there is the problem of matching result precision is relatively low in matching algorithm.
The content of the invention
The shortcomings that it is an object of the invention to overcome the above-mentioned prior art, provides a kind of light based on improved edit-distance
Matching algorithm is composed, the Spectral matching result precision of the algorithm is higher.
In order to achieve the above objectives, the Spectral matching algorithm of the present invention based on improved edit-distance comprises the following steps：
1) normal pigment block is made；
2) spectral reflectivity of mural painting paint and the spectral reflectivity of normal pigment block are gathered；
3) spectral reflectivity of the mural painting paint obtained using the Spectral matching algorithm of improved edit-distance to step 2)
And the spectral reflectivity of normal pigment block carries out Spectral matching, completes the Spectral matching based on improved edit-distance.
The manufacturing process of step 1) Plays pigment cake is：Block pigment is impregnated with clear water, then by the bright of phase homogenous quantities
Glue is added in clear water, is then ground with mortar, applies one layer of calcium carbonate on the surface of substrate, grid is depicted after drying, then
Fuel after grinding is coated on calcium carbonate, normal pigment block is obtained after drying.
It is anti-by the spectral reflectivity of spectrophotometer acquisition mural painting paint and the spectrum of normal pigment block in step 2)
Penetrate rate.
The concrete operations of step 3) are：
δ del (a), δ ins (a) and δ subs (a, b) 3a) is set to represent deletion a, insertion a respectively and replace a corresponding generations with b
Valency, then in the case where cost is all for l, cost equation is：
It 3b) sets cost equation C (i, j) and represents and A [1 ... i] is changed into cost needed for B [1 ... j], then cost equation C
(i, j) is：
Character string φ there are two 3a) settingmAnd φrn, φm=φ1φ2…φm, φrn=φ1φ2…φrn, construction matching pass
It is matrix, matching relationship matrix is m+2 rows, the matrix of n+2 row；
4a) matching relationship matrix is filled according to formula (3)；
The element in the matching relationship matrix lower right corner is character string φmWith φrnBetween editing distance ld, i.e., by character string
φmChange to character string φrnThe minimum number of Shi Jinhang edit operations；
5a) spectral reflectivity of the spectral reflectivity to mural painting paint and normal pigment block is normalized, by mural painting
The amplitude of the spectral reflectivity of paint and the amplitude of the spectral reflectivity of normal pigment block are limited to section [0,1]；If i-th
The reflectivity of spectrum is M (i), and the corresponding vector of i-th spectrum is S (i), then has
6a) set the decision condition of editing distance as：
Wherein, T is the threshold value adaptively chosen, the amplitude of the spectral reflectivity of mural painting paint and the light of normal pigment block
Compose the absolute value of the difference of reflectivity | φi-φrj|={ X1,X2,……,XK, K is data amount check, and the value of K is m*n, XkFor two
The difference of reflectivity, φiFor the spectral reflectivity of the normal pigment block of standard, φrjFor the spectral reflectivity of mural painting paint；
The tendency that the curve of spectrum is calculated based on editing distance algorithm 7a) is used, given threshold T is bent by spectrum by threshold value T
Line is divided into two groups of different data, one group of two reflectance value unanimous circumstances of expression, and another set represents that two reflected values are inconsistent
Situation, set C0In XiTo be less than the difference of threshold value, set C1The X of the insideiTo be more than the difference of threshold value.
C0={ X1,X2,…,XK}Xi≤T (7)
C1={ Xt+1,Xt+2,…,XN}Xi>T (8)
Every XiThe probability of appearance is pi=1/N.
Belong to C0And C1Class occur probability be respectively：
C0Class and C1Class occur average be：
C0Class and C1Class occur variance be：
It is possible thereby to calculate to obtain C0Class and C1The variance within clusters of classInter-class varianceAnd population varianceRespectively：
WhenWhen maximum, the value of corresponding threshold value T is optimal threshold.
The corresponding curve of spectrum of optimal threshold criterion pigment cake spectral reflectivity and mural painting paint spectral reflectivity
Whether the corresponding curve of spectrum is a kind of curve of substance.
The invention has the advantages that：
Spectral matching algorithm of the present invention based on improved edit-distance is compiled in concrete operations by using improving
The spectral reflectivity for the mural painting paint that the Spectral matching algorithm of volume distance obtains step 2) and the spectrum of normal pigment block are anti-
It penetrates rate and carries out Spectral matching, it is easy to operate to improve the precision of Spectral matching result, it is convenient, to realize wall painting pigment substance
It accurately identifies.
Specific embodiment
The present invention is described in further detail with reference to embodiment：
Spectral matching algorithm of the present invention based on improved edit-distance comprises the following steps：
1) normal pigment block is made；
2) spectral reflectivity of mural painting paint and the spectral reflectivity of normal pigment block are gathered；
3) spectral reflectivity of the mural painting paint obtained using the Spectral matching algorithm of improved edit-distance to step 2)
And the spectral reflectivity of normal pigment block carries out Spectral matching, completes the Spectral matching based on improved edit-distance.
The manufacturing process of step 1) Plays pigment cake is：Block pigment is impregnated with clear water, then by the bright of phase homogenous quantities
Glue is added in clear water, is then ground with mortar, applies one layer of calcium carbonate on the surface of substrate, grid is depicted after drying, then
Fuel after grinding is coated on calcium carbonate, normal pigment block is obtained after drying.
It is anti-by the spectral reflectivity of spectrophotometer acquisition mural painting paint and the spectrum of normal pigment block in step 2)
Penetrate rate.
The concrete operations of step 3) are：
3a) standard of the editing distance between two character strings A and B is defined as：It (including replacing, is inserted into basic operation
And delete) character string A is converted into the minimum operation number needed for B, editing distance is defined as with suitable recursion equation
Cost function deletes a, insertion a and replaces a corresponding generations with b if δ del (a), δ ins (a) and δ subs (a, b) are represented respectively
Valency, then in the case where cost is all for l, cost equation is：
It 3b) sets cost equation C (i, j) and represents and A [1 ... i] is changed into cost needed for B [1 ... j], then cost equation C
(i, j) is：
Character string φ there are two 3c) settingmAnd φrn, φm=φ1φ2…φm, φrn=φ1φ2…φrn, construction matching pass
It is matrix, matching relationship matrix is m+2 rows, the matrix of n+2 row；
4d) matching relationship matrix is filled according to formula (3)；
The element in the matching relationship matrix lower right corner is character string φmWith φrnBetween editing distance ld, i.e., by character string
φmChange to character string φrnThe minimum number of Shi Jinhang edit operations；
5e) spectral reflectivity of the spectral reflectivity to mural painting paint and normal pigment block is normalized, by mural painting
The amplitude of the spectral reflectivity of paint and the amplitude of the spectral reflectivity of normal pigment block are limited to section [0,1]；If i-th
The reflectivity of spectrum is M (i), and the corresponding vector of i-th spectrum is S (i), then has
6f) set the decision condition of editing distance as：
Wherein, T is the threshold value adaptively chosen, the amplitude of the spectral reflectivity of mural painting paint and the light of normal pigment block
Compose the absolute value of the difference of reflectivity | φi-φrj|={ X1,X2,……,XK, K is data amount check, and the value of K is m*n, XkFor two
The difference of reflectivity, φiFor the spectral reflectivity of the normal pigment block of standard, φrjFor the spectral reflectivity of mural painting paint；
The tendency that the curve of spectrum is calculated based on editing distance algorithm 7h) is used, given threshold T is bent by spectrum by threshold value T
Line is divided into two groups of different data, one group of two reflectance value unanimous circumstances of expression, and another set represents that two reflected values are inconsistent
Situation, set C0In XiTo be less than the difference of threshold value, set C1The X of the insideiTo be more than the difference of threshold value.
C0={ X1,X2,…,XK}Xi≤T (7)
C1={ Xt+1,Xt+2,…,XN}Xi>T (8)
Every XiThe probability of appearance is pi=1/N.
Belong to C0And C1Class occur probability be respectively：
C0Class and C1Class occur average be：
C0Class and C1Class occur variance be：
It is possible thereby to calculate to obtain C0Class and C1The variance within clusters of classInter-class varianceAnd population varianceRespectively：
WhenWhen maximum, the value of corresponding threshold value T is optimal threshold.
The corresponding curve of spectrum of optimal threshold criterion pigment cake spectral reflectivity and mural painting paint spectral reflectivity
Whether the corresponding curve of spectrum is a kind of curve of substance.
SAM algorithms, SID algorithms, SCF algorithms and the present invention are compared, and the master sample selected in experimentation is real
Test the existing azurite of room pigment, malachite green, red lead, white clam, bright red, cyanine, eosin, gamboge, sky blue, kermes, ochre and Zhu's fat 12
Kind pigment, pigment to be measured are the pigment cake that oneself makes, and the pigment of selection is existing all 12 kinds of pigment in storehouse, matched
Mode matches between pigment of the same race；It can be seen that by the comparison of above four kinds of algorithms and Spectral matching carried out to pigment of the same race
When, the matching rate sections of SAM algorithms is in 94%-97%, and the matching rate section of SCF algorithms is in 95-98%, the matching of SID algorithms
Rate section is in 96%-98%, and matching rate section of the invention is 98%~100%, and the present invention is matched in each group of pigment
In comparison, matching rate is above other three kinds of algorithms, it can be seen that the ratio of precision classics spectrum of the matching result of the present invention
Matching algorithm is high, and matching result is as shown in table 1：
Table 1
Claims (3)
1. a kind of Spectral matching algorithm based on improved edit-distance, which is characterized in that comprise the following steps：
1) normal pigment block is made；
2) spectral reflectivity of mural painting paint and the spectral reflectivity of normal pigment block are gathered；
3) spectral reflectivity and mark of the mural painting paint obtained using the Spectral matching algorithm of improved edit-distance to step 2)
The spectral reflectivity of quasi- pigment cake carries out Spectral matching, completes the Spectral matching based on improved edit-distance.
2. the Spectral matching algorithm of improved edit-distance according to claim 1, which is characterized in that step 1) Plays face
Material block manufacturing process be：Block pigment with clear water is impregnated with, then the gelatin of phase homogenous quantities is added in clear water, then with breast
Alms bowl is ground, and applies one layer of calcium carbonate on the surface of substrate, grid is depicted after drying, then the fuel after grinding is coated to carbonic acid
On calcium, normal pigment block is obtained after drying.
3. the Spectral matching algorithm of improved edit-distance according to claim 1, which is characterized in that in step 2), pass through
The spectral reflectivity of spectrophotometer acquisition mural painting paint and the spectral reflectivity of normal pigment block.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711227706.1A CN108052962A (en) | 2017-11-29 | 2017-11-29 | A kind of Spectral matching algorithm based on improved edit-distance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711227706.1A CN108052962A (en) | 2017-11-29 | 2017-11-29 | A kind of Spectral matching algorithm based on improved edit-distance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108052962A true CN108052962A (en) | 2018-05-18 |
Family
ID=62121310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711227706.1A Pending CN108052962A (en) | 2017-11-29 | 2017-11-29 | A kind of Spectral matching algorithm based on improved edit-distance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108052962A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020014842A1 (en) * | 2018-07-16 | 2020-01-23 | 深圳达闼科技控股有限公司 | Substance detection method and apparatus, terminal, and readable storage medium |
| CN114279976A (en) * | 2021-12-27 | 2022-04-05 | 北京建筑大学 | Mural soluble salt content detection method based on reflection spectrum |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102879099A (en) * | 2012-08-08 | 2013-01-16 | 北京建筑工程学院 | Wall painting information extraction method based on hyperspectral imaging |
| CN103400151A (en) * | 2013-08-16 | 2013-11-20 | 武汉大学 | Optical remote-sensing image, GIS automatic registration and water body extraction integrated method |
| CN103500343A (en) * | 2013-09-30 | 2014-01-08 | 河海大学 | Hyperspectral image classification method based on MNF (Minimum Noise Fraction) transform in combination with extended attribute filtering |
| CN104036289A (en) * | 2014-06-05 | 2014-09-10 | 哈尔滨工程大学 | Hyperspectral image classification method based on spatial and spectral features and sparse representation |
| CN107392925A (en) * | 2017-08-01 | 2017-11-24 | 西安电子科技大学 | Remote sensing image terrain classification method based on super-pixel coding and convolutional neural networks |
-
2017
- 2017-11-29 CN CN201711227706.1A patent/CN108052962A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102879099A (en) * | 2012-08-08 | 2013-01-16 | 北京建筑工程学院 | Wall painting information extraction method based on hyperspectral imaging |
| CN103400151A (en) * | 2013-08-16 | 2013-11-20 | 武汉大学 | Optical remote-sensing image, GIS automatic registration and water body extraction integrated method |
| CN103500343A (en) * | 2013-09-30 | 2014-01-08 | 河海大学 | Hyperspectral image classification method based on MNF (Minimum Noise Fraction) transform in combination with extended attribute filtering |
| CN104036289A (en) * | 2014-06-05 | 2014-09-10 | 哈尔滨工程大学 | Hyperspectral image classification method based on spatial and spectral features and sparse representation |
| CN107392925A (en) * | 2017-08-01 | 2017-11-24 | 西安电子科技大学 | Remote sensing image terrain classification method based on super-pixel coding and convolutional neural networks |
Non-Patent Citations (1)
| Title |
|---|
| 王建黑: "光谱图像技术在柑橘采摘和采后处理中的应用研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020014842A1 (en) * | 2018-07-16 | 2020-01-23 | 深圳达闼科技控股有限公司 | Substance detection method and apparatus, terminal, and readable storage medium |
| CN114279976A (en) * | 2021-12-27 | 2022-04-05 | 北京建筑大学 | Mural soluble salt content detection method based on reflection spectrum |
| CN114279976B (en) * | 2021-12-27 | 2023-09-19 | 北京建筑大学 | Method for detecting content of soluble salt in wall painting based on reflection spectrum |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111242224B (en) | Multi-source remote sensing data classification method based on unmanned aerial vehicle extraction classification sample points | |
| Ballabeni et al. | Advances in image pre-processing to improve automated 3D reconstruction | |
| CN108052962A (en) | A kind of Spectral matching algorithm based on improved edit-distance | |
| AU2012332053B2 (en) | Determining colour values in hyperspectral or multispectral images | |
| Pichi-Sermolli | An index for establishing the degree of maturity in plant communities | |
| CN108830844A (en) | A kind of facilities vegetable extracting method based on multidate high-resolution remote sensing image | |
| Musicco et al. | Automatic point cloud segmentation for the detection of alterations on historical buildings through an unsupervised and clustering-based Machine Learning approach | |
| Feng et al. | An improved nonlocal sparse unmixing algorithm for hyperspectral imagery | |
| Sun et al. | Middle Jurassic Ginkgo leaves from the Daohugou area, Inner Mongolia, China and their implication for palaeo-CO2 reconstruction | |
| Elfiky et al. | Color constancy using 3D scene geometry derived from a single image | |
| Axelsson et al. | The use of dual-wavelength airborne laser scanning for estimating tree species composition and species-specific stem volumes in a boreal forest | |
| CN106067171B (en) | A kind of high spectrum image essence is decomposed and image partition method | |
| CN113160077B (en) | High-fidelity digital restoration method for color of faded colored mural | |
| CN106952283B (en) | Image partition method and device | |
| Brøns et al. | ‘A lost chapter of ancient art’: archaeometric examinations of panel paintings from Roman Egypt | |
| Liu | Supervised classification and unsupervised classification | |
| CN111091087B (en) | Land coverage extraction algorithm based on multi-view collaborative canonical correlation forest remote sensing image | |
| Lei et al. | Study on the Application of Ganan Hakka Architectural Elements in Modern Architectural Interior Design | |
| Zheng et al. | The method of color element allocation of ornamental plants considering water condition | |
| Hill et al. | Material Choice and Interaction on Brown’s Bo om | |
| Lu et al. | Color constancy using stage classification | |
| CN111008653B (en) | Clustering optimization method for mixed pigment information unmixing | |
| CN110427950A (en) | Purple soil soil image shadow detection method | |
| Sun et al. | Performance Evaluation of Color Descriptors under Illumination Variation | |
| Ranjan et al. | 3-D Material Style Transfer for Reconstructing Unknown Appearance in Complex Natural Materials |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180518 |