CN110307900A - A kind of rebuilding spectrum system and its method for reconstructing based on printing exposure mask - Google Patents
A kind of rebuilding spectrum system and its method for reconstructing based on printing exposure mask Download PDFInfo
- Publication number
- CN110307900A CN110307900A CN201910518708.9A CN201910518708A CN110307900A CN 110307900 A CN110307900 A CN 110307900A CN 201910518708 A CN201910518708 A CN 201910518708A CN 110307900 A CN110307900 A CN 110307900A
- Authority
- CN
- China
- Prior art keywords
- exposure mask
- ink
- printing
- transmission curve
- mask
- 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
- 238000007639 printing Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000001228 spectrum Methods 0.000 title claims abstract description 26
- 230000005540 biological transmission Effects 0.000 claims abstract description 31
- 238000004611 spectroscopical analysis Methods 0.000 claims abstract description 18
- 238000004088 simulation Methods 0.000 claims abstract description 13
- 238000003384 imaging method Methods 0.000 claims abstract description 9
- 239000002356 single layer Substances 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000013211 curve analysis Methods 0.000 claims abstract description 4
- 238000011835 investigation Methods 0.000 claims abstract description 4
- 230000003595 spectral effect Effects 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 12
- 239000003086 colorant Substances 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000010410 layer Substances 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000001568 sexual effect Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 abstract description 2
- 239000000976 ink Substances 0.000 description 42
- 238000009826 distribution Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013138 pruning Methods 0.000 description 2
- 208000011380 COVID-19–associated multisystem inflammatory syndrome in children Diseases 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/12—Generating the spectrum; Monochromators
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/28—Investigating the spectrum
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/28—Investigating the spectrum
- G01J3/2823—Imaging spectrometer
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/12—Generating the spectrum; Monochromators
- G01J2003/1278—Mask with spectral selection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/28—Investigating the spectrum
- G01J2003/283—Investigating the spectrum computer-interfaced
- G01J2003/284—Spectral construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
The invention discloses a kind of rebuilding spectrum systems and its method for reconstructing based on printing exposure mask.System includes camera lens, exposure mask and imaging sensor, and exposure mask is fixed on a sensor, and is printed upon above transparent medium and is formed by multilayer mono ink, and the drop of ink is in random superposition state.The step of method for reconstructing are as follows: (1) establish the simulation model of single layer monochrome mask print;(2) simulation model of secondary colour mask print is established in the ink droplet of printing on transparent media multilayer monochrome using printer head;(3) ink investigation and transmission curve analysis;(4) spectroscopic data S is solved based on the minimum error term E with penalty term;(5) exposure mask made is fixed on a sensor, then acquire coded image;(6) training neural network, reconstruct obtain three-dimensional spectroscopic data.The lightweight of light spectrum image-forming acquisition instrument may be implemented in the present invention, and can reconstruct high-spectral data in a short time.
Description
Technical field
The present invention relates to calculate camera shooting field more particularly to a kind of lightweight Compact spectrum weight based on printing exposure mask
Build system and its method for reconstructing.
Background technique
High spectrum image can provide spectral signature abundant for various Computer Vision Tasks.However, due to EO-1 hyperion
Image Acquisition needs profession and expensive hardware, seriously hinders the extensive use of high spectrum image.
Three-dimensional spectroscopic data is acquired using 2D sensor, spectral Dimensions information and Spatial Dimension information don't fail to be related to
Compromise selection.Although traditional acquisition method based on scanning theory can restore EO-1 hyperion precision, time dimension is sacrificed
Degree, and high-precision displacement holder is needed to cooperate, be not suitable for mobile collection and dynamic acquisition.
Acquisition method based on dispersion generally can be by means of the optical device of the profession customization such as prism and grating by natural light
Dispersion is come, and sacrifices spatial resolution then to obtain spectral Dimensions information, the acquisition system based on the method has prism exposure mask
Formula hyper-spectral data gathering system (PMIS), Computed tomography spectrometer (CTIS), code aperture snapshot optical spectrum imagers
(CASSI) etc..
Reach light by converting the information of different filter plate acquisition different-wavebands based on the spectrum imaging method of filtering
The purpose of acquisition is composed, this method generally requires to sacrifice temporal resolution, and does not accomplish to acquire in real time, can not cope with dynamic scene
Demand, such as combustion field spectrum analysis, tracking etc for task;Such method mainly has fourier spectrometer filter array spectrum
Imager etc..
In recent years, some that the method for spectroscopic data is rebuild using RGB triple channel picture also gradually based on the method for study
Grow up, this provides a kind of thinking for lightweight spectral imaging apparatus, and still, three irrelevant observation bases are not enough to extensive
Spectral details of appearing again feature, that is, the precision of spectral Dimensions have lost significantly.
In addition, existing high-precision light spectrum image-forming sampler generally requires the program of complicated calibration, hardware design is multiple
Miscellaneous, majority needs to customize, and the acquisition method based on coding mode is not often accomplished to take into account spectral resolution and spatial resolution, and
Method for reconstructing real-time based on optimization is not high, greatly limits the extensive use and popularization of spectrum.
Summary of the invention
For the above problems of the prior art, the present invention provides a kind of rebuilding spectrum system based on printing exposure mask
And its method is able to achieve high-precision rebuilding spectrum by designing a kind of compact portable high light spectrum image-forming acquisition instrument.
In order to achieve the above object of the invention, the technical solution that present system uses are as follows:
A kind of rebuilding spectrum system based on printing exposure mask, including camera lens, exposure mask and imaging sensor, wherein exposure mask is solid
It is fixed that the exposure mask is printed upon above transparent medium by multilayer mono ink and is formed on an imaging sensor, the drop of ink be in
Machine overlaying state.
A kind of spectrum reconstruction method based on printing exposure mask of the present invention, includes the following steps:
Step 1, the simulation model for establishing single layer monochrome mask print is covered for the effect of printer emulation printing exposure mask
The transmission matrix L of i-th layer of ink in filmiSimulation model it is as follows:
The randomness for indicating the position of drop centers point is distributed using 0-1, wherein the probability for the point for having ink droplet to be distributed is p,
The shape of ink droplet is indicated using convolution kernel K, the diameter of ink droplet is d, and the transmission curve of single layer exposure mask is* convolution operation, H are indicated
Indicate the length of exposure mask, W indicates that the width of exposure mask, M (H, W, p) indicate the random matrix being distributed with Probability p;
Step 2, it is superimposed in the ink droplet of printing on transparent media multilayer monochrome according to the ink droplet of printing using printer head
Transmission curve later is in the characteristic for multiplying sexual intercourse, establishes the simulation model of secondary colour mask print:
Wherein, l is the number of plies of printing, and T is the transmission curve matrix of exposure mask;
Step 3, ink investigation and transmission curve analysis: the ink of n kind different colours ink is obtained using spectrometric instrument
The spectral transmission curve of dropPearson correlation coefficient ρ is calculated, shown in formula specific as follows:
Wherein timIt is vectorElement, tjmIt is vectorElement;According to the size of correlation coefficient ρ, correlation is selected
The smallest varicolored ink;
Step 4, for the varicolored ink of selection, best observation base is determined according to step 3, that is to say correlation most
The transmission curve of small ink is then based on the minimum error term E with penalty term and solves spectroscopic data S, minimizes error
The calculation formula of item E is as follows:
E=| | ∑ TS-y1+βT2
Wherein, y indicates the observation after being encoded through exposure mask, and β is multiplication term coefficient;Transmission curve is calculated simultaneously
The order of matrix T selects optimal printing scheme according to the degree of saturation of the precision of solution and order;
Step 5, according to the optimal printing scheme of selection, ink is packed into printer, carries out exposure mask according to printing solution
Production;The exposure mask made is fixed on a sensor, in addition carrying out the debugging of system after camera lens, then acquire code pattern
Picture, coded imaging model are as follows:
X=∫λT(H,W,λ)S(H,W,λ)
Wherein, λ is wavelength, and S (H, W, λ) indicates that the spectroscopic data to be rebuild, T (H, W, λ) are the transmission curve square of exposure mask
Battle array T;
Step 6, to database preprocessing, the enhancing screening of spectroscopic data is carried out, training pair is formed, convolutional neural networks
Input is coded image x, is exported as spectroscopic data S;Convolutional neural networks are trained, until model is restrained, obtain one
Trained model;
Step 7, it by the collected coded image of step 5, is input in the trained model of step 6, reconstruct obtains three-dimensional
Spectroscopic data.
The method that the present invention carries out rebuilding spectrum using the exposure mask of preparation, not only may be implemented light spectrum image-forming acquisition instrument
Lightweight, and high order feature ensure that the reconstruction of its spectral details feature, the operations such as changing easily to the beta pruning of network can be with
Realization reconstructs high-spectral data in a short time.
Detailed description of the invention
Fig. 1 is the cyan of Epson ink and the transmission curve after pinkish red superposition in the embodiment of the present invention.
Fig. 2 is the schematic diagram of present invention emulation exposure mask, and Blocked portion is partial enlarged view in figure.Wherein, (a) indicates diameter
For 8 pixel dimensions, print density 10% is 2 kinds using print colors;(b) indicate that diameter is 4 pixel dimensions, printing
Density is 1%, the use of print colors is 7 kinds;(c) indicate that diameter is 4 pixel dimensions, print density 1% uses printing face
Color is 10 kinds.
Fig. 3 is that the present invention is based on the acquisition system schematic drawing of printing exposure mask, 1- camera lens, 2- sensor, 3- exposure masks.
Fig. 4 is the flow chart of spectrum reconstruction method of the present invention.
Specific embodiment
Technical thought of the invention is as follows: under normal circumstances, the ink of colored commercial printer has three colors, six colors, eight colors
Mode.There is the ink of different colours different spectral transmissions to respond.In the micron-scale not, printer head spray ink droplet be with
Machine distribution, different overlapping color lumps, the spectral transmission curve of these verified overlapping block of pixels can be generated in print procedure
Be to original block of pixels it is non-relevant, it is interesting based on this and do not cause concern the phenomenon that, in printing on transparent media multilayer
It can then generate and a large amount of irrelevant freely observe base.Therefore, use multiple random printings consumer grade color printer as
Ink droplet, is repeatedly printed upon on high light transmission medium by auxiliary, makes the exposure mask of one simple and high order, exposure mask is then fixed on biography
On sensor, a kind of simple, low cost EO-1 hyperion coded image Acquisition Scheme is formed.Finally, using convolutional neural networks are based on
The depth decoded model of (Convolutional NeuralNetwork, CNN) obtains an instruction by the study of mass data
The model perfected reconstructs high-spectral data.
The spectra collection and method for reconstructing of the present embodiment specifically comprise the following steps:
Step 1, the ink droplet of printer head printing is explored... (code name for representing ink droplet) superimposed characteristics make
The cyan and the transmission curve after pinkish red superposition that instrument ASD has measured Epson ink are surveyed with professional spectrum point, and
Theoretical curve is calculated using following formula, both discoveries degree of agreement is high (as shown in Figure 1), can be considered as after ink droplet superposition
Transmission curve presentation multiplies sexual intercourse.It is shown below, ink dropletThe transmission response of new ink droplet is generated after superposition
Calculation formula is as follows, wherein indicates dot product;
Step 2, the simulation model of single layer monochrome mask print is established
For the effect of printer emulation printing exposure mask, printing exposure mask simulation model is proposed.Being distributed using 0-1 indicates ink
The randomness of the position of centre point is dripped, wherein the probability for the point for having ink droplet to be distributed uses circle because of the approximate circle distribution of ink droplet for p
Shape convolution kernel K indicates the shape of ink droplet, and the transmission curve of diameter d, this layer areIt is noted that this method is not limited to justify
Shape, convolution kernel can be set to the various shapes for meeting ink droplet.Simulation model such as following formula, wherein * indicate convolution operation, M (H, W,
P) random matrix (only comprising including 0-1, p refers to 1 probability) with probability density for p distribution is indicated:
Step 3, the simulation model of secondary colour mask print is established
Based on the multiplying property rule in step 1, secondary colour exposure mask can regard as by a variety of monochromatic exposure masks repeatedly print as a result,
It that is to say, final exposure mask model such as following formula, l is the number of plies of printing, and T is the transmission curve matrix of exposure mask, final result such as Fig. 2 institute
Show:
Step 4, ink investigation and transmission curve analysis, it is assorted to have investigated eight chromatic ink of Epson dedicated printer, Ling Mei
Ink, Parker ink etc., including magenta, cyan, pale red, shallow blueness, yellow, the colour of loess, pale yellow, green, light green color, purple, it is dark blue,
The blue different colours such as orange, red, orange red, pink.N kind different colours and material are obtained using spectrometric instrument
The spectral transmission curve of inkCalculate Pearson correlation coefficient ρ, shown in formula specific as follows, wherein timBe to
AmountElement, tjmIt is vectorElement.Select correlation the smallest several;
Step 5, for several inks of selection, true printing exposure mask is simulated using the simulation model of step 2 and 3, then
Error term E is minimized based on the least square method with penalty term and solves spectroscopic data S, wherein the calculation formula of E is as follows:
E=| | ∑ TS-y | |1+β||T||2
Y indicates that through the observation after exposure mask coding, β is multiplication term coefficient, is generally set to 10^ (- 3).And at the same time
The order for calculating transmission matrix selects optimal printing scheme according to the degree of saturation of the precision of solution and order, according to the ink investigated
The characteristic of water, final printing solution determine are as follows: marking ink used are as follows: Epson magenta, cyan, yellow, it is Ling Mei purple, green
Color, blue, Parker is red, eight kinds of inks, the printing device used such as orange are three Epson printers, dress inside each print cartridge
A kind of color, Method of printing are to print a kind of ink every time, and print density is set as 1%, every kind two layers of ink printed, printing
Medium is transparent high pass light quantity and on-deformable film, it should be noted that the production of exposure mask may be implemented in the program, but should
Invention is not limited only to this printing solution.
Step 6, equipment debugging is acquired
According to selected optimal printing scheme, the ink selected is packed into printer, is then covered according to printing solution
The production of film 3, the size of exposure mask 3 and the size of sensor are consistent.Before the exposure mask 3 made is fixed on sensor 2, in addition mirror
The debugging of equipment is carried out after first 1, as shown in Figure 3.Acquire coded image.Coded imaging model are as follows:
X=∫λT(H,W,λ)S(H,W,λ)
Step 7, based on the algorithm for reconstructing of CNN.Initially set up multilayer convolutional neural networks, using multiple dimensioned network model or
The existing U-Net of person carries out model optimization, designs the optimization method L of novel spectral Dimensionsλ, such as following formula,
Wherein F is trained neural network.In order to cut down model parameter and scale, the convolution unit in network is used
The Xception module of lightweight substitutes, and carries out beta pruning quantization operation to model with the compression of implementation model parameter.Using now
Some spectra databases, such as the spectroscopic data collection of Columbia University, the colleges and universities such as Harvard, Holland or research institution etc. deliver
Data set, can also voluntarily using profession acquisition equipment gather data.According to the database preprocessing of collection, spectroscopic data is carried out
Enhancing screening, form training pair, input as coded image x, export as spectroscopic data S, be trained, until model is restrained,
Obtain a trained model.
Step 8, the encoded picture practical system acquisition debugged arrived, is input in trained network model, weight
Structure obtains three-dimensional spectroscopic data.
Claims (2)
1. a kind of rebuilding spectrum system based on printing exposure mask, including camera lens, exposure mask and imaging sensor, wherein exposure mask is fixed
On an imaging sensor, the exposure mask is printed upon above transparent medium by multilayer mono ink and is formed, and the drop of ink is in random
Overlaying state.
2. a kind of spectrum reconstruction method based on printing exposure mask, which comprises the steps of:
Step 1, the simulation model for establishing single layer monochrome mask print, for the effect of printer emulation printing exposure mask, in exposure mask
The transmission matrix L of i-th layer of inkiSimulation model it is as follows:
It is distributed the randomness for indicating the position of drop centers point using 0-1, wherein the probability for the point for having ink droplet to be distributed is p, uses
Convolution kernel K indicates the shape of ink droplet, and the diameter of ink droplet is d, and the transmission curve of single layer exposure mask is* convolution operation, H table are indicated
Show the length of exposure mask, W indicates that the width of exposure mask, M (H, W, p) indicate the random matrix being distributed with Probability p;
Step 2, using printer head printing on transparent media multilayer monochrome ink droplet, according to the ink droplet of printing superposition after
Transmission curve be in multiply the characteristic of sexual intercourse, establish the simulation model of secondary colour mask print:
Wherein, l is the number of plies of printing, and T is the transmission curve matrix of exposure mask;
Step 3, ink investigation and transmission curve analysis: the ink droplet of n kind different colours ink is obtained using spectrometric instrument
Spectral transmission curvePearson correlation coefficient ρ is calculated, shown in formula specific as follows:
Wherein timIt is vectorElement, tjmIt is vectorElement;According to the size of correlation coefficient ρ, select correlation the smallest
Varicolored ink;
Step 4, for the varicolored ink of selection, best observation base is determined according to step 3, that is to say that correlation is the smallest
The transmission curve of ink is then based on the minimum error term E with penalty term and solves spectroscopic data S, minimizes error term E's
Calculation formula is as follows:
E=| | ∑ TS-y | |1+β||T||2
Wherein, y indicates the observation after being encoded through exposure mask, and β is multiplication term coefficient;Transmission curve matrix is calculated simultaneously
The order of T selects optimal printing scheme according to the degree of saturation of the precision of solution and order;
Step 5, according to the optimal printing scheme of selection, ink is packed into printer, the production of exposure mask is carried out according to printing solution;
The exposure mask made is fixed on a sensor, in addition carrying out the debugging of system after camera lens, coded image is then acquired, is encoded
Imaging model are as follows:
X=∫λT(H,W,λ)S(H,W,λ)
Wherein, λ is wavelength, and S (H, W, λ) indicates that the spectroscopic data to be rebuild, T (H, W, λ) are the transmission curve matrix T of exposure mask;
Step 6, to database preprocessing, the enhancing screening of spectroscopic data is carried out, training pair, the input of convolutional neural networks are formed
For coded image x, export as spectroscopic data S;Convolutional neural networks are trained, until model is restrained, obtain a training
Good model;
Step 7, it by the collected coded image of step 5, is input in the trained model of step 6, reconstruct obtains three-dimensional spectrum
Data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910518708.9A CN110307900B (en) | 2019-06-15 | 2019-06-15 | Spectral reconstruction system based on printing mask and reconstruction method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910518708.9A CN110307900B (en) | 2019-06-15 | 2019-06-15 | Spectral reconstruction system based on printing mask and reconstruction method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110307900A true CN110307900A (en) | 2019-10-08 |
CN110307900B CN110307900B (en) | 2021-05-11 |
Family
ID=68075851
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910518708.9A Active CN110307900B (en) | 2019-06-15 | 2019-06-15 | Spectral reconstruction system based on printing mask and reconstruction method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110307900B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114474722A (en) * | 2022-01-21 | 2022-05-13 | 芯体素(杭州)科技发展有限公司 | Transparent flexible film surface fine line processing method and device based on 3D printing |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1683164A (en) * | 2004-04-16 | 2005-10-19 | 安捷伦科技有限公司 | Ink and media sensing with a color sensor |
CN106768327A (en) * | 2016-12-06 | 2017-05-31 | 中国科学院光电技术研究所 | Liquid crystal tunable filter imaging spectrum reconstruction method |
CN107655571A (en) * | 2017-09-19 | 2018-02-02 | 南京大学 | A kind of spectrum imaging system obscured based on dispersion and its spectrum reconstruction method |
CN109285132A (en) * | 2018-09-20 | 2019-01-29 | 南京大学 | A kind of spectrum reconstruction method based on Frequency Domain Coding |
-
2019
- 2019-06-15 CN CN201910518708.9A patent/CN110307900B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1683164A (en) * | 2004-04-16 | 2005-10-19 | 安捷伦科技有限公司 | Ink and media sensing with a color sensor |
CN106768327A (en) * | 2016-12-06 | 2017-05-31 | 中国科学院光电技术研究所 | Liquid crystal tunable filter imaging spectrum reconstruction method |
CN107655571A (en) * | 2017-09-19 | 2018-02-02 | 南京大学 | A kind of spectrum imaging system obscured based on dispersion and its spectrum reconstruction method |
CN109285132A (en) * | 2018-09-20 | 2019-01-29 | 南京大学 | A kind of spectrum reconstruction method based on Frequency Domain Coding |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114474722A (en) * | 2022-01-21 | 2022-05-13 | 芯体素(杭州)科技发展有限公司 | Transparent flexible film surface fine line processing method and device based on 3D printing |
CN114474722B (en) * | 2022-01-21 | 2023-12-01 | 芯体素(杭州)科技发展有限公司 | Transparent flexible film surface fine circuit processing method and device based on 3D printing |
Also Published As
Publication number | Publication date |
---|---|
CN110307900B (en) | 2021-05-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Xiong et al. | Hscnn: Cnn-based hyperspectral image recovery from spectrally undersampled projections | |
CN101124462B (en) | A system for multi- and hyperspectral imaging | |
CN109886870A (en) | Remote sensing image fusion method based on binary channels neural network | |
CN107507250A (en) | A kind of complexion tongue color image color correction method based on convolutional neural networks | |
Shrestha et al. | One-shot multispectral color imaging with a stereo camera | |
CN110736542B (en) | Spectral reconstruction method based on RGB value | |
CN107560735A (en) | High-resolution infrared imaging system and method based on compressed sensing | |
CN109285132A (en) | A kind of spectrum reconstruction method based on Frequency Domain Coding | |
US20050182328A1 (en) | System enabling chromaticity measurement in the visible and invisible ranges | |
CN117726550B (en) | Multi-scale gating attention remote sensing image defogging method and system | |
CN106023130A (en) | Gradient filtering and PCA-based unmanned aerial vehicle (UAV) image and multispectral image fusion method | |
CN107064005A (en) | The fast illuminated imaging system and algorithm for reconstructing of a kind of EO-1 hyperion light field | |
CN110307900A (en) | A kind of rebuilding spectrum system and its method for reconstructing based on printing exposure mask | |
CN106895916B (en) | A kind of method that single exposure shooting obtains multispectral image | |
US6885394B1 (en) | Method and apparatus for outputting multi-band image | |
CN110660112B (en) | Drawing spectrum reconstruction method based on special color card and multispectral imaging | |
CN115731191A (en) | Narrow-band spectral imaging method based on neural network | |
CN108399617A (en) | A kind of detection method and device of animal health condition | |
US20200413012A1 (en) | Method for reconstructing a colour image acquired by a sensor covered with a mosaic of colour filters | |
CN107067444A (en) | A kind of spectral gamut mapping method of optimization | |
CN109783973A (en) | A kind of atmospheric visibility calculation method based on image degradation model | |
CN108648186A (en) | Based on primary vision perception mechanism without with reference to stereo image quality evaluation method | |
CN112365559B (en) | Infrared image coloring method for generating countermeasure network based on structural similarity | |
Wei et al. | Rapid hyperspectral imaging system via sub-sampling coding | |
Wood et al. | Minimum perceptible differences in the colour reproduction of photographic prints |
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 |