CN104915956B - Chinese medicine sulfur fumigation discrimination method based on imaging spectrometer and system - Google Patents
Chinese medicine sulfur fumigation discrimination method based on imaging spectrometer and system Download PDFInfo
- Publication number
- CN104915956B CN104915956B CN201510284297.3A CN201510284297A CN104915956B CN 104915956 B CN104915956 B CN 104915956B CN 201510284297 A CN201510284297 A CN 201510284297A CN 104915956 B CN104915956 B CN 104915956B
- Authority
- CN
- China
- Prior art keywords
- chinese medicine
- identified
- wave band
- pixel
- spectrum image
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/49—Analysis of texture based on structural texture description, e.g. using primitives or placement rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10036—Multispectral image; Hyperspectral image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Other Investigation Or Analysis Of Materials By Electrical Means (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a kind of Chinese medicine sulfur fumigation discrimination method and system based on imaging spectrometer, is related to remote sensing technology field, the method includes：S1：Chinese medicine to be identified is obtained in the high spectrum image for presetting wave band, and the spectral index feature to the Chinese medicine to be identified is calculated in the high spectrum image of default wave band according to the Chinese medicine to be identified；S2：Classified to the Chinese medicine to be identified in the high spectrum image of default wave band and the spectral index feature of the Chinese medicine to be identified according to the Chinese medicine to be identified, whether sulfur fumigation is passed through with the determination Chinese medicine to be identified.The present invention classifies to the Chinese medicine to be identified in the high spectrum image of default wave band and the spectral index feature of Chinese medicine to be identified by Chinese medicine to be identified, to improve the precision and efficiency of discriminating.
Description
Technical field
The present invention relates to remote sensing technology field, more particularly to a kind of Chinese medicine sulfur fumigation discriminating side based on imaging spectrometer
Method and system.
Background technology
It is the traditional method of China's processing of crude drugs that sulphur, which smokes Chinese medicine once, is mainly used for insect prevention and moisture-proof, is convenient for medicine
The storage of material reduces medicinal material loss, can also increase color and luster.But it due to will produce sulfur dioxide after sulfur burning, is easy to residual
It stays in medicinal material, long-term use can injure the internal organs such as alimentary canal and respiratory tract and liver, kidney.Therefore, state food drug is supervised
Pipe management board is in 2004 with regard to specially hereafter, being forbidden to use sulphur and smoking Chinese medicine.
Still illegal in this way by many pharmacists at present, traditional discrimination method is to make to smell with one's nose, visually distinguish
With taste.But since some Chinese medicines itself have smell or itself is toxic, so there is prodigious offices for the discrimination method
Sex-limited, the precision and efficiency of discriminating are very low.
Invention content
In order to improve the precision and efficiency of TCD identificafion, the present invention provides a kind of Chinese medicine sulphur based on imaging spectrometer
Stifling discrimination method, the method includes：
S1：Chinese medicine to be identified is obtained in the high spectrum image for presetting wave band, and according to the Chinese medicine to be identified in default wave
The high spectrum image of section calculates the spectral index feature to the Chinese medicine to be identified；
S2：According to the Chinese medicine to be identified in the high spectrum image of default wave band and the spectral index of the Chinese medicine to be identified
Feature classifies to the Chinese medicine to be identified, whether passes through sulfur fumigation with the determination Chinese medicine to be identified.
Optionally, before step S1, the method further includes：
S0：Sample Chinese medicine is obtained in the high spectrum image for presetting wave band, and according to the sample Chinese medicine in default wave band
High spectrum image calculates the spectral index feature to the sample Chinese medicine；
Correspondingly, step S2 is specifically included：
It is special in the high spectrum image of default wave band, the spectral index of the Chinese medicine to be identified according to the Chinese medicine to be identified
Sign, the sample Chinese medicine are in the high spectrum image of default wave band and the spectral index feature of the sample Chinese medicine to described to be identified
Chinese medicine is classified, and whether passes through sulfur fumigation with the determination Chinese medicine to be identified.
Optionally, in step S2, classified to the Chinese medicine to be identified by following formula,
Wherein, K (xi,xj)=μ K1(xi,xj)+(1-μ)K2(x′i,x′j)；
γ is the constant more than 0；J is pixel corresponding with Chinese medicine to be identified；xjIn to be identified
Medicine corresponding pixel values of pixel j on the high spectrum image of default wave band；x′jFor the corresponding spectral index features of pixel j；αiAnd b
To be asked in the high spectrum image of default wave band and the spectral index Feature-solving optimization problem of sample Chinese medicine by sample Chinese medicine
The parameter obtained；μ is the constant in [0,1] section；I is the corresponding pixel of sample Chinese medicine；N is that the corresponding pixel of sample Chinese medicine is total
Number；xiFor sample Chinese medicine on the high spectrum image of default wave band the corresponding pixel values of pixel i；x′iFor the corresponding spectrum of pixel i
Index characteristic；yiWhen pixel i is the Chinese medicine by sulfur fumigation, value is -1；It is without sulfur fumigation in pixel i
When Chinese medicine, value 1；As f (xj)<When 0, then differentiate that pixel j is the Chinese medicine by sulfur fumigation；As f (xj)>When 0, then sentence
Other pixel j is the Chinese medicine without sulfur fumigation.
Optionally, before step S0, the method further includes：
The sample Chinese medicine is obtained in the high spectrum image of all wave bands, calculates the corresponding sky of high spectrum image of each wave band
Between autocorrelation exponent, using the spatial autocorrelation indicators higher than predetermined threshold value wave band as the default wave band.
Optionally, the spectral index is characterized as the spectral index feature of centering drug Physicochemical sense parameters.
The invention also discloses a kind of Chinese medicine sulfur fumigation identification system based on imaging spectrometer, the system comprises：
Data capture unit to be identified, for obtaining Chinese medicine to be identified in the high spectrum image for presetting wave band, and according to institute
It states Chinese medicine to be identified and calculates the spectral index feature to the Chinese medicine to be identified in the high spectrum image of default wave band；
Classification of TCD unit to be identified, for according to the Chinese medicine to be identified in the high spectrum image of default wave band and described
Whether the spectral index feature of Chinese medicine to be identified classifies to the Chinese medicine to be identified, passed through with the determination Chinese medicine to be identified
Sulfur fumigation.
Optionally, the system also includes：
Sample data acquiring unit, for obtaining sample Chinese medicine in the high spectrum image for presetting wave band, and according to the sample
This Chinese medicine calculates the spectral index feature to the sample Chinese medicine in the high spectrum image of default wave band；
Correspondingly, the classification of TCD unit to be identified is additionally operable to the height in default wave band according to the Chinese medicine to be identified
The high spectrum image and institute of spectrum picture, the spectral index feature of the Chinese medicine to be identified, the sample Chinese medicine in default wave band
Whether the spectral index feature for stating sample Chinese medicine classifies to the Chinese medicine to be identified, passed through with the determination Chinese medicine to be identified
Sulfur fumigation.
Optionally, the classification of TCD unit to be identified is additionally operable to classify to the Chinese medicine to be identified by following formula,
Wherein, K (xi,xj)=μ K1(xi,xj)+(1-μ)K2(x′i,x′j)；
γ is the constant more than 0；J is pixel corresponding with Chinese medicine to be identified；xjIn to be identified
Medicine corresponding pixel values of pixel j on the high spectrum image of default wave band；x′jFor the corresponding spectral index features of pixel j；αiAnd b
To be asked in the high spectrum image of default wave band and the spectral index Feature-solving optimization problem of sample Chinese medicine by sample Chinese medicine
The parameter obtained；μ is the constant in [0,1] section；I is the corresponding pixel of sample Chinese medicine；N is that the corresponding pixel of sample Chinese medicine is total
Number；xiFor sample Chinese medicine on the high spectrum image of default wave band the corresponding pixel values of pixel i；x′iFor the corresponding spectrum of pixel i
Index characteristic；yiWhen pixel i is the Chinese medicine by sulfur fumigation, value is -1；It is without sulfur fumigation in pixel i
When Chinese medicine, value 1；As f (xj)<When 0, then differentiate that pixel j is the Chinese medicine by sulfur fumigation；As f (xj)>When 0, then sentence
Other pixel j is the Chinese medicine without sulfur fumigation.
Optionally, the system also includes：
Waveband selection unit calculates each wave band for obtaining the sample Chinese medicine in the high spectrum image of all wave bands
The spatial autocorrelation indicators are higher than the wave band of predetermined threshold value as described in by the corresponding spatial autocorrelation indicators of high spectrum image
Default wave band.
Optionally, the spectral index is characterized as the spectral index feature of centering drug Physicochemical sense parameters.
The present invention is by Chinese medicine to be identified in the high spectrum image of default wave band and the spectral index feature of Chinese medicine to be identified
Classify to the Chinese medicine to be identified, to improve the precision and efficiency of discriminating.
Description of the drawings
Fig. 1 is the flow of the Chinese medicine sulfur fumigation discrimination method based on imaging spectrometer of one embodiment of the present invention
Figure；
Fig. 2 is the structural frames of the Chinese medicine sulfur fumigation identification system based on imaging spectrometer of one embodiment of the present invention
Figure.
Specific implementation mode
With reference to the accompanying drawings and examples, the specific implementation mode of the present invention is described in further detail.Implement below
Example is not limited to the scope of the present invention for illustrating the present invention.
Fig. 1 is the flow of the Chinese medicine sulfur fumigation discrimination method based on imaging spectrometer of one embodiment of the present invention
Figure；Referring to Fig.1, the method includes：
S1：Chinese medicine to be identified is obtained in the high spectrum image for presetting wave band, and according to the Chinese medicine to be identified in default wave
The high spectrum image of section calculates the spectral index feature to the Chinese medicine to be identified；
S2：According to the Chinese medicine to be identified in the high spectrum image of default wave band and the spectral index of the Chinese medicine to be identified
Feature classifies to the Chinese medicine to be identified, whether passes through sulfur fumigation with the determination Chinese medicine to be identified.
Present embodiment is by Chinese medicine to be identified in the high spectrum image of default wave band and the spectral index of Chinese medicine to be identified
Feature classifies to the Chinese medicine to be identified, to improve the precision and efficiency of discriminating.
In the concrete realization, classify to the Chinese medicine to be identified for the ease of realizing, optionally, before step S1,
The method further includes：
S0：Sample Chinese medicine is obtained in the high spectrum image for presetting wave band, and according to the sample Chinese medicine in default wave band
High spectrum image calculates the spectral index feature to the sample Chinese medicine；
When obtaining high spectrum image, usable halogen lamp does light source, to Chinese medicine Uniform Illumination to be identified, using what is built
Imaging spectrometer system alignment medicinal material carries out light spectrum image-forming, at the same by known sulfur fumigation and it is known without it is stifling it is of the same race in
Medicine is placed in same visual field, certainly, can not also be limited to this by other acquisition modes, present embodiment.
Correspondingly, step S2 is specifically included：
It is special in the high spectrum image of default wave band, the spectral index of the Chinese medicine to be identified according to the Chinese medicine to be identified
Sign, the sample Chinese medicine are in the high spectrum image of default wave band and the spectral index feature of the sample Chinese medicine to described to be identified
Chinese medicine is classified, and whether passes through sulfur fumigation with the determination Chinese medicine to be identified.
To further increase the efficiency classified to the Chinese medicine to be identified, optionally, in step S2, pass through following formula pair
The Chinese medicine to be identified is classified,
Wherein, K (xi,xj)=μ K1(xi,xj)+(1-μ)K2(x′i,x′j)；
γ is the constant more than 0；J is pixel corresponding with Chinese medicine to be identified；xjIn to be identified
Medicine corresponding pixel values of pixel j on the high spectrum image of default wave band；x′jFor the corresponding spectral index features of pixel j；αiAnd b
To be asked in the high spectrum image of default wave band and the spectral index Feature-solving optimization problem of sample Chinese medicine by sample Chinese medicine
The parameter obtained；μ is the constant in [0,1] section；I is the corresponding pixel of sample Chinese medicine；N is that the corresponding pixel of sample Chinese medicine is total
Number；xiFor sample Chinese medicine on the high spectrum image of default wave band the corresponding pixel values of pixel i；x′iFor the corresponding spectrum of pixel i
Index characteristic；yiWhen pixel i is the Chinese medicine by sulfur fumigation, value is -1；It is without sulfur fumigation in pixel i
When Chinese medicine, value 1；As f (xj)<When 0, then differentiate that pixel j is the Chinese medicine by sulfur fumigation；As f (xj)>When 0, then sentence
Other pixel j is the Chinese medicine without sulfur fumigation.
Since the wave band number of high spectrum image is more, wavelength cover is wide, but the picture quality of subband is poor,
Serious mistake point can be brought when being classified, and to avoid the problem, need advanced row waveband selection, i.e., to the EO-1 hyperion number of acquisition
According to Geary ' s c values are calculated, the larger wave band of Geary ' s c values, the smaller wave band of retention are removed, and then remove picture quality
The strong wave band of correlation, reduces the redundancy of high-spectral data, plays the role of Data Dimensionality Reduction, optionally, step between difference or wave band
Before S0, the method further includes：
The sample Chinese medicine is obtained in the high spectrum image of all wave bands, calculates the corresponding sky of high spectrum image of each wave band
Between autocorrelation exponent, using the spatial autocorrelation indicators higher than predetermined threshold value wave band as the default wave band.
In present embodiment, the spatial autocorrelation indicators are weighed using Geary ' s c values, and calculation formula is as follows：
Wherein, c Geary ' s c values, m and n are any two pixel on same high spectrum image, cmn=(zm-zn)2,
zmFor the gray value of pixel m, znFor the gray value of pixel n, wmnFor space weight variable, distance is between pixel m and pixel n
When preset value, value 1, otherwise value is 0, σ2For the variance yields of gray scale on the high spectrum image.
Wherein, σ2Calculation formula be：
Wherein, n is the sum of pixel on the high spectrum image,For the average value of gray scale on the high spectrum image.
It should be noted that Geary ' s c values can reflect picture quality, (Geary ' s c values are smaller, and picture quality is got over
It is high；Conversely, picture quality is lower), and to wave band decorrelation.
Differentiate ground accuracy to improve, optionally, the spectral index is characterized as centering drug Physicochemical sense parameters
Spectral index feature, by verifying repeatedly, the spectral index feature can choose 50 kinds, specifically can refer to following table：
Fig. 2 is the structural frames of the Chinese medicine sulfur fumigation identification system based on imaging spectrometer of one embodiment of the present invention
Figure；Reference Fig. 2, the system comprises：
Data capture unit to be identified, for obtaining Chinese medicine to be identified in the high spectrum image for presetting wave band, and according to institute
It states Chinese medicine to be identified and calculates the spectral index feature to the Chinese medicine to be identified in the high spectrum image of default wave band；
Classification of TCD unit to be identified, for according to the Chinese medicine to be identified in the high spectrum image of default wave band and described
Whether the spectral index feature of Chinese medicine to be identified classifies to the Chinese medicine to be identified, passed through with the determination Chinese medicine to be identified
Sulfur fumigation.
Optionally, the system also includes：
Sample data acquiring unit, for obtaining sample Chinese medicine in the high spectrum image for presetting wave band, and according to the sample
This Chinese medicine calculates the spectral index feature to the sample Chinese medicine in the high spectrum image of default wave band；
Correspondingly, the classification of TCD unit to be identified is additionally operable to the height in default wave band according to the Chinese medicine to be identified
The high spectrum image and institute of spectrum picture, the spectral index feature of the Chinese medicine to be identified, the sample Chinese medicine in default wave band
Whether the spectral index feature for stating sample Chinese medicine classifies to the Chinese medicine to be identified, passed through with the determination Chinese medicine to be identified
Sulfur fumigation.
Optionally, the classification of TCD unit to be identified is additionally operable to classify to the Chinese medicine to be identified by following formula,
Wherein, K (xi,xj)=μ K1(xi,xj)+(1-μ)K2(x′i,x′j)；
γ is the constant more than 0；J is pixel corresponding with Chinese medicine to be identified；xjIn to be identified
Medicine corresponding pixel values of pixel j on the high spectrum image of default wave band；x′jFor the corresponding spectral index features of pixel j；αiAnd b
To be asked in the high spectrum image of default wave band and the spectral index Feature-solving optimization problem of sample Chinese medicine by sample Chinese medicine
The parameter obtained；μ is the constant in [0,1] section；I is the corresponding pixel of sample Chinese medicine；N is that the corresponding pixel of sample Chinese medicine is total
Number；xiFor sample Chinese medicine on the high spectrum image of default wave band the corresponding pixel values of pixel i；x′iFor the corresponding spectrum of pixel i
Index characteristic；yiWhen pixel i is the Chinese medicine by sulfur fumigation, value is -1；It is without sulfur fumigation in pixel i
When Chinese medicine, value 1；As f (xj)<When 0, then differentiate that pixel j is the Chinese medicine by sulfur fumigation；As f (xj)>When 0, then sentence
Other pixel j is the Chinese medicine without sulfur fumigation.
Optionally, the system also includes：
Waveband selection unit calculates each wave band for obtaining the sample Chinese medicine in the high spectrum image of all wave bands
The spatial autocorrelation indicators are higher than the wave band of predetermined threshold value as described in by the corresponding spatial autocorrelation indicators of high spectrum image
Default wave band.
Optionally, the spectral index is characterized as the spectral index feature of centering drug Physicochemical sense parameters.
Embodiment of above is merely to illustrate the present invention, and not limitation of the present invention, in relation to the common of technical field
Technical staff can also make a variety of changes and modification without departing from the spirit and scope of the present invention, therefore all
Equivalent technical solution also belongs to scope of the invention, and scope of patent protection of the invention should be defined by the claims.
Claims (8)
1. a kind of Chinese medicine sulfur fumigation discrimination method based on imaging spectrometer, which is characterized in that the method includes：
S1：Chinese medicine to be identified is obtained in the high spectrum image for presetting wave band, and according to the Chinese medicine to be identified in default wave band
High spectrum image is calculated to the Chinese medicine to be identified in the spectral index feature HI of the default wave band, the spectral index feature
HI is calculated by the following formula：
Wherein, ρ534For spectral reflectance values of the Chinese medicine to be identified when the wavelength of default wave band is 534nm, ρ698In to be identified
Spectral reflectance values of the medicine when the wavelength of default wave band is 698nm, ρ704It is in the wavelength for presetting wave band for Chinese medicine to be identified
Spectral reflectance values when 704nm；
S2：According to the Chinese medicine to be identified in the high spectrum image of default wave band and the Chinese medicine to be identified in the default wave band
Spectral index feature HI classify to the Chinese medicine to be identified, it is whether smoked by sulphur with the determination Chinese medicine to be identified
It steams, specifically, is classified to the Chinese medicine to be identified by following formula：
Wherein, K (xi,xj)=μ K1(xi,xj)+(1-μ)K2(x′i,x′j)；
γ is the constant more than 0；J is pixel corresponding with Chinese medicine to be identified；xjFor Chinese medicine to be identified
The corresponding pixel values of pixel j on the high spectrum image of default wave band；x′jFor the corresponding spectral index feature HI of pixel j；αiAnd b
To solve optimization problem in the high spectrum image of default wave band and the spectral index feature HI of sample Chinese medicine by sample Chinese medicine
The parameter acquired；μ is the constant in [0,1] section；I is the corresponding pixel of sample Chinese medicine；N is the corresponding pixel of sample Chinese medicine
Sum；xiFor sample Chinese medicine on the high spectrum image of default wave band the corresponding pixel values of pixel i；x′iFor the corresponding light of pixel i
Spectrum index feature HI；yiWhen pixel i is the Chinese medicine by sulfur fumigation, value is -1；It is smoked without sulphur in pixel i
When the Chinese medicine of steaming, value 1；As f (x)j<When 0, then differentiate that pixel j is the Chinese medicine by sulfur fumigation；As f (xj)>When 0,
Then differentiate that pixel j is the Chinese medicine without sulfur fumigation.
2. the method as described in claim 1, which is characterized in that before step S1, the method further includes：
S0：Sample Chinese medicine is obtained in the high spectrum image for presetting wave band, and according to the sample Chinese medicine in the bloom for presetting wave band
Spectrogram picture calculates the spectral index feature HI of the sample Chinese medicine；
Correspondingly, step S2 is specifically included：
According to the Chinese medicine to be identified the high spectrum image of default wave band, the Chinese medicine to be identified spectral index feature HI,
The sample Chinese medicine is in the high spectrum image of default wave band and the spectral index feature HI of the sample Chinese medicine to described to be identified
Chinese medicine is classified, and whether passes through sulfur fumigation with the determination Chinese medicine to be identified.
3. method as claimed in claim 2, which is characterized in that before step S0, the method further includes：
The sample Chinese medicine is obtained in the high spectrum image of all wave bands, calculates the corresponding space of high spectrum image of each wave band certainly
The index of correlation, the wave band using the spatial autocorrelation indicators higher than predetermined threshold value is as the default wave band.
4. method according to any one of claims 1 to 3, which is characterized in that the spectral index feature HI is to Chinese medicine
The spectral index feature HI of physical chemistry sense parameters.
5. a kind of Chinese medicine sulfur fumigation identification system based on imaging spectrometer, which is characterized in that the system comprises：
Data capture unit to be identified is being preset the high spectrum image of wave band for obtaining Chinese medicine to be identified, and is being waited for according to described
It is special in the spectral index of the default wave band to the Chinese medicine to be identified to differentiate that Chinese medicine is calculated in the high spectrum image of default wave band
HI is levied, the spectral index feature HI is calculated by the following formula：
Wherein, ρ534For spectral reflectance values of the Chinese medicine to be identified when the wavelength of default wave band is 534nm, ρ698In to be identified
Spectral reflectance values of the medicine when the wavelength of default wave band is 698nm, ρ704It is in the wavelength for presetting wave band for Chinese medicine to be identified
Spectral reflectance values when 704nm；
Classification of TCD unit to be identified, in the high spectrum image of default wave band and described waiting reflecting according to the Chinese medicine to be identified
Other Chinese medicine classifies to the Chinese medicine to be identified in the spectral index feature HI of the default wave band, described to be identified with determination
Whether Chinese medicine specifically classifies to the Chinese medicine to be identified by following formula by sulfur fumigation：
Wherein, K (xi,xj)=μ K1(xi,xj)+(1-μ)K2(x′i,x′j)；
γ is the constant more than 0；J is pixel corresponding with Chinese medicine to be identified；xjFor Chinese medicine to be identified
The corresponding pixel values of pixel j on the high spectrum image of default wave band；x′jFor the corresponding spectral index feature HI of pixel j；αiAnd b
To solve optimization problem in the high spectrum image of default wave band and the spectral index feature HI of sample Chinese medicine by sample Chinese medicine
The parameter acquired；μ is the constant in [0,1] section；I is the corresponding pixel of sample Chinese medicine；N is the corresponding pixel of sample Chinese medicine
Sum；xiFor sample Chinese medicine on the high spectrum image of default wave band the corresponding pixel values of pixel i；x′iFor the corresponding light of pixel i
Spectrum index feature HI；yiWhen pixel i is the Chinese medicine by sulfur fumigation, value is -1；It is smoked without sulphur in pixel i
When the Chinese medicine of steaming, value 1；As f (x)j<When 0, then differentiate that pixel j is the Chinese medicine by sulfur fumigation；As f (xj)>When 0,
Then differentiate that pixel j is the Chinese medicine without sulfur fumigation.
6. system as claimed in claim 5, which is characterized in that the system also includes：
Sample data acquiring unit, for obtaining sample Chinese medicine in the high spectrum image for presetting wave band, and according in the sample
Medicine calculates the spectral index feature HI of the sample Chinese medicine in the high spectrum image of default wave band；
Correspondingly, the classification of TCD unit to be identified is additionally operable to the EO-1 hyperion in default wave band according to the Chinese medicine to be identified
Image, the spectral index feature HI of the Chinese medicine to be identified, the sample Chinese medicine are in the high spectrum image of default wave band and described
Whether the spectral index feature HI of sample Chinese medicine classifies to the Chinese medicine to be identified, passed through with the determination Chinese medicine to be identified
Sulfur fumigation.
7. system as claimed in claim 6, which is characterized in that the system also includes：
Waveband selection unit calculates the bloom of each wave band for obtaining the sample Chinese medicine in the high spectrum image of all wave bands
Spectrogram is as corresponding spatial autocorrelation indicators, using the spatial autocorrelation indicators higher than the wave band of predetermined threshold value as described default
Wave band.
8. the system as described in any one of claim 5~7, which is characterized in that the spectral index feature HI is to Chinese medicine
The spectral index feature HI of physical chemistry sense parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510284297.3A CN104915956B (en) | 2015-05-28 | 2015-05-28 | Chinese medicine sulfur fumigation discrimination method based on imaging spectrometer and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510284297.3A CN104915956B (en) | 2015-05-28 | 2015-05-28 | Chinese medicine sulfur fumigation discrimination method based on imaging spectrometer and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104915956A CN104915956A (en) | 2015-09-16 |
| CN104915956B true CN104915956B (en) | 2018-09-28 |
Family
ID=54084994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510284297.3A Active CN104915956B (en) | 2015-05-28 | 2015-05-28 | Chinese medicine sulfur fumigation discrimination method based on imaging spectrometer and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104915956B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103743649A (en) * | 2013-12-31 | 2014-04-23 | 北京大学 | Detection device of ground feature density and rocks based on multi-angle polarization imaging |
| CN103760134A (en) * | 2014-01-27 | 2014-04-30 | 中国中医科学院中药研究所 | Method for identifying performing of sulfur fumigation on traditional Chinese medicine radix angelicae to be detected |
-
2015
- 2015-05-28 CN CN201510284297.3A patent/CN104915956B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103743649A (en) * | 2013-12-31 | 2014-04-23 | 北京大学 | Detection device of ground feature density and rocks based on multi-angle polarization imaging |
| CN103760134A (en) * | 2014-01-27 | 2014-04-30 | 中国中医科学院中药研究所 | Method for identifying performing of sulfur fumigation on traditional Chinese medicine radix angelicae to be detected |
Non-Patent Citations (2)
| Title |
|---|
| 不同试验方法检测硫磺熏蒸枸杞品质对比分析;冯楠 等;《新疆农垦科技》;20150430;第46-48页 * |
| 基于比值导数光谱法的强线性波段特征分析;赵恒谦 等;《红外与毫米波学报》;20131231;第32卷(第6期);第563-568页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104915956A (en) | 2015-09-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DK181217B1 (en) | Method and system for external fish parasite monitoring in aquaculture | |
| TWI669660B (en) | Speckle evaluation device, speckle evaluation method and program | |
| Kyraleou et al. | Changes in tannin composition of Syrah grape skins and seeds during fruit ripening under contrasting water conditions | |
| Marshall et al. | Visual biology of Hawaiian coral reef fishes. II. Colors of Hawaiian coral reef fish | |
| CN108701357A (en) | Equipment, system and method for skin detection | |
| CN105551168B (en) | A kind of method and system of farmland remote sensing monitoring and early warning fire | |
| Ottavian et al. | Data fusion for food authentication: fresh/frozen–thawed discrimination in West African Goatfish (Pseudupeneus prayensis) fillets | |
| Sassone et al. | Multivariate studies of Ipheion (Amaryllidaceae, Allioideae) and related genera | |
| Corona et al. | Chestnut cultivar identification through the data fusion of sensory quality and FT-NIR spectral data | |
| CN104915956B (en) | Chinese medicine sulfur fumigation discrimination method based on imaging spectrometer and system | |
| Li et al. | Burn injury diagnostic imaging device's accuracy improved by outlier detection and removal | |
| Chen et al. | Application of multispectral camera in monitoring the quality parameters of fresh tea leaves | |
| CN110008878B (en) | Anti-fake method for face detection and face recognition device with anti-fake function | |
| Prilianti et al. | Real-time assessment of plant photosynthetic pigment contents with an artificial intelligence approach in a mobile application | |
| CN102042984A (en) | Method and system for evaluating grade of medicinal material | |
| CN114187608A (en) | Face temperature measurement terminal capable of automatically capturing face | |
| Khatiwada et al. | Internal defect detection in fruit by using nir spectroscopy | |
| Nawn et al. | Spectral characterization of tracheal and esophageal tissues using a hyperspectral camera and fiber optic sensors | |
| CN110567908A (en) | Method for identifying traditional Chinese medicinal materials by adopting terahertz time-domain spectroscopy | |
| Raja et al. | Visible iris imaging: A novel imaging solution for improved iris recognition | |
| Zhu et al. | Visible near-infrared (VNIR) reflectance hyperspectral imagery for identifying aflatoxin-contaminated corn kernels | |
| Roberts et al. | Anatomical basis of diverse jaw protrusion directionality in ponyfishes (Family Leiognathidae) | |
| CN104101659A (en) | Hairtail fingerprint spectrum construction method | |
| Hamdan et al. | Redescription of Phalotris labiomaculatus (Serpentes, Dipsadidae, Elapomorphini), with notes on the taxonomic... | |
| KR102636215B1 (en) | Electronic device, method and program for scanning scalp based on image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |