WO2006019991A2 - Procédé et dispositif de détection multimode - Google Patents
Procédé et dispositif de détection multimode Download PDFInfo
- Publication number
- WO2006019991A2 WO2006019991A2 PCT/US2005/025112 US2005025112W WO2006019991A2 WO 2006019991 A2 WO2006019991 A2 WO 2006019991A2 US 2005025112 W US2005025112 W US 2005025112W WO 2006019991 A2 WO2006019991 A2 WO 2006019991A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- spectrum
- determining
- interest
- area
- unknown substance
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
Definitions
- toxins and/or pathogens are purposely used to inflict harm or damage, they are typically mixed with so-called "masking agents" to conceal their identity. These masking agents are used to trick various detection methods and apparatus to overlook or be unable to distinguish the toxins/pathogens mixed therewith. This is a recurring concern for homeland security where the malicious use of toxins and/or infectious pathogens may disrupt the nation's air, water and/or food supplies. Additionally, certain businesses and industries could also benefit from the rapid and accurate identification of the components of mixtures and materials. One such industry that comes to mind is the drug manufacturing industry, where the identification of mixture composition could aid in preventing the alteration of prescription and non ⁇ prescription drugs.
- WSHM 32000 2 One known method for identifying materials and organic substances contained within a mixture is to measure the absorbance, transmission, reflectance or emission of each component of the given mixture as a function of the wavelength or frequency of the illuminating or scattered light transmitted through the mixture. This, of course, requires that the mixture be separable into its component parts. Such measurements as a function of wavelength or frequency produce a signal that is generally referred to as a spectrum.
- the spectra of the components of a given mixture, material or object i.e., a sample spectra, can be identified by comparing the sample spectra to set a reference spectra that have been individually collected for a set of known elements or materials.
- the set of reference spectra are typically referred to as a spectral library, and the process of comparing the sample spectra to the spectral library is generally termed a spectral library search.
- Spectral library searches have been described in the literature for many years, and are widely used today.
- Spectral library searches using infrared (approximately 750 nm to 100 ⁇ m wavelength), Raman, fluorescence or near infrared (approximately 750 nm to 2500 nm wavelength) transmissions are well suited to identify many materials due to the rich set of detailed features these spectroscopy techniques generally produce.
- the above-identified spectroscopic techniques produce rich fingerprints of the various pure entities, which can be used to identify the component materials of mixtures via spectral library searching.
- the disclosure relates to a method for detecting and classifying an unknown substance comprising the steps of (a) providing a spectrum for each of a predetermined number of reference substances; (b) detecting an area of interest on said unknown substance; (c) targeting said area of interest; (d) determining a spectrum from said area of interest; (e) comparing the determined spectrum with the spectrum of one of the reference substances; and (f) classifying said unknown substance based on the comparison of spectra.
- the disclosure relates to a method for detecting and classifying an unknown substance comprising (a) providing a spectrum for each of a predetermined number of reference substances and determining therefrom a first set of eigenvectors using principal components analysis ("PCA") to thereby determine a first set of reduced reference models; (b) detecting an area of interest on said unknown substance; (c) targeting said area of interest; (d) determining a spectrum from said area of interest and determining therefrom a reduced test spectrum as a function of said first set of eigenvectors; (e) comparing the reference models with the reduced test spectrum; and (f) classifying said unknown substance based on said comparison of reduced spectra.
- PCA principal components analysis
- the disclosure relates to a system for detecting and classifying an unknown substance comprising: (a) means for providing a spectrum for each of a predetermined number of reference substances; (b) means for detecting an area of interest on said unknown substance; (c) means for targeting said area of interest; (d) means for determining a spectrum from said area of interest; (e) means for comparing the determined spectrum with the spectrum of one of the reference substances; and (f) means for classifying said unknown substance based on the comparison of spectra.
- the disclosure relates to A system for detecting and classifying an unknown substance comprising (a) means for providing a spectrum for
- WSHM 32000.2 each of a predetermined number of reference substances and determining therefrom a first set of eigenvectors using principal components analysis ("PCA") to define a first set of reduced reference models;
- PCA principal components analysis
- means for detecting an area of interest on said unknown substance means for targeting said area of interest;
- e means for comparing the reference models with the second reduced spectrum; and
- FIG. 1 is an exemplary detection diagram according to one embodiment of the disclosure
- Fig. 2 provides an exemplary algorithm for targeting a region of interest likely to provide a quality test spectrum
- Fig. 3 is an exemplary algorithm for computing the distance represented by a sample from each known class in the library
- Fig. 4 is an exemplary algorithm for spectral unmixing
- Fig. 5 shows a method for determining eigenvectors from reference spectra according to one embodiment of the disclosure
- Fig. 6 A shows an exemplary method for creating class models from the reference spectra and eigenvectors
- Fig. 6B shows a principal component scatter plot for the model of Fig. 6A.
- Fig. 7 schematically shows a method for mapping an unknown spectrum to PC space according to one embodiment of the disclosure.
- the instant disclosure relates to a method and apparatus for implementing multi-modal detection. More specifically, the disclosure relates to a method and apparatus configured to examine and identify an unknown substance.
- the unknown substance may include a chemical substance, a biological material or a combination of the chemical and biological material.
- the unknown substance may also contain a combination of toxic, hazardous and inert material in a physical mixture.
- An apparatus includes one or more detection probes or sensors in communication with an illumination source and a controller mechanism.
- the sensors can be devised to receive spectral and other attributes of the sample and communicate said information to the controller.
- the controller may include one or more processors in communication with a database for storing spectral library or other pertinent information for known samples.
- the processor can be programmed with various detection algorithms defining instructions for identification of the unknown sample.
- Fig. 1 is an exemplary detection algorithm according to one embodiment of the disclosure.
- Flow diagram 100 defines an algorithm for implementing a series of instructions on a processor.
- the detection algorithm 100 defines pre- computation parameters stored in a library.
- the pre- computation parameters may include assembling a library of known samples.
- the library may include, for example, a spectral library or a training set.
- the library includes entire optical, UV and Raman images of known substances and biological material.
- step 1 10 may also include defining additional parameters such as shape, size, color or the application of a pattern recognition software. If one of the contemplated modes is UV fluorescence,
- step 1 10 may include storing fluorescence spectra directed to identifying the UV signature of known substances including biological substances. If one of the contemplated modes is Raman imaging, then step 1 10 may further include storing Raman parameters (i.e., spectra) of various known substances.
- Raman parameters i.e., spectra
- the disclosure relates to reducing complex datasets to a more manageable dataset by instituting principal component analysis ("PCA") techniques.
- PCA principal component analysis
- the PCA analysis allows storing the most pertinent (alternatively, a reduced number of data points) in the library. Stated differently, PCA can be used to extract features of the data that may contribute most to variability.
- PCA eigenvectors tractable storage of class variability can substantially reduce the volume of stored data in the library. While the PCA eigenvectors are not identifiers per se, they allow tractable storage of class variability. They are also a key component of subspace-based detectors.
- the information in the library is dependent on the type of classifier used.
- a classifier can be any arbitrary parameter that defines one or more attribute of the stored data.
- the Mahalanobis classifier requires the average reduced spectrum and covariance matrix for each type of material, or class, in the library.
- a class can be an a priori assignment of a type of known material. For example, using an independently validated sample of material, one can acquire spectral data and identify the data as belonging to material from that sample. Taking multiple spectra from multiple samples from such a source, one can create a class of data for the classification problem.
- the multimodal library can store training data.
- the training algorithm typically includes pure component material data and instructions for extracting applicable features therefrom.
- the applicable features may include: optical imaging, morphological features (i.e., shape, color, diameter, area, perimeter), UV fluorescence (including full spectral signatures), Raman dispersive spectroscopy and Raman imaging (including full spectral signatures).
- the data can be reduced to eigenvectors to describe the variability inherent within the material and represent reduced dimensional subspaces for later detection and identification.
- step 1 10 includes: (a) defining the overall PCA space; (b) defining the so-called confusion areas; (c) defining classes and subclasses in the same PCA space (compute model parameters); (d) defining sub-spectral bands (e.g., CH-bands and other common fingerprints); (e) computing threat morphological features.
- the first step is to narrow the field of view ("FOV") of the detection probe to the sub-regions of the sample containing the most pertinent information.
- the sub-regions may include portions of the sample containing toxic chemical or adverse biological material.
- step 120 of Fig. 1 is labeled targeting.
- time is of the essence.
- the FOV and the time to identify are related to the spectral signal to noise ratio ("SNR") achievable. Higher SNR can be obtained from interrogating regions containing high amounts of suspect materials, so total acquisition time is reduced by carefully determining specific interrogation regions.
- SNR signal to noise ratio
- the disclosure relates to identifying those candidate regions using rapid sensors.
- the FOV selection of specific candidate regions defines targeting.
- targeting is reduced to a multi-tiered approach whereby each tier eliminates objects that do not exhibit properties of the target.
- targeting may include optical imaging and UV fluorescence imaging.
- optical imaging the sample is inspected for identifying target substances having particular morphology features.
- UV fluorescence imaging the target may be a biological material that fluoresces once illuminated with the appropriate radiation source. If multiple sensors are used, each sensor can be configured for a specific detection. If on the other hand, a
- each sensor modality can have characteristics that lend itself to either targeting or identification.
- Table 1 shows exemplary sensors characteristics.
- the optical imaging mode can recognize potential threat material via morphological features while UV Fluorescence imaging is sensitive to biological material. Combining the results of the two modes can result in identifying locations containing biological material that exhibits morphological properties of bio-threat or hazardous agents.
- step 130 of Fig. 1 the algorithm calls for targeting the sample.
- the FOV is narrowed to one ore more target regions and each region is examined to identify its composition.
- the testing step may include Raman acquisition.
- the Raman acquisition algorithm can be configured to operate with minimal operator input. Eventual bio-threat detection systems can be fully automated to ensure that the test spectrum is suitable for the detection process. Because detection probability
- WSHU 32000 2 depends highly on the test spectrum's signal-to-noise ratio ("SNR"), the system can be programmed to ignore any spectra falling below a pre-defined threshold. In one exemplary embodiment, SNR of about 20 is required for accurate detection. The SNR determination can be based on examining the signal response in CH-regions as compared to a Raman-empty (i.e., noise-only) region. If the target spectrum readily matches that of a known substance, then the target identification task is complete and the system can generate a report. If on the other hand, the target spectrum is not defined by the pre- computed parameters, then it can be mapped into PCA space for dimension reduction and outlier detection (see step 140 in Fig. 1). Outlier detection involves determining if the spectrum is significantly different from all classes to indicate a possible poor acquisition or the presence of an unknown material.
- SNR signal-to-noise ratio
- LDA linear discriminant analysis
- AMF adaptive matched filter classifiers
- AMSD adaptive matched subspace detectors
- OSP orthogonal subspace
- a heuristic method is used to identify and to compare the dispersive test spectrum with each candidate class and choose the class closest to the test spectrum by measuring the minimum distance measured with a known metric.
- One such computational metric is derived from Euclidean geometry. The Euclidian distance (or minimum Euclidean distance) compares two vectors of length n by:
- x and y are two full-length spectral vectors.
- the distance d E is calculated for the test spectrum against the average spectrum of each training classes along with each spectrum in a comprehensive spectral library comprised of a single spectrum per class (see step 1 10). If the minimum Euclidean distance (d E ) results in a unique match that is one of the full training classes, it may be reported as the identity of the sample. On the other hand, if the minimum Euclidean distance does not match one of the training classes, the Mahalanobis distance can be used next to further identify the sample.
- the Mahalanobis metric can be viewed as an extension of Euclidean distance which considers both the mean spectrum of a class and the shape, or dispersion of each class. The dispersion information is captured in the covariance matrix C and the distance value can be calculated as follows:
- Equation (2) An advantage of estimating the Mahalanobis distance, d M , is that it accounts for correlation between different features and generates curved or elliptical boundaries between classes. In contrast, the Euclidean distance, d E , only provides spherical boundaries that may not accurately describe the data-space.
- C is the covariance matrix that is defined for each class from the eigenvector PCA value.
- the training library defines a set of mean vectors and covariance matrices derived from the PCA eigenvectors of each class. In addition to checking for minimum distance, one embodiment the disclosure determines whether the test spectrum lies in the so-called confusion region of overlapping classes.
- the mean vector and covariance matrix define a hyper-ellipse with dimensions equal to the number of eigenvectors stored for each model.
- ellipses can be drawn around the 2- ⁇ confidence interval about the mean for each class. If the test spectrum (represented by a point in the principal component space (PC space) lies within the 2- ⁇ interval (for each projection) it is likely a member of that class. Thus, the overlap regions can be clearly seen, and if a test
- WSHM 32000 2 spectrum is a member of more than one class, the spectrum is likely a mixture of more than one component.
- an imaging channel and a spectral unmixing algorithms are used to identify the contents of the mixture.
- the specified spectral unmixing algorithm is capable of determining the constituents of a mixed spectrum and their level of purity or abundance. Thus, when a unique class is not determined from a dispersive spectrum through Mahalanobis distance calculation, spectral unmixing can be used.
- An exemplary unmixing algorithm is disclosed in PCT Application No. PCT/US2005/013036 filed April 15, 2005 by the assignee of the instant application, the specification of which is incorporated herein in its entirety for background information.
- Ramanomics defines a spectrum according to its biochemical composition. More specifically, Ramanomics determines whether the composition is composed of proteins, lipids or carbohydrates and the percent of each component in the composition. According to one embodiment, the constituent amounts are estimated by comparing the input spectrum to spectra from each of the constituents.
- a report is generated to identify the sample's composition.
- the results may include a unique class, a list of overlapping classes, a pure non-library class or the presence of an outlier component. If a unique class is identified, the results may include a corresponding confidence interval obtained based on Euclidean or Mahalanobis distance values.
- Fig. 2 provides an exemplary algorithm for target testing of the spectrum.
- step 210 of Fig. 2 a test is conducted to assess validity of the spectrum. As stated, this
- WSHM 32000.2 can be accomplished by comparing the sample's spectrum against a pre-defined threshold or baseline.
- the sample's spectra is mapped into the Euclidean space. This can be done, for example by determining d E according to equation (1). Once mapped into the Euclidean space, the distance can be tested against library classes not defined by pre- compute parameters (see step 1 10, Fig. 1). If the distance d E is not defined by the library of parameter, then the sample under test can represent a unique material. Should this be the case, the result can be reported as shown in step 240. If the d E does not represent a unique material (step 230) then its spectra can be mapped into PCA space (step 250) for dimension reduction (step 260) and for outlier detection (step 270). Dimension reduction can be accomplished through conventional PCA techniques.
- the sample is determined to be an outlier, then its spectra can be saved for review.
- Ramanomics can be used to further determine whether the sample is a mixture. If the sample is not a mixture then it can be identified as a new class of material.
- Fig. 3 is an exemplary algorithm for computing the distance represented by a sample from each known class in the library.
- a statistical test is performed for each class of material identified within the sample. The statistical test may determine whether the material is a unique material (see step 320). If the material is unique, then it can be reported immediately according to step 320. If the statistical test shows that the material is not unique, then it must be determined whether the sample result is within the confusion region (step 340).
- the statistical test can be Euclidean Distance, Mahalanobis Distance, or other similar distance metrics. Subspace detection methods use hypothesis testing and generalized likelihood tests to assess similarity,
- the various subclasses, stored in the library are assessed to determine whether the sample belongs to any such subclass.
- a method of orthogonal detection can be
- the orthogonal detection consists of performing wide- field Raman imaging on the region to derive a spectral signature for each pixel in a spectral image. These spatially-localized spectra are then classified individually to produce a classified Raman image.
- step 350 If the material is within a confusion region (step 350), then one or more of the following steps can be implemented: (1) check the fiber array spectra; (2) apply spectral unmixing; (3) conduct orthogonal detection and Raman imaging of the sample; and (4) save the results for review.
- the dispersive Raman detector produces an average signal taken over a spatial FOV by combining signals from a set of optical fibers. By examining the individual fibers and their corresponding signals, one embodiment of the disclosure obtains more local spectral estimates from points within the FOV. These local spectra are more likely to be pure component estimates than the overall average dispersive spectrum.
- the step of conducting Raman imaging can be implemented because dispersive spectroscopy integrates the Raman signal over an entire FOV. Thus, if more than one material occupies the FOV, the spectrum will be a mixture of all those components.
- One solution is to increase the spatial resolution of the sensor.
- a wide-field Raman imaging system is employed. If a suspected target arises from the dispersive analysis, Raman imaging can isolate the target component. In this manner, Mahalanobis distance test can be performed on each spectrum in the Raman image.
- the algorithm can check the fiber array spectra (or nominal mixture spectra) to determine whether the sample defines a mixture. If so, a spectral unmixing algorithm can be implemented to determine its components and their amounts. Further orthogonal
- WSHM 32000.2 detection can also be implemented at this stage through Raman imaging to further the analysis.
- step 370 the results are reported to the operator.
- spectral unmixing can be implemented.
- Fig. 4 is an exemplary algorithm for spectral unmixing if Mahalanobis sequence fails to identify the sample's composition. Assuming that the spectral unmixing is unsuccessful, step 410 of Fig. 4 calls for further testing to determine the purity of the initial test spectrum. Purity assessment involves examining the intermediate results from spectral unmixing to assess the correlation of the spectrum with all the library entries and combinations of library entries.
- Fig. 5 shows a method for determining eigenvectors according to one embodiment of the disclosure.
- class 1 several reference spectrum are shown as class 1 through class 4.
- Each class defines a unique spectra which is the fingerprint of the material it represents.
- classes 1-4 can be represented as eigenvectors, schematically shown as matrix 540. This information can be stored in the library as discussed in reference to step 1 10 of Fig. 1.
- Fig. 6A shows an exemplary method for creating class models from the reference spectra and eigenvectors.
- the reference spectra are multiplied by the eigenvectors to transform the spectra into a form suitable for inclusion as Mahalanobis models 620.
- Fig. 6B shows a principal component scatter plot for the model of Fig. 6A.
- each dot represents a spectrum in PC space.
- principal component 1 (PCl) is plotted on the X-axis
- principal component 2 (PC2) is plotted on the Y- axis.
- PCl captures the most of the variability among the spectra, as seen by the separation of the classes in the PCl dimension.
- the ellipses around the classes represent the 2- ⁇ intervals accounting for approximately 95% of the likelihood of class membership.
- Fig. 7 schematically shows a method for mapping an unknown spectrum to PC space according to one embodiment of the disclosure.
- an unknown sample's spectrum is shown as spectrum 710.
- the unknown spectrum is reduced to eigenvectors in step 720 and a mean reduced spectrum 730 is obtained therefrom.
- the mean reduced spectrum is compared with models existing in the library by mapping the known mean reduced spectrum into PC space. Depending on the location of the known mean reduced spectrum in the PC space and its proximity to the closest known class, the unknown sample can be identified.
- Fig. 7 illustrates this concept.
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Chemical & Material Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Theoretical Computer Science (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/632,471 US7679740B2 (en) | 2005-07-14 | 2005-07-14 | Method and apparatus for multimodal detection |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US58821204P | 2004-07-15 | 2004-07-15 | |
US60/588,212 | 2004-07-15 | ||
US59113204P | 2004-07-26 | 2004-07-26 | |
US60/591,132 | 2004-07-26 |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2006019991A2 true WO2006019991A2 (fr) | 2006-02-23 |
WO2006019991A3 WO2006019991A3 (fr) | 2008-07-31 |
Family
ID=35907918
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2005/025112 WO2006019991A2 (fr) | 2004-07-15 | 2005-07-14 | Procédé et dispositif de détection multimode |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2006019991A2 (fr) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7990532B2 (en) | 2007-01-16 | 2011-08-02 | Chemimage Corporation | Method and apparatus for multimodal detection |
US8054454B2 (en) | 2005-07-14 | 2011-11-08 | Chemimage Corporation | Time and space resolved standoff hyperspectral IED explosives LIDAR detector |
US8368880B2 (en) | 2005-12-23 | 2013-02-05 | Chemimage Corporation | Chemical imaging explosives (CHIMED) optical sensor using SWIR |
EP2517136A4 (fr) * | 2009-12-23 | 2017-03-22 | The Governors of the University of Alberta | Sélection de caractéristiques automatisée, objective et optimisée en modélisation chimiométrique (résolution d'amas) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5606164A (en) * | 1996-01-16 | 1997-02-25 | Boehringer Mannheim Corporation | Method and apparatus for biological fluid analyte concentration measurement using generalized distance outlier detection |
US6075891A (en) * | 1998-07-06 | 2000-06-13 | General Dynamics Government Systems Corporation | Non-literal pattern recognition method and system for hyperspectral imagery exploitation |
US6421553B1 (en) * | 1998-12-23 | 2002-07-16 | Mediaspectra, Inc. | Spectral data classification of samples |
WO2004058058A1 (fr) * | 2002-12-30 | 2004-07-15 | Koninklijke Philips Electronics N.V. | Appareil et procede d'analyse |
US20050137806A1 (en) * | 2003-07-18 | 2005-06-23 | Cytokinetics, Inc. A Delaware Corporation | Characterizing biological stimuli by response curves |
-
2005
- 2005-07-14 WO PCT/US2005/025112 patent/WO2006019991A2/fr active Search and Examination
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5606164A (en) * | 1996-01-16 | 1997-02-25 | Boehringer Mannheim Corporation | Method and apparatus for biological fluid analyte concentration measurement using generalized distance outlier detection |
US6075891A (en) * | 1998-07-06 | 2000-06-13 | General Dynamics Government Systems Corporation | Non-literal pattern recognition method and system for hyperspectral imagery exploitation |
US6421553B1 (en) * | 1998-12-23 | 2002-07-16 | Mediaspectra, Inc. | Spectral data classification of samples |
WO2004058058A1 (fr) * | 2002-12-30 | 2004-07-15 | Koninklijke Philips Electronics N.V. | Appareil et procede d'analyse |
US20050137806A1 (en) * | 2003-07-18 | 2005-06-23 | Cytokinetics, Inc. A Delaware Corporation | Characterizing biological stimuli by response curves |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8054454B2 (en) | 2005-07-14 | 2011-11-08 | Chemimage Corporation | Time and space resolved standoff hyperspectral IED explosives LIDAR detector |
US8368880B2 (en) | 2005-12-23 | 2013-02-05 | Chemimage Corporation | Chemical imaging explosives (CHIMED) optical sensor using SWIR |
US7990532B2 (en) | 2007-01-16 | 2011-08-02 | Chemimage Corporation | Method and apparatus for multimodal detection |
EP2517136A4 (fr) * | 2009-12-23 | 2017-03-22 | The Governors of the University of Alberta | Sélection de caractéristiques automatisée, objective et optimisée en modélisation chimiométrique (résolution d'amas) |
Also Published As
Publication number | Publication date |
---|---|
WO2006019991A3 (fr) | 2008-07-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7679740B2 (en) | Method and apparatus for multimodal detection | |
US7990532B2 (en) | Method and apparatus for multimodal detection | |
Muro et al. | Forensic body fluid identification and differentiation by Raman spectroscopy | |
US11158049B2 (en) | Methods and systems for assessing histological stains | |
US20120134582A1 (en) | System and Method for Multimodal Detection of Unknown Substances Including Explosives | |
Takamura et al. | Soft and robust identification of body fluid using Fourier transform infrared spectroscopy and chemometric strategies for forensic analysis | |
CN108254351B (zh) | 用于物品查验的拉曼光谱检测方法 | |
EP3005293B1 (fr) | Separation de couleurs physiologiquement plausibles adaptative d'image | |
US7409299B2 (en) | Method for identifying components of a mixture via spectral analysis | |
US10360995B2 (en) | System and method for partitioning chemometric analysis | |
US11721427B2 (en) | Computational pathology approach for retrospective analysis of tissue-based companion diagnostic driven clinical trial studies | |
CA2447888A1 (fr) | Modele pour donnees spectrales et chromatographiques | |
US20120140981A1 (en) | System and Method for Combining Visible and Hyperspectral Imaging with Pattern Recognition Techniques for Improved Detection of Threats | |
CN108398416A (zh) | 一种基于激光拉曼光谱的混合物成分测定方法 | |
JP6295474B2 (ja) | 分光学的探索アプリケーションにおいて対象の標準物質をタグ付けする方法 | |
KR101634792B1 (ko) | 초분광 영상의 분광혼합분석에 의한 표적물질 탐지방법 | |
WO2018157387A1 (fr) | Détection d'anomalie pour des échantillons médicaux dans de multiples réglages | |
US7792321B2 (en) | Hypersensor-based anomaly resistant detection and identification (HARDI) system and method | |
CN109190714A (zh) | 基于深度机器学习模型实现拉曼信号鉴别的系统及方法 | |
WO2006019991A2 (fr) | Procédé et dispositif de détection multimode | |
Green et al. | Performance characterization of a combined material identification and screening algorithm | |
US7672813B2 (en) | Mixed statistical and numerical model for sensor array detection and classification | |
US20120041689A1 (en) | System and method for particle detection in spectral domain | |
Kiltz et al. | Revised benchmarking of contact-less fingerprint scanners for forensic fingerprint detection: challenges and results for chromatic white light scanners (CWL) | |
Eversole | Point detection of threat aerosols: basic considerations and status |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A2 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KM KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NG NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SM SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A2 Designated state(s): BW GH GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LT LU LV MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) | ||
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 11632471 Country of ref document: US |
|
WWW | Wipo information: withdrawn in national office |
Country of ref document: DE |
|
122 | Ep: pct application non-entry in european phase | ||
DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) |