Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Nonlinear laser fluorescence spectrum real-time identification method

A fluorescence spectrum and recognition method technology, applied in the field of real-time recognition of nonlinear laser fluorescence spectrum, can solve problems such as no public reports, and achieve the effects of less training samples, shortened computing time, and reduced the number of support vectors

Active Publication Date: 2010-09-22
DALIAN MARITIME UNIVERSITY
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, there is no public report on the real-time identification method of support vector based nonlinear laser fluorescence spectrum using curvelet transform

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Nonlinear laser fluorescence spectrum real-time identification method
  • Nonlinear laser fluorescence spectrum real-time identification method
  • Nonlinear laser fluorescence spectrum real-time identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] figure 1 It is a flow chart of the present invention. First, 30 groups of fluorescence spectrum data with five types of oil labels are selected from the oil product library as the learning sample spectrum, and 3 groups of laser fluorescence spectrum data of unknown oil products are actually measured as the test sample spectrum.

[0046] image 3 , Figure 4It is the initial fluorescence spectrum diagram with light diesel oil logo and lubricating oil logo in the spectra of 30 learning samples respectively, extracting effective fluorescence bands as the region of interest ROI, the process of extracting the region of interest is to scan line by line from the data head, If saturation and empty data are encountered, delete this part of the band, and finally obtain spectral data containing only fluorescence information. And normalize its intensity in the range of [0, 1], the entire extracted spectrum is characterized by five bands from 0 to 4 bands, as a preprocessing lear...

Embodiment 2

[0057] Embodiment 2 uses image data to classify, and preprocesses the sample image after ROI selection of the region of interest: the image is converted into a binary image, and the background is set to 0, and the spectral feature is set to 1, and then the image size is uniformly transformed into p x p. figure 2 Shown is the process of spectral image position offset correction, scan the preprocessed image sequence frame by frame, traverse all sub-blocks, check whether the image position exceeds the offset value, if the image position offset is too large, redo the region of interest ROI Select and continue to check until the offset condition is met, continue to perform curvelet transformation, input support vector base training, and finally get the classification result.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a nonlinear laser fluorescence spectrum real-time identification method, which comprises the following steps: learning a sample spectrum, testing sample spectral classification, extracting ROI in an interested region, preprocessing the spectrum, extracting the fluorescence spectrum characteristics by discrete curvelet transform, forming feature vectors, constructing i classes of support vector machines, and distinguishing the test results by classes. The invention adopts the classification method of the support vector machines, and does not depend on large sample training, the input vector is the low-frequency coefficient part after curvelet decomposition, the number of training samples is small, the number of the support vectors is greatly reduced, so the operation time is shortened and the method has instantaneity. The second-generation curvelet transform adopted by the invention is based on a new support frame, and can provide high-efficient, stable and nearly-optimal sparse representation for the curve function with strangeness. Compared with the traditional method, the method is more effective and has higher identification rate. The invention can identify the spectrum samples with data format and image format, and has better adaptability.

Description

technical field [0001] The invention relates to a real-time identification technology of fluorescence spectrum, in particular to a real-time identification method of nonlinear laser fluorescence spectrum. Background technique [0002] The airborne lidar excites the oil spill film on the sea surface to generate fluorescence by emitting a fixed-wavelength ultraviolet band laser, and collects the excited fluorescence through a telescope to form a fluorescence spectrum. Due to the different types of fluorescent substrates contained in different petroleum products and the different ratios of various substrates, each substrate can emit its own unique fluorescence spectrum. The fluorescence spectrum emitted by a certain wavelength of ultraviolet laser excitation usually has different intensities and shapes. , so the type of spilled oil can be identified according to the spectral characteristics. However, recognition by human eyes requires extensive experience and takes a long time...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G01N21/64G06K9/62
Inventor 李颖陈澎
Owner DALIAN MARITIME UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products