One-dimensional Active Contour Models for Raman Spectrum Baseline Correction

Raman spectroscopy is a powerful and non-invasive method for analysis of chemicals and detection of unknown substances. However, Raman signal is so weak that background noise can distort the actual Raman signal. These baseline shifts that exist in the Raman spectrum might deteriorate analytical results. In this paper, a modified version of active contour models in one-dimensional space has been proposed for the baseline correction of Raman spectra. Our technique, inspired by principles of physics and heuristic optimization methods, iteratively deforms an initialized curve toward the desired baseline. The performance of the proposed algorithm was evaluated and compared with similar techniques using simulated Raman spectra. The results showed that the 1D active contour model outperforms many iterative baseline correction methods. The proposed algorithm was successfully applied to experimental Raman spectral data, and the results indicate that the baseline of Raman spectra can be automatically subtracted.

[1]  Terry E. Weymouth,et al.  Using Dynamic Programming For Minimizing The Energy Of Active Contours In The Presence Of Hard Constraints , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[2]  Won-Sook Lee,et al.  Domain adaptation for ultrasound tongue contour extraction using transfer learning: A deep learning approach. , 2019, The Journal of the Acoustical Society of America.

[3]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[4]  L. Tay,et al.  Methodology for binary detection analysis of inkjet-printed optical sensors for chemical detection , 2021 .

[5]  Won-Sook Lee,et al.  Semantic Segmentation with Peripheral Vision , 2020, ISVC.

[6]  L. Tay,et al.  Surface-enhanced Raman and optical scattering in coupled plasmonic nanoclusters , 2013 .

[7]  L. Tay,et al.  Paper‐based surface‐enhanced Raman spectroscopy sensors for field applications , 2020, Journal of Raman Spectroscopy.

[8]  Jeremy J. Baumberg,et al.  Present and Future of Surface-Enhanced Raman Scattering , 2019, ACS nano.

[9]  Jamshid Tanha,et al.  Silica encapsulated SERS nanoprobe conjugated to the bacteriophage tailspike protein for targeted detection of Salmonella. , 2012, Chemical communications.

[10]  Andrew Jirasek,et al.  Investigation of Selected Baseline Removal Techniques as Candidates for Automated Implementation , 2005, Applied spectroscopy.

[11]  M. Hamed Mozaffari,et al.  Anomaly detection using 1D convolutional neural networks for surface enhanced raman scattering , 2020, Future Sensing Technologies.

[12]  O. Beyssac.  New Trends in Raman Spectroscopy: From High-Resolution Geochemistry to Planetary Exploration , 2020, Elements.

[13]  Ramesh C. Jain,et al.  Using Dynamic Programming for Solving Variational Problems in Vision , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Emad L. Izake,et al.  Forensic and homeland security applications of modern portable Raman spectroscopy. , 2010, Forensic science international.

[15]  Li-Lin Tay,et al.  Detection of acute brain injury by Raman spectral signature. , 2011, The Analyst.

[16]  Demetri Terzopoulos,et al.  Constraints on Deformable Models: Recovering 3D Shape and Nonrigid Motion , 1988, Artif. Intell..

[17]  Yuanjie Liu,et al.  A survey of the baseline correction algorithms for real-time spectroscopy processing , 2016, SPIE/COS Photonics Asia.

[18]  Nathaniel R. Gomer,et al.  Remote Raman Spectroscopy for Planetary Exploration: A Review , 2012, Applied spectroscopy.

[19]  Won-Sook Lee,et al.  Convergent heterogeneous particle swarm optimisation algorithm for multilevel image thresholding segmentation , 2017, IET Image Process..

[20]  L. Tay,et al.  Raman based detection of Staphylococcus aureus utilizing single domain antibody coated nanoparticle labels and magnetic trapping , 2013 .

[21]  M. Hamed Mozaffari,et al.  A Review of 1D Convolutional Neural Networks toward Unknown Substance Identification in Portable Raman Spectrometer , 2020, ArXiv.

[22]  Jyh-Horng Jeng,et al.  Active contour model via multi-population particle swarm optimization , 2009, Expert Syst. Appl..

[23]  L. Tay,et al.  A SERS and electrical sensor from gas-phase generated Ag nanoparticles self-assembled on planar substrates. , 2016, The Analyst.

[24]  H. G. Schulze,et al.  A Model-Free, Fully Automated Baseline-Removal Method for Raman Spectra , 2011, Applied spectroscopy.

[25]  David J. Lockwood,et al.  Low-temperature Si growth on Si (001): Impurity incorporation and limiting thickness for epitaxy , 2004 .

[26]  A Jirasek,et al.  Accuracy and Precision of Manual Baseline Determination , 2004, Applied spectroscopy.

[27]  Mohammad Hamed Mozaffari,et al.  IPO: An Inclined Planes System Optimization Algorithm , 2016, Comput. Informatics.

[28]  Marios Savvides,et al.  Active Contour Model in Deep Learning Era: A Revise and Review , 2020 .