Dr. Kanniah Rajasekaran Profile

Dr. Kanniah Rajasekaran

at Agricultural Research Service

SPIE Involvement:

Author

Publications (6)

Proceedings Article | 1 June 2022 Presentation + Paper

Identification of aflatoxin contamination in corn kernels using line-scan Raman imaging

Feifei Tao, Haibo Yao, Zuzana Hruska, Kanniah Rajasekaran, Jianwei Qin, Moon Kim

Proceedings Volume 12120, 1212002 (2022) https://doi.org/10.1117/12.2624965

KEYWORDS: Raman spectroscopy, Contamination, Line scan image sensors, Chemical analysis, Agriculture, Statistical modeling, Imaging systems, Hyperspectral imaging

Read Abstract +

Proceedings Article | 12 April 2021 Presentation + Paper

Near-infrared hyperspectral imaging for identification of aflatoxin contamination on corn kernels

Feifei Tao, Haibo Yao, Zuzana Hruska, Russell Kincaid, Kanniah Rajasekaran

Proceedings Volume 11754, 1175408 (2021) https://doi.org/10.1117/12.2591078

KEYWORDS: Contamination, Near infrared, Hyperspectral imaging, Visualization, Spectral models, Safety, Nondestructive evaluation, Imaging systems, Agriculture

Read Abstract +

Proceedings Article | 18 May 2020 Paper

Raman imaging for detection of corn kernels infected with Aspergillus flavus: a preliminary study

Feifei Tao, Haibo Yao, Zuzana Hruska, Kanniah Rajasekaran, Jianwei Qin, Moon Kim

Proceedings Volume 11421, 1142107 (2020) https://doi.org/10.1117/12.2558859

KEYWORDS: Raman spectroscopy, Image segmentation, Line scan image sensors, Imaging systems, Agriculture, Data modeling, Hyperspectral imaging

Read Abstract +

Proceedings Article | 30 April 2019 Paper

Potential of near-infrared hyperspectral imaging in discriminating corn kernels infected with aflatoxigenic and non-aflatoxigenic Aspergillus flavus

Feifei Tao, Haibo Yao, Zuzana Hruska, Russell Kincaid, Kanniah Rajasekaran, Deepak Bhatnagar

Proceedings Volume 11016, 1101603 (2019) https://doi.org/10.1117/12.2521654

KEYWORDS: Hyperspectral imaging, Statistical modeling, Near infrared, Principal component analysis, Agriculture

Read Abstract +

Proceedings Article | 15 May 2018 Presentation + Paper

Development of high speed dual-camera system for batch screening of aflatoxin contamination of corn using multispectral fluorescence imaging

Deok Han, Haibo Yao, Zuzana Hruska, Russell Kincaid, Christopher Ramezanpour, Kanniah Rajasekaran, Deepak Bhatnagar

Proceedings Volume 10665, 106650J (2018) https://doi.org/10.1117/12.2305148

KEYWORDS: Cameras, Imaging systems, Image processing, Contamination, Multispectral imaging, Hyperspectral imaging, Optical filters, Image processing software, Defect detection

Read Abstract +

Proceedings Article | 15 May 2018 Paper

Rapid and non-destructive detection of aflatoxin contamination of peanut kernels using visible/near-infrared (Vis/NIR) spectroscopy

Feifei Tao, Haibo Yao, Zuzana Hruska, Yongliang Liu, Kanniah Rajasekaran, Deepak Bhatnagar

Proceedings Volume 10665, 106650K (2018) https://doi.org/10.1117/12.2304399

KEYWORDS: Contamination, Spectroscopy, Data modeling, Nondestructive evaluation, Statistical modeling, Agriculture

Read Abstract +

Aflatoxin contamination can occur in a wide variety of agricultural products pre- and post-harvest, posing potential severe health hazards to human and livestock. However, current methods for detecting aflatoxins are generally based on wet chemical analyses, which are time-consuming, destructive to test samples and require skilled personnel to perform, making them impossible for large-scale non-destructive screening and on-site detection. In this study, we utilized the visible/near-infrared (Vis/NIR) spectroscopy over the spectral range of 400-2500 nm to detect contamination of shelled commercial peanut kernels with the predominant aflatoxin B₁ (AFB₁). Our results indicated the usefulness of Vis/NIR spectroscopy combined with the chemometric techniques of partial least squares discriminant analysis (PLS-DA) and least squares support vector machine (LS-SVM) in identifying the AFB₁ contamination of peanut kernels. Both PLS-DA and LS-SVM methods provided satisfactory classification results using the full spectral information over the ranges of 410-1070 (I), 1120-2470 nm (II) and I+II. Based on the classification threshold of 20 ppb, the best PLS-DA prediction results using the full spectra yielded the average accuracy of 87.9% and overall accuracy of 88.6%. With 100 ppb as the classification threshold, the best PLS-DA model using the full spectra achieved the average accuracy of 94.0% and overall accuracy of 91.4%. Using the full spectra, the best average accuracies recorded by LS-SVM were 90.9% and 98.0%, with the classification thresholds of 20 and 100 ppb, respectively. Correspondingly, the best overall accuracies by LS-SVM were 90.0% and 97.1%. In addition, the simplified models of CARS-PLS-DA and CARS-LS-SVM also demonstrated good prediction capability in identifying the AFB1 contamination from peanut surface. Based on both classification thresholds of 20 and 100 ppb, the best CARS-PLS-DA and CARS-LS-SVM prediction results were ≥ 90.0% in both average accuracy and overall accuracy. Most importantly, the computation complexity and the employed data dimensionality were significantly reduced by using the simplified models.

Showing 5 of 6 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years