Near-infrared Hyperspectral System Research Articles

Detection of fungal infection and Ochratoxin A contamination in stored wheat using near-infrared hyperspectral imaging

A study was done to detect Aspergillus glaucus, and Penicillium spp., infection and Ochratoxin A contamination in stored wheat using a Near-Infrared (NIR) Hyperspectral Imaging system. Fungal-infected samples were imaged every two weeks, and the three dimensional hypercubes obtained from image data were transformed into two dimensional data. Principal component analysis was applied to the two dimensional data and based on the highest factor loadings, 1280, 1300, and 1350 nm were identified as significant wavelengths. Six statistical features and ten histogram features corresponding to the significant wavelengths were extracted and subjected to linear, quadratic and Mahalanobis discriminant classifiers. All the three classifiers differentiated healthy kernels from fungal-infected kernels with a classification accuracy of more than 90%. The quadratic discriminant classifier provided classification accuracy higher than the linear and Mahalanobis classifiers for pair-wise, two-way and six-way classification models. The Ochratoxin A contaminated samples had a unique significant wavelength at 1480 nm in addition to the two significant wavelengths corresponding to fungal infection. The peak at 1480 nm was identified only in the Ochratoxin A contaminated samples. The Ochratoxin A contaminated samples can be detected with 100% classification accuracy using NIR hyperspectral imaging system. The NIR hyperspectral system can differentiate between different fungal infection stages and different levels of Ochratoxin A contamination in stored wheat.

Automated Classification and Visualization of Healthy and Diseased Hard Dental Tissues by Near-Infrared Hyperspectral Imaging

Dental caries remains one of the most prevalent chronic diseases of modern society. The initial stages of dental caries are characterized by demineralization of enamel, resulting in subclinical lesions, which are difficult to diagnose. If detected early enough, such demineralization can be arrested and reversed by noninvasive means through well-established preventive measures, such as fluoride therapy, anti-bacterial therapy, or low intensity laser irradiation. Near-infrared (NIR) hyperspectral imaging is a promising new technique for early detection of dental caries based on distinct spectral features of healthy and diseased dental tissues. In this study, we apply NIR hyperspectral imaging to classify and visualize healthy and diseased dental tissues including enamel, dentin, calculus, enamel caries, and dentin caries. For this purpose, a standardized teeth database was constructed consisting of 12 extracted human teeth with different degrees of caries lesions imaged by an NIR hyperspectral system, X-ray, and digital color camera. The color and X-ray images of teeth were presented to a clinician expert for localization of the dental tissues and classification of pathological changes, thereby obtaining the gold standard. Principal component analysis (PCA) was used for multivariate local modeling of healthy and diseased dental tissues. Finally, the dental tissues were classified by employing multiple discriminant analysis. Good agreement was observed between the resulting cross-validated classification and the gold standard with the classification sensitivity and specificity exceeding 79.8% and 93.8%, respectively. This study clearly shows that the proposed automated classification and visualization method based on NIR hyperspectral imaging has considerable diagnostic potential.