Acquisition of labeled data for supervised Hyperspectral Image (HSI) classification is expensive in terms of both time and costs. Moreover, manual selection and labeling are often subjective and tend to induce redundancy into the classifier. Active learning (AL) can be a suitable approach for HSI classification as it integrates data acquisition to the classifier design by ranking the unlabeled data to provide advice for the next query that has the highest training utility. However, multiclass AL techniques tend to include redundant samples into the classifier to some extent. This paper addresses such a problem by introducing an AL pipeline which preserves the most representative and spatially heterogeneous samples. The adopted strategy for sample selection utilizes fuzziness to assess the mapping between actual output and the approximated a-posteriori probabilities, computed by a marginal probability distribution based on discriminative random fields. The samples selected in each iteration are then provided to the spectral angle mapper-based objective function to reduce the inter-class redundancy. Experiments on five HSI benchmark datasets confirmed that the proposed Fuzziness and Spectral Angle Mapper (FSAM)-AL pipeline presents competitive results compared to the state-of-the-art sample selection techniques, leading to lower computational requirements.

Blood is key evidence to reconstruct crime scenes in forensic sciences. Blood identification can help to confirm a suspect, and for that reason, several chemical methods are used to reconstruct the crime scene however, these methods can affect subsequent DNA analysis. Therefore, this study presents a non-destructive method for bloodstain identification using Hyperspectral Imaging (HSI, 397–1000 nm range). The proposed method is based on the visualization of heme-components bands in the 500–700 nm spectral range. For experimental and validation purposes, a total of 225 blood (different donors) and non-blood (protein-based ketchup, rust acrylic paint, red acrylic paint, brown acrylic paint, red nail polish, rust nail polish, fake blood, and red ink) samples (HSI cubes, each cube is of size 1000 × 512 × 224, in which 1000 × 512 are the spatial dimensions and 224 spectral bands) were deposited on three substrates (white cotton fabric, white tile, and PVC wall sheet). The samples are imaged for up to three days to include aging. Savitzky Golay filtering has been used to highlight the subtle bands of all samples, particularly the aged ones. Based on the derivative spectrum, important spectral bands were selected to train five different classifiers (SVM, ANN, KNN, Random Forest, and Decision Tree). The comparative analysis reveals that the proposed method outperformed several state-of-the-art methods.

Food adulteration is a global concern, drawing attention from safety authorities due to its potential health risks. Detecting and categorizing oil adulteration is crucial for consumer safety and food industry integrity. This research explores hyperspectral imaging (HSI) analysis to identify substandard oil adulteration at different stages. Using the non-destructive HSI Specim Fx 10 system, a method for precise and easy imaging-based fraud detection and classification was proposed. The 670 oil samples, including pure (Almond, Mustard, Coconut, Olive) and adulterated (Sunflower, Castor, Liquid Paraffin), were analyzed. The Savitzky-Golay filter preprocessed the images to remove noise and smooth spectral signatures. The oils were identified using various machine learning approaches, including Support Vector Machines, Logistic Regression, Linear Discriminant Analysis, Random Forests, Decision Trees, K-Nearest Neighbors, and Naïve Bayes with Linear Discriminant Analysis excelling in identification. Performance parameters, including precision, recall, F1-score, and overall accuracy, were calculated. The proposed method achieved a validation accuracy of 100%, outperforming numerous state-of-the-art approaches. This study introduces a robust pipeline for effective oil adulteration detection, offering a significant advancement in food safety and quality control.

The quality of red chili is characterized based on its color and pungency. Several factors like humidity, temperature, light, and storage conditions affect the characteristic qualities of red chili, thus preservation required several measures. Instead of ensuring these measures, traders are using oil and Sudan dye in red chili to increase the value of an inferior product. Thus, this work presents the feasibility of utilizing a hyperspectral camera for the detection of oil and Sudan dye in red chili. This study describes the important wavelengths (500–700 nm) where different adulteration affects the response of the reflected spectrum. These wavelengths are then utilized for training an Support Vector Machine (SVM) algorithm to detect pure, oil-adulterated, and Sudan dye-adulterated red chili. The classification performance achieves $97\%$ with the reduced dimensionality and $100\%$ with complete validation data. The trained algorithm is further tested on separate data with different adulteration levels in comparison to the training data. Results show that the algorithm successfully classifies pure, oil-adulterated, and Sudan-adulterated red chili with an accuracy of 100%.

Minced meat substitution is one of the most common forms of food fraud in the meat industry. Recently, Hyperspectral Imaging (HSI) has been used for the classification and identification of minced meat types. However, conventional methods are based only on spectral information and ignore the spatial variability of the data. Moreover, these methods first tend to reduce the size of the data, which to some extent ignores the abstract level information and does not preserve the spatial information. Therefore, this work proposes a novel Isos-bestic wavelength reduction method for the different minced meat types, by retaining only Myoglobin pigments (Mb) in the meat spectra. A total of 60 HSI cubes are acquired using Fx 10 Hyperspectral sensor. For each HSI cube, a set of preprocessing schemes is applied to extract the Region of Interest (ROI) and spectral preprocessing, i.e., Golay filtering. Later, these preprocessed HSI cubes are fed into a 3D-Convolutional Neural Network (3D-CNN) model for nonlinear feature extraction and classification. The proposed pipeline outperformed several state-of-the-art methods, with an overall accuracy of $94.0\%$.