This study presents a novel method for detecting and classifying oil adulteration using hyperspectral imaging (HSI) combined with machine learning (ML) techniques. The research focuses on identifying adulterated oils, including pure oils such as almond, mustard, coconut, and olive, and adulterants such as sunflower, castor, and liquid paraffin. A total of 670 oil samples were analyzed using a non-destructive HSI system, the Specim Fx 10, which captures spectral and spatial data. The spectral data was preprocessed using the Savitzky-Golay filter to remove noise and smooth the spectral signatures. The processed data was then used to train various ML models, including Support Vector Machines (SVM), Logistic Regression (LR), Linear Discriminant Analysis (LDA), Random Forests (RF), Decision Trees (DT), K-Nearest Neighbors (KNN), and Naïve Bayes. The models were evaluated based on performance metrics such as precision, recall, F1-score, and overall accuracy. The proposed method achieved a validation accuracy of 100%, outperforming existing techniques. The study demonstrates the effectiveness of HSI and ML in detecting oil adulteration, providing a robust and accurate solution for food safety and quality control. The results show that LDA was the most effective model for classification, achieving high accuracy across all classes. The study also highlights the potential of HSI for non-destructive and rapid detection of adulterants, offering a significant advancement in the food industry. The proposed system is designed to be fast, accurate, and cost-effective, addressing the limitations of traditional methods in detecting oil adulteration. The research contributes to the development of intelligent systems for food safety, ensuring the authenticity and quality of edible oils.This study presents a novel method for detecting and classifying oil adulteration using hyperspectral imaging (HSI) combined with machine learning (ML) techniques. The research focuses on identifying adulterated oils, including pure oils such as almond, mustard, coconut, and olive, and adulterants such as sunflower, castor, and liquid paraffin. A total of 670 oil samples were analyzed using a non-destructive HSI system, the Specim Fx 10, which captures spectral and spatial data. The spectral data was preprocessed using the Savitzky-Golay filter to remove noise and smooth the spectral signatures. The processed data was then used to train various ML models, including Support Vector Machines (SVM), Logistic Regression (LR), Linear Discriminant Analysis (LDA), Random Forests (RF), Decision Trees (DT), K-Nearest Neighbors (KNN), and Naïve Bayes. The models were evaluated based on performance metrics such as precision, recall, F1-score, and overall accuracy. The proposed method achieved a validation accuracy of 100%, outperforming existing techniques. The study demonstrates the effectiveness of HSI and ML in detecting oil adulteration, providing a robust and accurate solution for food safety and quality control. The results show that LDA was the most effective model for classification, achieving high accuracy across all classes. The study also highlights the potential of HSI for non-destructive and rapid detection of adulterants, offering a significant advancement in the food industry. The proposed system is designed to be fast, accurate, and cost-effective, addressing the limitations of traditional methods in detecting oil adulteration. The research contributes to the development of intelligent systems for food safety, ensuring the authenticity and quality of edible oils.