This data article presents an image dataset compiled for the purpose of machine learning-based identification and prediction of adulteration levels in Teff (Eragrostis tef (Zucc.) Trotter) flour. The dataset includes images of pure white, mixed, and red Teff flour varieties, as well as these flours adulterated with wood flour (sawdust) and gypsum (calcium sulfate) powder. Adulteration levels range from 10% to 40% in 5% increments. The data collection process involved preparing Teff flour from naturally dried and milled Teff grains. Samples of 100 grams of each Teff flour variety were then mixed with the adulterants at the specified concentrations. A total of 5,000 raw images were captured using an 18-megapixel Canon EOS 7D camera under controlled studio lighting (300 W incandescent lamps), with the samples placed 30 cm from the camera lens in a 10 cm x 10 cm plastic box. To enhance the dataset's diversity and quantity, 25,000 augmented images were generated by shuffling image pixels' locations with various block sizes (1 × 1, 2 × 2, 4 × 4, 8 × 8, and 16 × 16). This dataset is a valuable resource for researchers and students in Teff adulteration using image processing and feature extraction. It also holds potential for use by Food and Drug Administration Authorities and law enforcement to develop automated methods for detecting Teff flour adulteration, offering an alternative to time-consuming physio-chemical laboratory tests. The dataset's structure and augmentation methods are detailed to ensure reproducibility and encourage further research into robust machine learning models for food quality control.
Bochera et al. (2026) studied this question.