The current study proposes a novel approach for assessing the effect of storage on potato tuber texture using biospeckle imaging. Agria potato tubers were subjected to biospeckle imaging using three low-power laser diodes and mechanical reference tests including uniaxial compression and creep tests for 6 months. The speckle activity indices of features such as inertia moment, absolute value of differences, autocorrelation function, and energy of wavelet transform were computed from the images. Mechanical and rheological properties were also measured using mechanical tests. An adaptive neuro-fuzzy inference system (ANFIS) coupled with the genetic algorithm was employed to develop models for predicting mechanical properties. The models for retarded compliance, maximum force, and retarded viscosity, with correlation coefficients of 0.812, 0.773, and 0.750, provided the best results. These findings can be used to non-invasively predict the mechanical properties of potatoes. The study demonstrates the potential of biospeckle imaging in assessing the texture of potato tubers during storage.
