Application of computer vision technique for physical quality monitoring of turmeric slices during direct solar drying

In the present work, computer vision technology was adopted to study the effect of direct solar drying on quality attributes of turmeric in terms of color, morphology, texture, browning factor and shrinkage. Drying experiments were carried out with turmeric slices placed in an in-house built natural convection direct solar dryer. A standardized image acquisition unit was fabricated comprising LED strips and a digital camera for capturing the images of turmeric slices during the drying period. The color and shrinkage of sample were analyzed using RGB images in ImageJ software. The thickness of dried layer on the circumference of the sample was visualized using gray scale images in order to estimate the degree of polishing required for obtaining better quality samples. Browning determinant (BD) was computed using gray scale values of captured images and results showed decrement in BD with drying time revealing higher total phenolic content in dried turmeric in comparison to fresh sample. Lightness index (L-*) was increased by 5.55%, while redness index (a(*)) and yellowness index (b(*)) were decreased by 117.06% and 278.26%, respectively during the entire drying period of 4h. The morphological features like area, perimeter, roundness, solidity and density were found to decline smoothly with drying time by 83.72, 60.69, 22.34, 6.12, and 83.72% respectively. Fractal analysis was performed using scanning electron microscopy images and the micrographs showed rougher and more complex shaped particles for hot air dried turmeric (fractal dimension, D-B = 1.78) powder as compared to solar dried powder (D-B = 1.46).