Predicting furan content in a fried dough system using image analysis.

The aim of this paper is to test different models for predicting furan content in a dough system, based on partial least squares regression using colour images. Starch dough systems were fried at five temperatures between 150 and 190 °C and for 5, 7, 9, 11 and 13 min. The furan content was quantified using gas chromatography/mass spectrometry, while the corresponding images were simultaneously obtained and processed in order to extract 2914 features. Good furan content predictions were obtained using computer vision image chromatic features using correlation coefficient of prediction (Rp = 0.86). However, the best prediction correlation was obtained using the image textural features (Rp = 0.93), when the number of features was reduced to 10 by algorithms applications. These results suggest that furan content in fried dough systems can be predicted using features of computer vision images.

Effect of formulation and baking conditions on the structure and development of non-enzymatic browning in biscuit models using images.

The aim of this research was to determine the effect of composition (dietary fiber = DF, fat = F, and gluten = G) and baking time on the target microstructural parameters that were observed using images of potato and wheat starch biscuits. Microstructures were studied Scanning Electron Microscope (SEM). Non-enzymatic browning (NEB) was assessed using color image analysis. Texture and moisture analysis was performed to have a better understanding of the baking process. Analysis of images revealed that the starch granules retained their native form at the end of baking, suggesting their in complete gelatinization. Granules size was similar at several different baking times, with an average equivalent diameter of 9 and 27 µm for wheat and potato starch, respectively. However, samples with different levels of DF and G increased circularity during baking to more than 30%, and also increasing hardness. NEB developed during baking, with the maximum increase observed between 13 and 19 min. This was reflected in decreased luminosity (L*) values due to a decrease in moisture levels. After 19 min, luminosity did not vary significantly. The ingredients that are used, as well as their quantities, can affect sample L* values. Therefore, choosing the correct ingredients and quantities can lead to different microstructures in the biscuits, with varying amounts of NEB products.