Application of machine vision technology for visual assessment of microwave pre-treated donut

Fried foods such as donuts enjoyed worldwide for their taste, distinctive flavor, aroma and crunchy texture. There is, however, grave health concern over large fat content of fried foods (Melito and Farkas, 2013). There are several ways to lower fat content in deep-fried foods. One method is to reformulate the product by adding hydrophilic ingredients such as dietary fibers to reduce oil uptake during frying. Another method to reduce fat content is to partially cook the food using another heating method (Melito and Farkas, 2012). There is an increasing interest in microwaving foods for several reasons: it is faster than conventional methods, the energy consumption is often lower and foods cooked by microwaving maintain nutritional integrity.vIn foods, the appearance is a main criterion in making purchasing decisions. Appearance is used throughout the production –storage-marketing-utilization chain as the key means of judging the quality of individual units of product. The appearance of unities of products could be assessed by considering their color and surface texture. The use of computer-vision technology has quickly increased in the fields of quality inspection, classification and evaluation in processing a large number of food products (Brosnan and Sun, 2004). Therefore the aim of this study was to study the effects of microwave pre-treatment on sensory and appearance properties of donut.
Response surface methodology and Box- Behnken design were applied to evaluate the effects of independent variable include microwave power (300-900 W), microwave time (30-90 s) and frying time (70-130 s) on sensory and appearance properties of donuts. Donuts were prepared according to the formulation by Melito and Farkas (2012) with some modifications. Ingredients used in donuts formulation were consisted of 100 g of wheat flour (9 g/100g), 52 g of water, 9.75 g of Shortening, 14 g of Egg, 14 g of water for yeast, 6.80 g of sugar, 6.80 g of nonfat dried milk powder, 3.25 g of active dried yeast, 1.70 g of Vanilla extract, 1.7 g of baking powder, 1.70 g of Salt, 1.3 g of Persian gum and 7.00 g of carrot pomace powder. The dough was cut into squares approximately 50 mm on each side. Then, the dough pieces were allowed to proof for 30 min at 27 ºC. The proofed samples were pre-treated using a microwave oven at different levels of microwave power and microwave time in accordance with the experimental design. Formerly, the per-treated donuts were deep-fat fried in a Moulinex deep-fat fryer (model F18-RA, France) filled with 1.5 L of vegetable frying oil (A mixture of Sunflower, palm, and soybean oil; Behshahr CO., Tehran, Iran) at different levels of frying time in accordance with the experimental design. The oil was preheated for 30 min prior to frying and replaced with fresh oil after every frying process. After frying, donuts were removed from the fryer and allowed to cool for 30 min on paper towels. They were then stored in coded sealed polyethylene bags.The evaluation of the crumb grain and crust color of donuts was performed using an image analysis system consisted of a Canon digital camera (model SX60 HS, Japan) and a personal computer with a Pentium(R) Dual-Core processor and Windows 7 Ultimate. The samples were photographed at a fixed distance of 30 cm from the crumb of samples, which were sitting inside a black box. The captured images were analyzed using the MATLAB R2014a software (The MathWorks Inc., Natick, Mass, USA).The CIE L*a*b* (or CIELAB) color model was used for determination of the crust color of donuts. Crumb grain features of the donut samples were obtained with described digital image analysis system. After imaging, each image was converted from RGB format to 8 bits (grey level) using the MATLAB software. In this format, an area of 3 × 3 cm2 was selected at the center of the captured image. After contrast enhancement of image, the image segmented using the Otsu algorithm, which produces highly uniform binary images (Otsu, 1979). Finally, crumb grain properties of donuts were studied by determination of cells densities and area of cells. Sensory evaluation of donut samples was carried out by assigning scores for crust appearance, crumb appearance, crust color, aroma, texture, taste and overall acceptance parameters based on a nine-point hedonic scale. (Stone et al., 2012).
Results showed that roughness of the donuts surface increased significantly (p