SNACK QUALITY EVALUATION METHOD BASED ON IMAGE FEATURES AND NEURAL-NETWORK PREDICTION

Quality maintenance of food products like snacks and chips is a challe nging problem in the food processing industry. At present, it is typic al for food companies to determine ''quality'' standards using a senso ry panel of trained experts. Process operators sample and observe the product to ensure it is similar to target flavor and quality. This pro cess is subjective and prone to differences. A neural network approach via image texture and shape features is investigated in this study fo r the evaluation of the quality of typical snack products. Although qu ality of food, especially snacks and chips, is very difficult to quant ify, some external attributes of the product are indicators of the sna ck eating quality. External texture features (which can reflect intern al structure), together with the size and shape features of snacks are used to describe the quality from a texture (mouthfeel) standpoint. A backpropagation neural network was trained with a large number of sam ples having texture and morphological features as input and sensory at tributes as output. The network is shown to predict the sensory attrib utes of the snack quality with a reasonable degree of accuracy. The an alysis is validated through a comparison of the predicted sensory attr ibutes obtained by the network to those from a taste panel on untraine d samples. The developed methodology can be used in the food industry to evaluate the snack quality in a nondestructive sense.