Non-destructive testing techniques have gained importance in monitoring food quality over the years. Hyperspectral imaging is one of the important non-destructive quality testing techniques which provides both spatial and spectral information. Advancement in machine learning techniques for rapid analysis with higher classification accuracy have improved the potential of using this technique for food applications. This paper provides an overview of the application of different machine learning techniques in analysis of hyperspectral images for determination of food quality. It covers the principle underlying hyperspectral imaging, the advantages, and the limitations of each machine learning technique. The machine learning techniques exhibited rapid analysis of hyperspectral images of food products with high accuracy thereby enabling robust classification or regression models. The selection of effective wavelengths from the hyperspectral data is of paramount importance since it greatly reduces the computational load and time which enhances the scope for real time applications. Due to the feature learning nature of deep learning, it is one of the most promising and powerful techniques for real time applications. However, the field of deep learning is relatively new and need further research for its full utilization. Similarly, lifelong machine learning paves the way for real time HSI applications but needs further research to incorporate the seasonal variations in food quality. Further, the research gaps in machine learning techniques for hyperspectral image analysis, and the prospects are discussed.

No abstract

No abstract

Optimization of important oil expelling parameters was carried out using dehulled sunflower and wheat bran as a source of fiber to carry out a systematic study on effect of moisture and press head temperature on the pressing characteristics of sunflower seed. Box‐Behnken design of response surface methodology was used for the study considering 80–95 g dehulled sunflower, 5–20 g wheat bran, and 6%–10% (w.b.) sample moisture while press head temperature was 50–90°C. Important oil expelling parameters viz. oil recovery, residual oil, free fatty acid, etc., was evaluated. Oil recovery was affected due to variation in wheat bran, dehulled sunflower, sample moisture as well as press head temperature. This study indicated that 86.08% of dehulled sunflower, 13.92% of wheat bran with 6% sample moisture may be considered for oil expelling of dehulled sunflower at 70°C press head temperature. The oil recovery in two sets of experiments varied from 87.23% (at constant temperature) to 87.71% (at constant moisture). Practical applications The main aim of oil extraction processes is to obtain higher oil recovery and good quality meal for its utilization in human foods. The traditional process of sunflower oil expelling involves using whole sunflower seeds resulting in poor quality meal due to the presence of hull. Hence, dehulling of sunflower, if carried out before oil expelling will result in good quality meal with acceptable color for its further utilization in all kind of food products for human consumption. The moisture content of the oilseed and press head temperature is important in screw pressing for a range of oil bearing materials for obtaining higher oil recovery and good quality meal. In view of this, optimization of important oil expelling parameters was carried out using dehulled sunflower and wheat bran as a source of fiber for achieving higher oil recovery and better quality meal which will ultimately benefit the oil milling industry in terms of higher oil recovery and value added food products from oil meal.

No abstract