SAPS: Automatic Saffron Adulteration Prediction Systems, research issues, and prospective solutions

Saffron is one of the costlier spices that is cultivated in specific regions of the world. Due to its limited availability and higher demand in the population, thus saffron adulteration is one of the crucial challenges. It becomes very difficult for human vision to discriminate between real and adulterated saffron samples. With the emergence of visual computing and machine learning algorithms, automatic saffron adulteration prediction becomes an easier task. In this paper, we expound the state of the art of intelligent saffron adulteration predication systems along with various research issues and future perspectives. The present study is an attempt to explore the existing methods of handcrafted features to train linear classifiers such as artificial neural networks (ANN), support vector machine (SVM), and decision tree (DT). However, the majority of the techniques exhibit promising performance but the problem of generalization capabilities (unseen – samples) and scarcity of the saffron databases are the open research challenges. Moreover, deep neural networks are the viable solution for designing an efficient and robust saffron adulteration prediction system (SAPS).