Application of computer vision on non-destructive detection of the authentic and adulterated saffron

Saffron is one of the most expensive spices in the world. Saffron is a spice that is widely cheated. The development of techniques based on simple, inexpensive, appropriate and fast tools in the food industry is essential for detecting adulteration such as saffron adulterated. In the present study, the combination of image processing and Support vector machine (SVM) method has been used for fast and non-destructive evaluation of distinguishing authentic saffron from adulterated saffron. After preparing images from pure and counterfeit saffron and separate stigmas, the images entered the pre-processing stages and finally, statistical features related to the texture of the images and morphological features including 105 features were extracted. In order to increase the speed and accuracy of classification, PCA principal component analysis method was used to reduce the properties of the feature matrix. Also, the images were classified into two classes using different SVM kernel functions. Also, the images were classified into two classes using different SVM kernel functions. Then statistical indicators such as accuracy, precision, sensitivity, specificity and AUC were calculated to evaluate the classification. The values of these indices for classification with SVM cubic kernel for authentic saffron were 97, 98, 99, 93 and 97%, and for adulterated saffron, 97, 93, 83, 97.5 and 97% were obtained, respectively. The results of this classification showed that this system, as an intelligent, fast, non-destructive and accurate method, has the ability to distinguish the authentic saffron from adulterated saffron.