Processing, food industry and biochemistry
Behrouz akbari-adergani; morteza mohammadzade moghadam; mehdi Karimi noghabi; Mojtaba Mohammadpour; Mohammad Khalilian-Movahhed
Abstract
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 ...
Read More
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.
Processing, food industry and biochemistry
Morteza Mohamadzadeh moghadam; Masoud Taghizadeh; Hassan Sadrnia; Hamid reza Pourreza
Abstract
The classification of saffron as the most expensive spice is of great importance for customers and traders. In general, two methods are currently used to classify saffron. The first method is based on the experiences of an expert and by observing the samples. The second method is destructive and is performed ...
Read More
The classification of saffron as the most expensive spice is of great importance for customers and traders. In general, two methods are currently used to classify saffron. The first method is based on the experiences of an expert and by observing the samples. The second method is destructive and is performed using laboratory methods. According to experts, the use of machine learning techniques to classify saffron is a goal due to its non-destructive nature and timely characteristics. This method can also increase the accuracy of the industrial scale grading process. In this paper, a vision machine method is presented. Due to lack of documented research on this subject, a comprehensive literature search is presented in this work. Almost all color characteristics were extracted and used in a large number of classifiers. Experts in Iran classify saffron into three main categories based on their appearance: Pushal, Negin and Sargol. In this paper, a database consisting of 440 images from saffron for the three different classes was collected using a mobile phone camera. After applying some preprocessing steps, such as background removal, cropping etc., 21 color features were extracted using different image analysis methods. Twenty-two classifiers were employed for classification. Comparing results of different classifiers showed that the Linear Discriminant, Linear SVM, Bagged Trees and RUSBoost Trees can produce more accurate grading compared to other classifiers when using color features. In particular, mean classification accuracy of 82.23% was achieved in this work using Linear a SVM classifier.
