Study on the possibility of physical assessment and grading of Mazafati dates using digital image processing and Support vector machines

Takallouzadeh, Meghdad; Mohebbi, Mohebbat; Taghizadeh, Masoud

doi:10.22101/JRIFST.2022.275507.1234

Study on the possibility of physical assessment and grading of Mazafati dates using digital image processing and Support vector machines

Document Type : Original Paper

Authors

¹ PhD. Student, Food Science and Technology, Ferdowsi University of Mashhad, Mashhad, Iran

² Professor, Department of Food Science and Technology, Ferdowsi University of Mashhad, Iran

³ Associate Professor, Food Science and Technology, Ferdowsi University of Mashhad, Mashhad, Iran

10.22101/JRIFST.2022.275507.1234

Abstract

The traditional methods of grading dates, due to the lack of specific characteristics, are causing incorrect grading and wasting both time and money. Date grading based on the classification algorithms could reduce seller and buyer disagreement. It also allows the product to be sold at the right price. In this research, identification of some qualitative characteristics of Mazafati dates and its classification into four categories (grades 1, 2, 3, and 4) has been done according to the opinions extracted from experts Support vector machine (SVM) is used to compare the quality of dates and mobile image processing application in Matlab environment.Support Vector Machine (SVM) has been used between the quality of the dates and the mobile image processing in the Matlab environment. The results of linear, quadratic, cubic, and medium Gaussian SVMs are 100% accurate, meaning that the classification has been successful. The ROC curve provides a positive classification rate versus a false positive rate for selecting classification training. A grade 1 positive rate of 0.97 indicates that the current classifier allocates 97% of the observations correctly to the positive class (primarily rank). In order to make the final verification, the Kappa coefficient has been used. All Kappa values are greater than 0.6 and have sufficient stability. Also, the highest Kappa coefficient is related to the cubic method by more than 0.8 and the lowest is related to fine Gaussian with a value of 0.76. Due to the accuracy and precision of implementation with SVM, this method with high efficiency is capable of grading dates.

Keywords