Abstract: Machine learning (ML) has played a signifcant role in pattern recognition including fruits and vegetables classifcation. In this paper, comparative analysis of various ML techniques have been carried out for the identifcation of Spices. For the current work, ML techniques namely Naïve Bayes (NB), Decision Tree (DT), K-Nearest Neighbor (KNN), Random Forest (RF) and Support Vector Machine (SVM) have been undertaken. The main aim of the current study is to fnd out the most appropriate ML approach for Spices recognition. The experimental study has been performed on primary dataset of Spices. This dataset consists of 1000 images of fve diferent Spices including clove, green cardamom, cinnamon, black pepper and curry leaf. The performance of the ML techniques have been analyzed on the basis of four parameters i.e. accuracy, precision, recall and f1-score. Out of fve implemented ML models, best performance has been predicted by SVM approach with accuracy of 94.5%, precision of 95%, and recall of 94% with f1-score of 0.95. Keywords: Decision tree, K-Nearest neighbor, Machine learning, Spices recognition, Support vector machine. Classifcation of Spices using Machine Learning Techniques Yukti Gupta 1* , Haneet Kour 2 , Jatinder Manhas 3 and Vinod Sharma 4 1 M.Tech. Student, Department of Computer Science and IT, University of Jammu, Jammu and Kashmir, India. Email: yuktigupta19@gmail.com 2 PhD Research Scholar, Department of Computer Science and IT, University of Jammu, Jammu and Kashmir, India. Email: haneetkour9@gmail.com 3 Sr. Assistant Professor, Department of Computer Science and IT, Bhaderwah Campus, University of Jammu, Jammu and Kashmir, India. Email: manhas.jatinder@gmail.com 4 Professor, Department of Computer Science and IT, University of Jammu, Jammu and Kashmir, India. Email: vnodshrma@gmail.com *Corresponding Author I. Introduction India is referred to the Land of Spices and it is the world’s largest manufacturer, consumer and exporter of Spices. It commands a formidable position in the world Spice trade. The total value of Spices produced in India is about 7000 crores annually. The country produces about 75 out of 109 types of Spices listed by the International Organization for Standardization (ISO) [1]. Every Spice has its own favor and essence, and its addition or omission can genuinely make or destroy a dish. Spices include remarkable nutritional values and have numerous health benefts including antioxidant and anti-infammatory properties, glucose- lowering efects, appetite control, regulates metabolism, aids in weight loss, improves memory and brain function. Spices are being used by several medical industries such as cosmetic, pharmaceutical and aromatic as perfumery [2]. It is quite difcult to distinguish between Spices as many Spices look similar. The recognition of Spices used in our daily basis food is gaining more importance in our daily life. Research on Spices recognition and classifcation is vital for several economic sectors, both for the wholesale and retail markets, as well as for the processing industries. Consuming healthy and good quality fruits and vegetables are the utmost necessity of the purchaser. Hence, automation in food industries are developing nowadays because it is improbable for humans to manually audit the fruits and vegetables as it requires a large number of workers along with a lot of time and efort. In recent years, numerous machine learning (ML) algorithms have been applied with various diferent feature description methods for fruits and vegetables classifcation in several real-world applications [3]. In this study, comparative analysis of several ML techniques including Naive Bayes (NB), Decision Tree (DT), K-Nearest Neighbor (KNN), Random Forest (RF) and SVM (Support Vector Machine) have been carried out for the recognition of Spices. The main motive of the current research work is to implement ML based system for the detection of Spices for food image researchers and dietician to make an appropriate analysis of nutrition and other type of health hazards. Classifying a particular kind of Spice will enable us to distinguish it from another kind. For the current study, fve diferent classes of International Journal of Knowledge Based Computer Systems 10 (1) June 2022, 27-32 http://www.publishingindia.com/ijkbcs/