A New Approach for Classification of Spices to Make Special Herbal Tea Using Caralluma Fimbriata

Abstract

Classification of multiple types of spice images is automatically challenging due to conflict between the texture patterns of spice images. This work aims to develop an automatic system for classifying different types of spice images so that the system can choose an appropriate spice to make herbal tea using Caralluma fimbriata. This work considers the following seven spices, namely, cinnamon, citrus peel, clove, ginger, jeera, kokum, mint, and Caralluma fimbriata as one more class for classification. Most of the existing systems need human intervention to choose different spices to make Caralluma fimbriata tea. It is observed that the pattern of different spice images represents different textures. This observation motivated us to extract features based on multi-Sobel kernels. To reduce the number of computations, the proposed work introduces a novel idea of corner detection based on Gaussian distribution. For each corner, the method performed is multi-Sobel kernels for extracting features. The features are fed to convolutional neural network layers for the classification of multiple spice images. The results of our dataset and comparative study with the state-of-the-art methods show that the proposed model is superior to existing methods in terms of classification rate.