An IoT based authentication system for therapeutic herbs measured by local descriptors using machine learning approach

• The work aims to develop an automatic recognition model to classify medicinal plants using machine learning techniques and enrich the traditional medical system. • Our findings prove that the combination of local descriptors is an efficient measurement approach that benefits automatic recognition of plants based on leaf images. • Modified local binary pattern technique for feature extraction and K-NN classifier with chi-square dissimilarity measure to classify the 32 species of Indian herbs collected in a dataset of size 1320. • Additional technique of Harris corner approach is employed to measure the intensity of the corners. • The probability of misclassification measures the degree of confidence and contributes to higher accuracy in a variety of applications, such as leaf detection, face identification, recognition of handwritten characters, genes classification, among others. • The similarity measured by calculating the Euclidean distance. The work aims to develop an automatic recognition model to classify medicinal plants using machine learning techniques to enrich the traditional medical system of India. Though many countries have accepted conventional medicine as the best alternative to synthetic drugs, there exists limitations such as lack of awareness among general public and unavailability of easy access to its source evidences that has led to its limited acceptance and usability. Herein, an intelligent system is proposed to use Raspberry Pi 3 Model B+ (RPi) and the RPi camera to capture the leaf images of Indian medicinal herbs and reveal their medical properties. Five types of models implemented to identify the medicinal plants. One of the models proposed as Herbmodel extracts a feature map from a captured medicinal leaf by combining three different feature extraction techniques, namely, Scale Invariant Feature Transform (SIFT), Oriented FAST and Rotated BRIEF (ORB) and histogram of oriented gradients on support vector machine as a classifier, predicts an average accuracy of 96.22% over a custom medicinal leaf dataset of 40 different species containing 2515 samples. Generate Bag of Visual Words (BoVW) by applying K-Means clustering on both SIFT and ORB descriptors to reduce the dimensionality. The combined feature vector is further analysed using random forest and k-nearest neighbor classifier. The efficacy of the proposed approach is benchmarked using Flavia dataset and artificial neural network (ANN) as a classifier. Our findings prove that the combination of local descriptors is an efficient measurement approach that benefits automatic recognition of plants based on leaf images. Also, a reliable source of medicinal leaf datasets with good quality leaf images is necessary to establish a machine learning model for medicinal plants.