AI-Based Smart Identification of Medicinal Plants Using Vision Transformer and CatBoost for Biodiversity and Healthcare

The diversity of plants in Indonesia means that many plants have the potential to be used as medicine by the community. Because of its potential as a medicine, many people do not know about it, so it is important to study it. The use of medicinal plants by the community has been passed down from generation to generation, so there is still a lack of documentation regarding the use of medicinal plants. This study aims to identify medicinal plants in the Saradan Kesatuan Pemangkuan Hutan (KPH) area as well as the utilization of plants that are often used as medicine by the community in the Saradan KPH area. The research was conducted in March 2022. Ethnobotanical data were collected using the roaming method and the structured interview method using ethnobotanical interview sheets. Identification of medicinal plants using the help of books on medicinal plants by Widyaningrum. The selection of respondents was carried out randomly, according to the study, which documented 32 species of medicinal plants from 18 families. The most commonly found families of medicinal plants are the Zingiberaceae and Euphorbiaceae families. The leaves are the most useful part of the plant. and the method of treatment with medicinal plants is mostly done by boiling and pounding. The medicinal plant diversity documented in KPH Saradan village is 32 species. Ocimum basilicum L., Alpinia Galanga L. Willd., Zingiber officinale Rosc., and Curcuma domestica Val. medicinal plants that are most widely used by the community around KPH Saradan.

Plants play crucial role in our life as they provide food, oxygen, housing, medicine and many more. Mainly plants have been used for medicinal use since decades. Currently, identification of medicinal plant is done manually where it requires huge investment and experts to confirm its accuracy effectively. To overcome this issue, creating a website application to identify medicinal plants by applying certain machine learning algorithms. After that training machines using data by extracting features and classification which are important to identify medicinal plants which affects accuracy of the system. This research scrutinize methods of image processing for classification and identification of plants.

Medicinal plants are the backbone of the system of medicines; they are the richest bioresource of drugs of traditional systems of medicine, modern medicines, nutraceuticals, food supplements, folk medicines, pharmaceutical intermediates, and chemical entities for synthetic drugs. These plants are classified according to their medicinal values. Classification of medicinal plants is acknowledged as a significant activity in the production of medicines along with the knowledge of its use in the medicinal industry. Medicinal plant classification based on parts such as leaves has shown significant results. An automated system for the identification of medicinal plants from leaves using Image processing and Machine Learning techniques has been presented. This paper provides knowledge of the process of identification of medicinal plants from features extracted from the images of leaves and different preprocessing techniques used for feature extraction from a leaf. Many features were extracted from each leaf such as its length, width, perimeter, area, color, rectangularity, and circularity. It is expected that for the automatic identification of medicinal plants, a web-based or mobile computer system will help the community people to develop their knowledge on medicinal plants, help taxonomists to develop more efficient species identification techniques and also participate significantly in the pharmaceutical drug manufacturing.

Medicinal plants have a variety of values and are an important source of new drugs and their lead compounds. They have played an important role in the treatment of cancer, AIDS, COVID-19 and other major and unconquered diseases. However, there are problems such as uneven quality and adulteration. Therefore, it is of great significance to find comprehensive, efficient and modern technology for its identification and evaluation to ensure quality and efficacy. In this study, deep learning, which is superior to conventional identification techniques, was extended to the identification of the part and region of the medicinal plant Paris polyphylla var. yunnanensis from the perspective of spectroscopy. Two pattern recognition models, partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM), were established, and the overall discrimination performance of the three types of models was compared. In addition, we also compared the effects of different sample sizes on the discriminant performance of the models for the first time to explore whether the three models had sample size dependence. The results showed that the deep learning model had absolute superiority in the identification of medicinal plant. It was almost unaffected by factors such as data type and sample size. The overall identification ability was significantly better than the PLS-DA and SVM models. This study verified the superiority of the deep learning from examples, and provided a practical reference for related research on other medicinal plants.

This research proposes multi-objective genetic algorithm non-dominated-sorting (MOGA NSGA-II) of fuzzy local binary pattern to optimize LBP operator and fuzzy threshold for identification of Indonesian medicinal plants. Multi-objective genetic algorithm (MOGA) is the genetic algorithm (GA) which is developed specifically for problems with multiple objectives. We evaluated 1,440 medicinal plant leaf images which belong to 30 species. The images were taken from Biofarmaka IPB, Cikabayan Farm, Greenhouse Center Ex-Situ Conservation of Medicinal Plant Indonesia Tropical Forest and Gunung Leutik. FLBP is used to handle uncertainty on images with various patterns. FLBP approach is based on the assumption that a local image neighbourhood may be characterized by more than a single binary pattern. The experimental results show that the correct selection of FLBP operator and threshold using MOGA can reach accuracy of 85%. It can be concluded that this propose method is capable to identify medicinal plants species efficiently and accurately.

The accurate identification and monitoring of medicinal plants in remote and diverse terrains is crucial for biodiversity conservation, pharmaceutical research, and traditional medicine documentation. This project presents an IoT-based medicinal plant identification system that integrates deep learning with robotics and wireless communication to automate the process of plant species recognition in real-world environments. Manual plant identification is time-consuming and often error-prone, especially in inaccessible regions. With the advancement of IoT, automated plant classification systems can now be deployed in the field. The ESP32-CAM, a compact low-power module with onboard Wi-Fi and camera, offers an ideal platform for real-time image capture and cloud data transmission. Combining this with the Rocker-Bogie mechanism enables smooth traversal over rough terrain, making it suitable for field applications. The proposed system consists of a mobile robotic platform using the Rocker-Bogie mechanism for stable all-terrain navigation. Mounted on the robot is an ESP32-CAM module that captures high-resolution images of plants from multiple angles. A GPS module is integrated to tag each image with accurate geo location data. The Rocker-Bogie platform provided stable movement across uneven surfaces, while the ESP32-CAM captured clear images for classification. The developed IoT-based medicinal plant identification system effectively combines to provide a reliable and scalable solution for automated plant monitoring in remote environments.

Today, with the development of technology, most manual methods have been replaced by automated computer systems for human convenience. Plant identification and disease classification are two major areas of agricultural research and are aimed at introducing computerized systems instead of manual methods. Millions of plant species are in the world and play a significant role in human life. Among all the types of plants, medicinal plants play an essential role in the traditional medical field because herbal plants can heal humans. Currently, there is a reactivation of interest in herbal medicines at the global level, and conventional medicine is now accepting the use of medicines and their products once they have been scientifically validated. To achieve this goal, we evaluated the performance of two common pre-trained deep learning models (VGG19 and ResNet50) and compared their accuracy levels Finally, the system can estimate some performance metrics such as accuracy and error rate for both algorithms and compare the algorithms based on accuracy in the form of graph. These results are promising, as they show that machine-learning techniques could be used for the early identification of medicinal plants. Our algorithm has been able to achieve a high level of accuracy in the classification of medicinal plants in training and test sets, making it a potentially valuable tool for fast and accurate diagnosis in clinical environments. Keywords—VGG19, ResNet50, Traditional medicine, Medicinal Plant Identification and Disease Classification

Medicinal plants are a primary source of disease treatment in many countries. As most are edible however, consumption of the wrong herbal plants can have serious consequences and even lead to death. Automatic accurate recognition of plant species to help users who do not have specialist knowledge of herbal plants is thus a desirable aim. Several automatic medicinal plant identification systems have been proposed, though most are significantly constrained either in the small number of species or in requiring manual image segmentation of plant leaves. This means they are captured on a plain background rather than being readily identified in their natural surroundings, which often involve complex and noisy backgrounds. While deep learning (DL) based methods have made considerable strides in recent times, their potential has not always been maximised because they are trained with samples which are not always fully representative of the intra-class and inter-class differences between the plant species concerned. This paper addresses this challenge by incorporating mutual information into a Convolutional Neural Network (CNN) model to select samples for the training, validation, and testing sets based on a similarity measure. A critical comparative evaluation of this new CNN medicinal plant classification model incorporating a mutual information guided training (MIGT) algorithm for sample selection, corroborates the superior classification performance achieved for the VNPlant-200 dataset, with an average accuracy of more than 97%, while the precision and recall values are also consistently above 97%. This is significantly better than existing CNN classification methods for this dataset as it crucially means false positive rates are substantially lower thus affording improved identification reliability.

In today’s world, people are more prone to diseases due to food adulteration and pollution in the environment, and people have found a way of using herbal medicine as an alternative to allopathic medicine, especially since coronavirus disease 2019 (COVID-19). Medicinal plants are the source of herbal medicines that increase the immunity of humans. Medicinal plants are used in many applications, like pharmaceuticals, cosmetics, and drugs. Medicinal plants are of great importance, and hence this work presents a review of the medicinal plants grown in Karnataka State, India. The work also highlights species identification and disease detection of medicinal plants employing machine learning and deep learning approaches. The paper provides information about datasets available for various medicinal plant leaf images. The deep learning models used for species identification and disease detection in medicinal plants have been discussed along with the results.

Protocols for in vitro cultures and secondary metabolite analysis of aromatic and medicinal plants

Ayurveda is one of the oldest holistic treatment systems in the world. Finding an accurate and correct plant is the key to the working of Ayurvedic treatment. Identification of medicinal plants is a tedious job due to the look-alike feature and availability issue of medicinal plants with other plants. This paper emphases on the ideal identification and classification of plants of medicinal use using deep learning approaches. Previously researchers have used traditional machine learning techniques to identify medicinal plants, which lead to mixed results. Such results are good but not enough as the identification of medicinal plants may lead to a worsening situation for patients. This research is conducted to get results closer to an ayurvedic expert. The dataset used for this research has been taken from Mendeley Data. The dataset comprises 30 different species of medicinal plants. Hybrid transfer learning has been applied to this dataset. The model has generated a test accuracy of 95.25% which is better than the other popular transfer learning techniques.

MediFlora-Net: Quantum-enhanced deep learning for precision medicinal plant identification.

Deep learning for Ethiopian indigenous medicinal plant species identification and classification

Plants are essential for human life. They help people breathe, provide food, clothing, medicine, and fuel, and also safeguard the environment. Plants can be loaded with medicinal properties and possess active substances that can be used for medical purposes. Several beneficial plant species are disappearing as a result of such factors as global warming, increasing population, professional secrecy, insufficient government support for research efforts, and the lack of public understanding of medicinal plants. It takes time to identify medicinal plants, therefore use professionals to assist you. For better benefit to humankind, a new method to identify and classify therapeutic plants must be developed. Because of the advanced technology in our day and age, medicinal plant identification and classification is an important subject of research in the field of image processing. Feature extraction and classification are the most important components in the process of identifying medicinal plants and classifying them. This research examines methods used in identifying and classifying medicinal plants as well as the medicinal properties of plants that have become increasingly relevant in the recent past. There is a vital importance placed on identifying the suitable medicinal plants in the creation of an ayurvedic medication. In order to identify a medicinal plant, look for these three features: leaf form, colour, and texture. From the both sides of the leaf, there are both deterministic and nondeterministic factors that identify the species. In this study, a combination of traits is designed that is said to identify a single tree the most effectively while minimising errors. The database is made up of scanned photos of both the front and back side of ayurvedic medicinal plant leaves, which is an ayurvedic medicinal plant identification database. In leaf identification, rates as high as 99% have been found when tested on a wide range of classifiers. Extending the prior work by using dried leaves and feature vectors results in identification using which identification rates of 94% are possible. Identification of the correct medicinal plants that goes in to the preparation of a medicine is very important in ayurvedic medicinal industry. The main features required to identify a medicinal plant is its leaf shape, colour and texture. Colour and texture from both sides of the leaf contain deterministic parameters to identify the species. This paper explores feature vectors from both the front and back side of a green leaf along with morphological features to arrive at a unique optimum combination of features that maximizes the identification rate. A database of medicinal plant leaves is created from scanned images of front and back side of leaves of commonly used ayurvedic medicinal plants. The leaves are classified based on the unique feature combination. Identification rates up to 99% have been obtained when tested over a wide spectrum of classifiers. The above work has been extended to include identification by dry leaves and a combination of feature vectors is obtained, using which, identification rates exceeding 94% have been achieved.

Addressing the escalating demand for medicinal plants, this study undertakes the critical task of establishing an efficient identification system. Employing Convolutional Neural Networks (CNNs) with ResNet50v2 architecture, the project endeavours to develop a robust model capable of classifying 30 distinct medicinal plant types from high-resolution images. This classification relies on the precision of feature extraction to ensure accurate identification. Notably, the dataset used is meticulously curated to ensure its adaptability to the diverse botanical characteristics inherent in medicinal plants. Central to achieving high accuracy is the ResNet50v2 model, which forms the cornerstone of the project. Integrated into a real-time web application implemented with Flask, this model facilitates swift and accessible plant identification for various users, including researchers, herbalists, and enthusiasts. The study underscores the efficacy of deep learning algorithms in medicinal plant identification, showcasing remarkable accuracy and reliability in classification tasks. Beyond mere identification, the model demonstrates an ability to precisely categorize plant species, thereby bridging the gap between identification and exploration. This precision is underscored by an exceptional 99% accuracy rate in distinguishing between 30 medicinal plant species, attributed to meticulous model training with a diverse, high-resolution dataset capturing intricate plant features. Continual efforts are directed towards expanding the dataset to encompass variations in real-world scenarios. Strategies to address class imbalance through oversampling techniques and class weight adjustments are being rigorously pursued. Additionally, the model undergoes refinement through fine-tuning its architecture and integrating advanced data augmentation techniques. The research significantly contributes to the broader field of AI applications in sustainable practices, particularly in the conservation of medicinal plant resources. Serving as a potent tool for accurate identification, it holds promising implications for future advancements in deep learning and botanical research.