Herbal plant recognition using deep convolutional neural network

Abstract

This paper investigates the application of deep Convolutional Neural Network (CNN) for herbal plant recognition through leaf identification. Traditional plant identification is often time-consuming due to varieties as well as similarities possessed within the plant species. This study shows that a deep CNN model can be created and enhanced using multiple parameters to boost recognition accuracy performance. This study also shows the significant effects of the multi-layer model on small sample sizes to achieve reasonable performance. Furthermore, data augmentation provides more significant benefits on the overall performance. Simple augmentations such as resize, flip and rotate will increase accuracy significantly by creating invariance and preventing the model from learning irrelevant features. A new dataset of the leaves of various herbal plants found in Malaysia has been constructed and the experimental results achieved 99% accuracy

Labeling of an intra-class variation object in deep learning classification

“…For instance, the Plumeria Tourn. ex L. is approved [18], [23], [31], [41], [42]. The Plumeria is a flowering plant that is easy to be cultivated, by grafting technique; hence cross cultivation can be with any varieties, resulting in about a hundred (400 variety, personal communication) varieties of petal flowers.…”

“…Features then automatically gain from learning in the training process [8]- [13]. The convolutional neural networks (CNNs) ISSN: 2252-8938 is a computer vision subfield that leverage ML to be the most powerful object image classifier [14]- [18]. Considering a large of neural networks, the term of deep consists of more than two hidden layers that involve a huge dataset to be trained.…”

Handwritten Javanese script recognition method based 12-layers deep convolutional neural network and data augmentation

“…After the pre-processing and augmentation stages, the dataset is divided into two groups, namely training and testing with DCNN. This is feature extraction and deep learning method widely used in image recognition and classification [11], [35], [36]. Various DCNN models have been proposed, while the one used in this study has 12 layers.…”

Teachable Machine: Optimization of Herbal Plant Image Classification Based on Epoch Value, Batch Size and Learning Rate

“…In other research, herbal plants have been studied by previous researchers with various case studies, such as the classification of herbal plants according to the type of disease identified through the texture, shape and color of herbal plant diseases [11]. Identification of herbal medicinal plant names, scientific names and remedies on leaf objects [12], [13], so that the identification of herbal plants is able to increase the accuracy of herbal plant recognition with CNN well which is able to achieve a recognition rate above 95% near perfect depending on the quality of the object and other approaches [14], [15], because some herbal plants have a surpa level of similarity such as turmeric and ginger, so a good classification technique approach is needed such as CNN and other algorithms [16].…”