Skip to content
Open access

Classification of Antihypertensive Medicinal Plant Leaves Using MobileNetV2 with Cosine Annealing and L2 Regularization

Sep 2026 · PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic · Vol 14, pp. 273-282 · 0 citations

TL;DR

The results indicated that the combination of MobileNetV2, Cosine Annealing, and L2 regularization improved classification performance while helping to control overfitting.

Abstract

The identification of medicinal plants through leaf characteristics was considered an important approach for supporting the utilization of herbal plants, particularly those associated with hypertension management. However, similarities in visual characteristics among plant species and variations in image conditions presented challenges in the classification process. This study aimed to develop a deep learning model for classifying seven medicinal plant leaf species, namely Annona muricata, Apium graveolens, Centella asiatica, Moringa oleifera, Ocimum basilicum, Psidium guajava, and Syzygium polyanthum. The dataset consisted of 2,100 leaf images from seven classes used for model development, while an independently collected private dataset captured using mobile cameras was used as an independent test set to evaluate model generalization under real-world conditions. The experiments were conducted in three stages. First, four deep learning architectures, namely MobileNetV2, VGG16, ResNet50, and EfficientNetB0, were compared. Second, the effect of Cosine Annealing as a learning rate optimization strategy was evaluated. Third, several regularization methods were compared using MobileNetV2, including no regularization, L1, L2, and Dropout. The results showed that MobileNetV2 achieved the highest performance among the evaluated architectures, with a test accuracy of 94.60%. The application of Cosine Annealing increased the test accuracy to 96.19%. Furthermore, L2 regularization achieved the best overall performance, with training, validation, and test accuracies of 97.68%, 96.87%, and 97.14%, respectively. These results indicated that the combination of MobileNetV2, Cosine Annealing, and L2 regularization improved classification performance while helping to control overfitting.

Read PDF

Similar papers

Open access Nov 2026

Soybean Leaf Disease Classification using MobileNetV2 and EfficientNetB0

Soyabean is an important crop used for food, animal feed, and industrial application. Disease symptoms on leaves can reduce crop health and productivity, making timely identification valuable. This paper presents a deep-learning workflow for classifying soybean leaf images into six dataset categories: Bacterial Blight,...

Ankita Dnyanoba Joldapke and Ms. Snigdha Shukla · 0 citations
Open access Sep 2026

COMPARISON OF MOBILENETV2 AND RESNET50 PERFORMANCE IN CLASSIFICATION OF SHALLOT PLANT DISEASES

This study applies transfer learning to two CNN architectures, MobileNetV2 and ResNet50, to classify red onion leaf diseases into three classes yellow spot, leaf curl, and healthy leaves, and shows that ResNet50 demonstrates better generalization, with a stable training curve, and outperforms MobileNetV2 in terms of ac...

Isma Fadianti, Supatman Supatman · 0 citations
Sep 2026

Carica papaya Leaf Disease Prediction and Classification Based on Hyperparameter-Tuned ResNet18

One of the essential components of human civilisation is agriculture. It contributes to economic development by providing food security, generating employment, and much more. According to the National Horticulture Board (NHB), India is one of the top suppliers of papaya, accounting for nearly 38.6% of worldwide product...

S. Hemasri · 0 citations
Open access Oct 2026

Convolutional Neural Network Based on Transfer Learning for Pest Classification in Chili Plant

Pest infestation is a major cause of productivity loss in chili cultivation, requiring accurate and automated pest identification systems to support precision agriculture. This study proposes a lightweight MobileNetV2-based transfer learning model for multi-species chili pest classification using a validated Indonesian...

Valdi Dhani Pratama, Febry Putra Rochim · 0 citations
Open access Oct 2026

Comparative Evaluation of Convolutional and TransformerBased Models for Cucumber Disease Classification

Cucumber (Cucumis sativus) is an important horticultural crop, and disease-related losses can reduce both yield and market quality. Image-based deep learning methods have been increasingly used for plant disease recognition, yet practical model selection requires attention to both predictive performance and computation...

M. Aliyev, J. Zeynalov, Yiğitcan Çakmak et al. · 0 citations
Oct 2026

Comparative Evaluation of Lightweight and Heavyweight Convolutional Neural Network Architectures for Apple Leaf Disease Classification

Leaf diseases can significantly reduce both the productivity and quality of crops; therefore, early and accurate diagnosis is required for sustainable farming. Reliance on visual examination by experts is time-consuming and expensive and may result in inconsistent or inaccurate diagnoses. The present study investigated...

Neha Sawant, K. L. Bansal Bansal · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.