Development of Novel Neural Network Architecture for Automated Pharmaceutical and Vitamin Identification Using Image Classification

Abstract

Automated identification of pharmaceutical drugs and vitamins is critical for improving medication safety and reducing human errors in healthcare systems. This study proposes a novel multi-scale, attention-enhanced convolutional neural network designed for fine-grained classification of pharmaceutical images. The model integrates multi-scale feature extraction to capture both local visual details (e.g., imprints, edges) and global characteristics (e.g., shape, color distribution), while an attention mechanism emphasizes discriminative regions, enabling accurate differentiation of visually similar classes. Transfer learning with ImageNet-pretrained weights accelerates convergence and improves generalization. The model was evaluated on the Pharmaceutical Drugs and Vitamins Synthetic Images dataset, comprising 100,000 images across ten classes. Experimental results demonstrate high classification performance, achieving a macro-averaged F1-score of 0.897, with per-class F1-scores ranging from 0.766 to 0.934. ROC analysis and confusion matrices confirm robust discriminative capability, although challenges remain for classes with minimal visual differences. Compared to conventional CNN architectures, the proposed approach shows improved precision, recall, and F1-scores. The study contributes a scalable, accurate framework for automated pharmaceutical identification, offering a foundation for integrating synthetic data augmentation, multimodal features, and few-shot learning in future research.

More by Ualikhan Sadyk

• Interpretable Hybrid CNN-BiLSTM-Attention Model for ECG Arrhythmia ClassificationIEEE International Conference on Smart Information Systems and Technologies · 2026
• Development of Multimodal Neural Network for Suicidal Ideation Detection Using Kazakh-Russian BERT and Attention MechanismInternational Conference on Electronics, Computer and Computation · 2026
• Benchmarking Deep Transfer Learning for Banknote Recognition: Vision Transformers Vs. CNNs on the KZ-BD DatasetInternational Conference on Electronics, Computer and Computation · 2026
• Kazakh banknote image datasetData in Brief · 2026