About this document

IEEE Journal Paper Template Copy Copy by chandan1947das is a document available to read on EtoBox.

This paper presents HCT-Net, a Hybrid CNN–Transformer architecture designed for fine-grained classification of indigenous Indian vegetable cultivars in challenging agricultural environments, achieving a peak accuracy of 98.4%. The framework integrates the strengths of CNNs and Vision Transformers to effectively capture both local and global features, addressing limitations of existing models. Additionally, the authors introduce the Indian Vegetable Image Dataset (IVID-2025), comprising 4,500 high-resolution

Author

chandan1947das

Language

EN