A Novel 1D-DenseNet-Like Architecture for Enhanced Raisin Grain Classification

This study introduces a novel sparse one-dimensional dense convolutional network-like (1D-DenseNet) architecture, optimized explicitly for raisin variety classification. By combining advanced deep learning techniques with a concise set of seven pre-extracted morphological features, our method signif...

Popoln opis

Bibliografske podrobnosti

Glavni avtor:	Thi-Thu-Hong Phan
Format:	Artigo
Jezik:	Inglês
Izdano:	World Scientific Publishing 2026-05-01
Serija:	Vietnam Journal of Computer Science
Teme:	Raisin grain classification 1D-DenseNet morphological features hybrid model classification accuracy
Online dostop:	https://www.worldscientific.com/doi/10.1142/S2196888825500101
Oznake:	Označite Brez oznak, prvi označite!