Narrow-leaved lupin seed variety identification with weighted ensemble soft voting technique

Adeeba Anis; Penghao Wang; Chengdao Li; Geoffrey John Thomas; Elaine Gough; Priestley Michelle; Ferdous Sohel

doi:10.1016/j.atech.2026.102420

Back

Narrow-leaved lupin seed variety identification with weighted ensemble soft voting technique

Journal article

Open access

Peer reviewed

Narrow-leaved lupin seed variety identification with weighted ensemble soft voting technique

Adeeba Anis, Penghao Wang, Chengdao Li, Geoffrey John Thomas, Elaine Gough, Priestley Michelle and Ferdous Sohel

Smart agricultural technology, Vol.14, 102420

2026

DOI: https://doi.org/10.1016/j.atech.2026.102420

Files and links (1)

pdf

Published16.83 MBDownload View

Open Access CC BY V4.0

Abstract

Agricultural Engineering

Agriculture

Agriculture, Multidisciplinary

Agronomy

Life Sciences & Biomedicine

Science & Technology

Narrow-leaved lupin (Lupinus angustifolius) is an important legume in Australia due to its high protein content, applications in human food as well as livestock feed, and its ability to improve soil fertility through nitrogen fixation. Lupin varieties have different adaptation and quality profiles for production and market preference. Therefore, quick and accurate variety identification from seed is important for crop management, breeding, seed quality assessment and marketing. However, many lupin varieties show highly similar visual characteristics, making manual identification difficult and time-consuming. The objective of this study is to develop and evaluate deep learning (DL) techniques for automated lupin variety seed identification using RGB images. Accordingly, a dataset was created comprising 12 distinctive lupin varieties which includes PBA Barlock, Tanjil, PBA Gunyidi, Mandelup, Jenabillup, Quilinock, PBA Jurien, Unicrop, Coromup, Kalya, Rosemont, and Danja. The dataset contains both healthy and Phomopsis diseased lupin seed images. Several deep learning models including EfficientNetB0, InceptionV3, SqueezeNet, ShuffleNet, MobileNetV2, ResNet50, and DenseNet121 have been trained and tested with this dataset. Among all, the weighted ensemble of ResNet50 and DenseNet121 outperformed the other models with an accuracy of 98.85%. Results show that DL models can effectively identify visually similar lupin variety seed despite challenges such as inter-class similarity and intra-class dissimilarity. The proposed ensemble model presents a pioneering approach for automated lupin variety seed identification. This can support farmers, marketers and breeders in improving crop quality through better assurance of seed purity.

Details

Title: Narrow-leaved lupin seed variety identification with weighted ensemble soft voting technique
Authors/Creators: Adeeba Anis - Murdoch Univ, Western Crop Genet Alliance, Murdoch, WA 6150, Australia
Penghao Wang - Murdoch University
Chengdao Li - Murdoch University, Centre for Crop and Food Innovation
Geoffrey John Thomas - Dept Primary Ind & Reg Dev Western Australia, Canning Vale, WA, Australia
Elaine Gough - Dept Primary Ind & Reg Dev Western Australia, Canning Vale, WA, Australia
Priestley Michelle - Dept Primary Ind & Reg Dev Western Australia, Canning Vale, WA, Australia
Ferdous Sohel - Murdoch University, School of Information Technology
Publication Details: Smart agricultural technology, Vol.14, 102420
Publisher: Elsevier B.V.
Number of pages: 14
Grant note: Western Australian Agricultural Research Collaboration DAW2305-006RTX / Australian Grains Research and Development Corporation; Grains R&D Corp
Identifiers: 991005909776607891
Murdoch Affiliation: Western Crop Genetics Alliance; Centre for Crop and Food Innovation; School of Information Technology
Language: English
Resource Type: Journal article

Metrics

1 Record Views