What does this research mean for the field?

Combining 3D geometric morphometrics with deep learning and transformer-based tabular foundation models significantly outperforms traditional 2D methods for complex cereal grain classification. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The aim is to improve grain classification accuracy using advanced 3D morphometric techniques and deep learning.

May 31, 2026Open Access

High-performance 3D morphometrics via deep learning and tabular foundation models: a case study on complex cereal grain classification

Key Points

The aim is to improve grain classification accuracy using advanced 3D morphometric techniques and deep learning.
Utilized 3D Gaussian Mixture Models (GMM) and deep learning for grain analysis.
Employed spherical harmonics coefficients to represent 3D shapes effectively.
Implemented transformer-based Tabular Foundation Models for classification tasks.
Binary classification accuracy ranged from 87.76% to 96.47%, with multiclass accuracy at 82.2%.
Demonstrated that 3D methods outperform traditional 2D approaches in grain classification.
Provided open data and code for reproducible workflows in 3D model classification.

Abstract

• 3D GMM and DL greatly outperform prior 2D methods in grain classification. • Spherical harmonics coefficients are highly efficient representing 3D shapes. • Binary classifications reach 87.76% to 96.47% accuracy and multiclass 82.2%. • Transformer-based Tabular Foundation Models achieve best-in-class performance. • Open data and code enable a reproducible workflow for 3D model classification.

High-performance 3D morphometrics via deep learning and tabular foundation models: a case study on complex cereal grain classification

Key Points

Abstract

Cite This Study