# Deep learning-based methods for phenotypic trait extraction in rice panicles

## TL;DR

This paper introduces an automated deep learning tool for measuring rice panicle traits, improving accuracy and efficiency in rice breeding.

## Contribution

A novel deep learning pipeline for phenotypic trait extraction in rice panicles, handling occlusion and varying maturity stages.

## Key findings

- Panicle length extraction achieved R²=0.9583 and RMSE=5.69 mm.
- Grain counting achieved R² values of 0.9799 (loose), 0.9551 (normal), and 0.9278 (dense).
- Grain length R²=0.8823 and grain width MAPE=6.64%.

## Abstract

Key rice panicle traits (grain number, panicle length, grain dimensions, maturity) determine yield and quality, and high-precision/high-throughput measurement is critical for rice breeding. Traditional methods are.

A dataset of 5300 rice panicle images (loose/normal/dense types; milk/dough/full maturity/over-ripe stages) was constructed, with 3290 for training, 940 for validation, and 470 for testing. A deep learning pipeline integrating.

The panicle length extraction achieved R²=0.9583, RMSE=5.69 mm. Grain counting R² values were 0.9799 (loose), 0.9551 (normal), 0.9278 (dense). Grain length R²=0.8823, grain width MAPE=6.64%. OPG-YOLOv8.

This study provides a comprehensive, automated tool for rice panicle phenotyping, addressing occlusion challenges and bridging the gap between advanced models and breeding applications.