Automated Image Analysis Framework for the High-Throughput Determination of Grapevine Berry Sizes Using Conditional Random Fields

TL;DR

This study presents an automated, high-throughput image analysis framework using conditional random fields for accurately estimating grapevine berry sizes non-invasively, adaptable to varying image conditions.

Contribution

The paper introduces a novel automated image analysis framework employing conditional random fields and active learning for precise grapevine berry size estimation.

Findings

Correlation of 0.88 between estimated and manual berry sizes.

Framework successfully tested on 139 images from different growth stages.

Automated process adapts to changing image conditions without user intervention.

Abstract

The berry size is one of the most important fruit traits in grapevine breeding. Non-invasive, image-based phenotyping promises a fast and precise method for the monitoring of the grapevine berry size. In the present study an automated image analyzing framework was developed in order to estimate the size of grapevine berries from images in a high-throughput manner. The framework includes (i) the detection of circular structures which are potentially berries and (ii) the classification of these into the class 'berry' or 'non-berry' by utilizing a conditional random field. The approach used the concept of a one-class classification, since only the target class 'berry' is of interest and needs to be modeled. Moreover, the classification was carried out by using an automated active learning approach, i.e no user interaction is required during the classification process and in addition, the process adapts automatically to changing image conditions, e.g. illumination or berry color. The framework was tested on three datasets consisting in total of 139 images. The images were taken in an experimental vineyard at different stages of grapevine growth according to the BBCH scale. The mean berry size of a plant estimated by the framework correlates with the manually measured berry size by $0.88$.