terclim by ICS banner
IVES 9 IVES Conference Series 9 Implementation of hyperspectral image analysis for evaluating table grape quality on bunch and berry level

Implementation of hyperspectral image analysis for evaluating table grape quality on bunch and berry level

Abstract

Typically, subjective, and visual methods are used by grape growers to assess harvest maturity. These methods may not accurately represent the maturity of an entire vineyard – especially if extensive and representative sampling was not used. New technologies have been investigated for improved harvest management decisions. Spectroscopy methods utilizing the near-infrared region of the light spectrum is one such technology investigated as an alternative to classic methods and particularly the application of hyperspectral imaging (HSI) has recently gained attention in research. HIS is a spectroscopic technique that obtains hundreds of images at different wavelengths collecting spectral data for each pixel in the sample i.e., providing both spectral and spatial data.
In this study HSI in the visible-near infrared (VNIR) and short-wave infrared (SWIR) regions was tested for determining total soluble solids (TSS), pH and total acidity (TA) of table grapes under laboratory conditions. Imaging of whole bunches as well as individual berries selected from top, middle and bottom positions of bunches was done. The bunches and berries were collected over multiple samples sessions throughout the 2022-23 and 2023-24 seasons allowing for fruit of various maturity levels (unripe though to harvest maturity) to be included. Spectral data was extracted from the images using MATLAB codes developed for this purpose using different analysis approaches. The resulting data is spatial and numerical yielding mean reflectance per pixel across points for entire bunches, and entire berries. Models for determining grape chemical composition were developed using ground-truthing data collected from the sampled fruit. Initial results indicate that this method could be suitable for determining grape ripeness on a bunch or berry level.

Download the abstract

DOI:

Publication date: June 14, 2024

Issue: Open GPB 2024

Type: Poster

Authors

Talitha Venter1*, Rodrigo Oliva-Mancilla1,2, Fikile Wolela1, Eunice Avenant1,3, Carlos Poblete-Echeverría1 *

1 South African Grape and Wine Research Institute, Stellenbosch University, Private Bag X1, Stellenbosch, South Africa, 7602
2 Global technical consultancies, 05 Barn Road, Bergvliet, Cape Town, South Africa, 7945
3 South African Table Grape Industry, PO Box 2932, Paarl, South Africa, 7620

Contact the author*

Keywords

table grapes, hyperspectral imaging, ripeness, quality, spectroscopy

Tags

IVES Conference Series | Open GPB | Open GPB 2024

Citation

Related articles…

Using open source software in viticultural research

Many high quality Open Source scientific applications have been available for a long time. Some of them have proved to be particularly useful for carrying out the usual activities involved in viticultural research projects, such as statistical analyses (including spatial analyses), GIS work, database management (possibly integrated with statistical and spatial analysis) and even “low-level” often highly time-consuming activities (e.g. repetitive task on text files).

Read More

A multilayer interactive web map of the wine growing region carnuntum with emphasis on geochemical and mineralogical zoning

During a three-year study the vineyards of the wine-growing region Carnuntum have been investigated for their terroir characteristics (climate, soil, rocks) and major viticulture functions. As an outcome of the study, various thematic layers and geodata analyses describe the geo-environmental properties and variability of the wine growing region and delimit homogenous multilayer mapping units by using a Geographic Information System.

Read More

The South African vineyard landscapes: impact on long term cultural practices

This paper follows the one presented by Saayman at the International Symposium on Landscapes of Vines and Wines in the Loire Valley during July 2003. Where Saayman’s paper described the heritage and development of South African vineyard landscapes, this one focuses on how the landscape is used to assist in decision-making concerning the most important long term practices.

Read More

Data fusion approaches for sensory and multimodal chemistry data applied to storage conditions

The need to combine multimodal data for complex samples is due to the different information captured in each of the techniques (modes).

Read More

Development and validation of a standardized oxidation assay for the accurate measurement of the ability of different wines to form “de novo” oxidation-related aldehydes

From the standpoint of wine aroma oxidation there are two effects observed: aroma degradation of oxygen sensitive compounds (polyfunctional mercaptans) and the appearance of new substances with high aromatic power (acetaldehyde, methional, phenylacetaldehyde, sotolon, alkenals, isobutanal and 2, 3-metylbutanals) (1-5). According to our experience, Strecker aldehydes are compounds with highest sensory relevance in the oxidative degradation of many wines (5-7).

Read More