Grape sugar content prediction with multispectral alignment and improved residual network.

Abstract

Sugar content is a crucial indicator of grape ripeness and grading, and developing non-contact and non-destructive sugar content detection devices is essential for grape-picking robots and sorting platforms. Spectroscopy, which can detect the chemical composition of grapes, has become a key technology for developing non-destructive testing devices. In this paper, we collected 2,880 randomly labeled multispectral images of Sunshine Rose grapes with a Changguang Yuchen MS600 PRO multispectral camera and measured the sugar content (in Brix values) of the labeled grapes with a handheld refractometer, using data exclusively from this grape variety. To address noise and misalignment issues in the multispectral images, we proposed preprocessing methods including Gaussian denoising and ECC (Enhanced Correlation Coefficient) algorithm registration. Based on a ResNet-50 residual network, we constructed a grape sugar content prediction regression model Improved-Res with SE (Squeeze-and-Excitation) attention modules, DSC (Depthwise Separable Convolutions), and Inception modules. The model's performance was evaluated by MSE (Mean Squared Error), MAE (Mean Absolute Error), and R 2 (R-Square) metrics. We compared the performance of four feature extraction methods combined with four traditional machine learning models, as well as seven deep learning models. The results showed that among traditional machine learning methods, the combination of color histogram feature extraction and the XGBoost regression achieved the best performance, with MSE, MAE, and R 2 of 1.35, 0.90 Brix, and 0.78, respectively. Among deep learning methods, the ResNet-50 model demonstrated the best performance, with MSE, MAE, and R 2 of 0.95, 0.96 Brix, and 0.84, respectively. Effective improvements of SE attention module, depthwise separable convolutions, and Inception module in the ResNet-50 model was confirmed through ablation experiments: the proposed Improved-Res model achieved MSE, MAE, and R 2 of 0.49, 0.55 Brix, and 0.92, respectively, which significantly outperformed traditional machine learning methods and classical deep learning models.

Plant phenotyping relevance

ブドウ果実の糖度という植物形質をマルチスペクトル画像から非破壊推定する前処理・深層学習モデルを開発し、複数手法との比較とアブレーション検証を行っており、フェノタイピング手法が中心である。

Code and data availability

The paper describes a self-collected dataset of 480 sets (2,880 images) of multispectral grape images with Brix labels and an Improved-Res model, but the supplied blocks contain no data availability statement, no public dataset deposit, and no author code/model release. The only URLs are the article DOI and the Atago (

No evidence-backed public reproduction asset is currently recorded.