Rapid Identification of Apple Maturity Based on Multispectral Sensor Combined with Spectral Shape Features

• Published in: Horticulturae Vol. 8; no. 5; p. 361
• Main Authors: Zhang, Mengsheng, Shen, Maosheng, Pu, Yuge, Li, Hao, Zhang, Bo, Zhang, Zhongxiong, Ren, Xiaolin, Zhao, Juan
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.05.2022
• Subjects: Apples; Data processing; Discriminant analysis; Food quality; Fruits; Infrared analysis; Light; Maturity; multispectral sensor; Optics; Portable equipment; Prediction models; Preprocessing; Sensors; spectral shape feature; Spectrum analysis; Storage conditions; Support vector machines; visible and near-infrared spectroscopy; ‘Fuji’ apple; United States > US; Austria
• ISSN: 2311-7524; 2311-7524
• DOI: 10.3390/horticulturae8050361

The rapid and convenient detection of maturity is of great significance to determine the harvest time and postharvest storage conditions of apples. In this study, a portable visible and near-infrared (VIS/NIR) analysis device prototype was developed based on a multispectral sensor and applied to ‘Fuji’ apple maturity detection. The multispectral data of apples with maturity variation was measured, and the prediction model was established by a least-square support vector machine and linear discriminant analysis. Due to the low resolution of the multispectral data, regular preprocessing methods cannot improve the prediction accuracy. Instead, the spectral shape features (spectral ratio, spectral difference, and normalized spectral intensity difference) were used for preprocessing and model establishment, and the combination of the three features effectively improved the model performance with a prediction accuracy of 88.46%. In addition, the validation accuracy of the optimal model was 84.72%, and the area under curve (AUC) value of each maturity level was higher than 0.8972. The results show that the multispectral sensor is an appliable choice for the development of the portable detection device of apple maturity, and the data processing method proposed in this study provides a potential solution to improve the detection accuracy for multispectral sensors.