Hyperspectral imaging analysis for ripeness evaluation of strawberry with support vector machine

•Identify strawberry ripeness by hyperspectral imaging with two spectral ranges.•Both spectral and texture features were extracted for analysis.•Models on data fusion combining spectral and texture features performed best.•Models on datasets from images of 441.1–1013.97 nm performed better.

A hyperspectral imaging system covering two spectral ranges (380–1030 nm and 874–1734 nm) was applied to evaluate strawberry ripeness. The spectral data were extracted from hyperspectral images of ripe, mid-ripe and unripe strawberries. The optimal wavelengths were obtained from spectra of 441.1–1013.97 and 941.46–1578.13 nm by loadings of principal component analysis (PCA). Pattern texture features (correlation, contrast, entropy and homogeneity) were extracted from the images at optimal wavelengths. Support vector machine (SVM) was used to build classification models on full spectral data, optimal wavelengths, texture features and the combined dataset of optimal wavelengths and texture features, respectively. SVM models using combined datasets performed best among all datasets. SVM models using datasets from hyperspectral images at 441.1–1013.97 nm performed better with classification accuracy over 85%. The overall results indicated that hyperspectral imaging could be used for strawberry ripeness evaluation, and data fusion combining spectral information and spatial information showed advantages in strawberry ripeness evaluation.