Real-time hyperspectral imaging for the in-field estimation of strawberry ripeness with deep learning

Abstract

Strawberry is one of the popular fruits with numerous nutrients. The ripeness of this fruits was estimated using the hyperspectral imaging (HSI) system in field and laboratory conditions in this study. Strawberry at early ripe and ripe stages were collected HSI data, covered wavelength ranges from 370 to 1015 nm. Spectral feature wavelengths were selected using the sequential feature selection (SFS) algorithm. Two wavelengths selected for field (530 and 604 nm) and laboratory (528 and 715 nm) samples, respectively. Then, reliability of such spectral features was validated based on support vector machine (SVM) classifier. Performance of SVM classification models had good results with receiver operating characteristic values for samples under both field and laboratory conditions higher than 0.95. Meanwhile, the spatial feature images were extracted from the spectral feature wavelength and the first three principal components for laboratory samples. Pretrained AlexNet convolutional neural network (CNN) was used to classify the early ripe and ripe strawberry samples, which obtained the accuracy of 98.6% for test dataset. The above results indicated real-time HSI system was promising for estimating strawberry ripeness under field and laboratory conditions, which could be a potential application technique for evaluating the harvesting time management for farmers and producers.

Keywords

• Strawberry ripeness
• Hyperspectral imagery
• In field
• CNN