Paddy variety identification using hyperspectral imagery under non-ideal illumination conditions

Abstract

Hyperspectral imaging (HSI) has shown great potential in the use of paddy variety identification. However, the quality of HSI images taken by a hyperspectral camera under non-ideal illumination is vulnerable to environmental influences such as shadows and noises, leading to a degraded identification result. This problem is addressed in this study by a two-stage image processing method. First, to eliminate the influence of shadows, a grayscale image based on the reflectance slope is synthesized. The synthetic reflectance slope image (SRSI) is binarized for image segmentation and shape features extraction. Secondly, an HSI image de-noising technology based on weighted spatial filtering (WSF), which integrates both spatial and spectral information of the HSI image, is proposed to reduce the influence of noises. Finally, the extracted shape, spectral and texture features are combined and input into the support vector machine for paddy variety identification. Four varieties of paddy with different origins were tested in the experiments. The experiment results showed that compared with color images, the SRSIs could help obtain more accurate shape features. The results also showed that the WSF method can significantly reduce noises and improves the paddy variety identification accuracy.