Detection of Wampee Damage based on Hyperspectral Imaging Technology

Abstract

Wampee is one of the characteristic fruits in southern China, and its brittle and thin skin can easily be damaged. In this study, principal components analysis (PCA) and minimum noise fraction (MNF) analysis were carried out on the two wampee varieties by hyperspectral imaging technology, and 680nm was determined to be the optimal characteristic wavelength. The accurate recognition rate obtained from PCA algorithm for wampee samples of two varieties was about 83.75%, and that obtained from MNF algorithm for two variety samples was 85%. It was indicated that the wampee damaged can be identified more accurately and effectively by MNF based on hyperspectral imaging technology

Detection of physical descaling damage in carp based on hyperspectral images and dimension reduction of principal component analysis combined with pixel values

“…In this paper, PCA was chosen to reduce dimensionality at the image level. When the cumulative contribution rate of the principal component (PC) images exceeds 99.99%, the PC images can almost represent the information of all the images, and the feature image can be selected from these PC images (Bagnasco et al., 2015; Qiu et al., 2020). Pixel value is the smallest unit of the hyperspectral image, and it is the data element with spatial and spectral characteristics at the same time (Xiao, 2014).…”

“…In the process of collecting hyperspectral images, the HSI system may be interfered with the current of electronic equipment, resulting in a series of dark currents and noises (Qiu et al., 2020). The influence of the current on the hyperspectral image can be eliminated as much as possible by correcting the black and white hyperspectral image (Rivera et al., 2014).…”

“…The common physical descaling methods: (a) mechanical descaling; (b) water-jet descaling products (Garhwala et al, 2020;Qiu et al, 2020). But there are no reports of using HSI technology to identify damages in aquatic products, especially for carp.…”

“…The researchers endeavor about using HSI as a quick and accurate method for the aquatic products, such as salmon moisture adulteration (Zhang et al., 2018) and tilapia freshness detection (Shi et al., 2019). To our knowledge, HSI has the potential for damage identification in agricultural products (Garhwala et al., 2020; Qiu et al., 2020). But there are no reports of using HSI technology to identify damages in aquatic products, especially for carp.…”