Near-infrared hyperspectral imaging for classification of mung bean seeds

Abstract

Hard mung bean seeds pose a problem in the sprouting process as they develop mold and infect neighboring seeds. Near-infrared hyperspectral imaging combined with partial least squares discriminant analysis was applied to develop a classifying model to separate hard mung beans from normal ones. The orientation of the measured beans was found to affect the classification result. The optimal partial least squares discriminant analysis model based on all orientations resulted in a correlation coefficient (R) of 0.919 with a root mean squared error of prediction of 0.197. The nongerminative parts were mapped and were concentrated at one end of the bean. Finally, a germinability index was proposed according to the proportion of colored areas between the germinative and non-germinative parts from the hyperspectral imaging results. ARTICLE HISTORY

Fusing spectral and textural information in near-infrared hyperspectral imaging to improve green tea classification modelling

“…has been used for the study of a wide range of food products such as wheat flour [7], olive oil [8], herbal tea [9], seeds [10], coffee [11], beans [12] and many more [13].…”

“…The information generated by HSI takes the form of hypercubes where the first two dimensions represent the spatial information of the imaged scene and the third dimension adds the spectral information to the pixels [12]. The extraction of meaningful information from the hypercube requires advanced pattern recognition and data modelling.…”

Prediction and visualisation of S-ovalbumin content in egg whites using hyperspectral images

“…Various nondestructive approaches commonly used are machine vision, [5] near-infrared spectroscopy, [6][7][8] and hyper-spectral imaging technology. [9,10] Machine vision reflects the spatial attributes and distribution properties of the detected object, [11] while near-infrared spectroscopy estimates its physical and chemical values. Hyper-spectral imaging technology has the advantages of both spectral detection and machine vision techniques.…”

Study on a two‐dimensional correlation visible–near infrared spectroscopy kinetic model for the moisture content of fresh walnuts stored at room temperature

“…Near‐infrared spectroscopy (NIR) is a non‐destructive, fast, reproducible, and efficient analysis technique. It can make the best of full‐spectrum or multi‐wavelength spectral data for qualitative and quantitative analysis, and it has been widely used in the detection of melons and fruits (He et al, 2018; Li et al, 2018), vegetables (Jiang et al, 2018; Phuangsombut, Ma, Inagaki, Tsuchikawa, & Terdwongworakul, 2018), animal products (Ma, Tang, et al, 2012; Ma, Xu, Tang, Tian, & Fu, 2012; Yang et al, 2018b, 2018b) and so on. Aiming at the detection of storage time indicators, some studies have achieved the prediction of the internal quality of apples during storage by testing the soluble solids content, titratable acid, and hardness of apples at different storage times (Ignat et al, 2014).…”