Optical non-destructive techniques for small berry fruits: A review  

作　　者：Shuping Li Hongpei Luo Menghan Hu Miao Zhang Jianlin Feng Yangtai Liu Qingli Dong Baolin Liu 

机构地区：[1]Shanghai Key Laboratory of Multidimensional Information Processing,East China Normal University,Shanghai 200241,China [2]School of Medical Instrument and Food Engineering,University of Shanghai for Science and Technology,516 Jun Gong Rd.,Shanghai 200093,China [3]Meng Xiancheng College of ECNU,East China Normal University,Shanghai 200241,China [4]College of Fine Arts,East China Normal University,Shanghai 200241,China

出　　处：《Artificial Intelligence in Agriculture》2019年第2期85-98,共14页农业人工智能（英文）

基　　金：This work was supported by the Shanghai Sailing Program under Grant 19YF1414100;the China Postdoctoral Science Foundation funded project under Grant 2016M600315;the Innovation Fund Project for Graduate Student of Shanghai(JWCXSL1401);the STCSM(No.18DZ2270700).

摘　　要：Small berries including strawberry and blueberry are extensively consumed fruits with great economic values due to their characteristic flavor and appearance as well as potential health benefits.This review elaborated the optical non-destructive techniques viz.Vis-NIR spectroscopy,computer vision system,hyperspectral imaging,multispectral imaging,laser-induced method and thermal imaging,and their applications for quality and safety control of small berry fruits.The discussion regarding the photoacoustic technique,X-ray technique,Terahertz spectroscopy,odor imaging,micro-destructive testing and smart mobile terminal-based analyzer was also presented.Furthermore,we proposed our personal understanding of the technical challenges and further trends for these optical non-destructive techniques:1)owing to the relatively low detection limit,the so-called micro-destructive techniques may be alternative to the traditional non-destructive techniques in both practical and fundamental research;2)we suggest that the research articles like“collecting data first,and then modeling the relevant properties of agricultural products by machine learning”should be less produced in related fields.That's because such research methods are likely to be suspected of“cheating”.It is recommended that some modeling competitions can be carried out in the agricultural engineering field to avoid or reduce the“cheating”model.

关 键 词：Berry fruit Optical non-destructive measurement Food quality and safety 

分 类 号：TN9[电子电信—信息与通信工程]