Abstract
In order to achieve fast and accurate detection of cucumber freshness by hyperspectral technology, taking the hardness and rate of water loss as the quality index, the hyperspectral imaging technology was used to test the cucumber with different storage dates in the same batch. Firstly, Savitzky-Golar method, multivariate scattering correction (MSC) and standard normal variable transformation (SNV) were used to preprocess the collected hyperspectral data of cucumber, and the pretreatment results were compared to determine that the Savitzky-Golar method was more effective. Then, competitive adaptive reweighted sampling (CARS), partial least squares (PLS) and successive projections algorithm (SPA) were used to select the hyperspectral characteristic wavelengths, and 25, 13 and 20 characteristic wavelengths were selected for the hardness index, respectively. 20, 16, and 20 characteristic wavelengths were selected for the index of water loss rate, respectively. Finally, the BP neural network was used to distinguish the cucumber hardness and water loss rate based of the characteristic wavelengths. The results showed that the BP neural network combined with SPA method had the best discrimination effects, and the accuracy of the training set and the test set for hardness discrimination were 95.24% and 91.67%, respectively. The accuracy of training set and test set for rate of water loss were 97.78% and 95.00%, respectively.
Publication Date
2-28-2021
First Page
145
Last Page
151
DOI
10.13652/j.issn.1003-5788.2021.02.025
Recommended Citation
Shuai-shuai, MA; Hui-chun, YU; Yong, YIN; Yun-xia, YUAN; Xin, LI; and Shu-ning, XUE
(2021)
"Selection of hyperspectral characteristic wavelength and construction of prediction model for cucumber hardness and moisture,"
Food and Machinery: Vol. 37:
Iss.
2, Article 25.
DOI: 10.13652/j.issn.1003-5788.2021.02.025
Available at:
https://www.ifoodmm.cn/journal/vol37/iss2/25
References
[1] 张保华, 李江波, 樊书祥. 高光谱成像技术在果蔬品质与安全无损检测中的原理及应用[J]. 光谱学与光谱法分析, 2014, 34(10): 2 743-2 751.
[2] 傅霞萍, 应义斌, 陆辉山, 等. 应用多种近红外建模方法分析梨的坚实度[J]. 光谱学与光谱分析, 2007, 27(5): 911-915.
[3] 柴阿丽, 廖宁放, 田立勋, 等. 基于高光谱成像和判别分析的黄瓜病害识别[J]. 光谱学与光谱分析, 2010, 30(5): 1 357-1 361.
[4] 孙瑞东, 于海业, 于常乐, 等. 基于图像处理的黄瓜叶片含水量无损检测研究[J]. 农机化研究, 2008(7): 87-89.
[5] 石吉勇, 邹小波, 赵杰文, 等. 高光谱图像技术检测黄瓜叶片的叶绿素叶面分布[J]. 分析化学, 2011, 39(2): 243-247.
[6] 程帆, 赵艳茹, 余克强, 等. 基于高光谱技术的病害早期胁迫下黄瓜叶片中过氧化物酶活性的研究[J]. 光谱学与光谱分析, 2017, 37(6): 1 861-1 865.
[7] 卢娜, 韩平, 王纪华. 高光谱成像技术在果蔬品质安全无损检测中的应用[J]. 食品安全质量检测学报, 2017, 8(12): 4 594-4 601.
[8] 冯蕾. 基于电子鼻及低场核磁共振的黄瓜与樱桃番茄新鲜度智能检测研究[D]. 无锡: 江南大学, 2019: 11-18.
[9] 邹小波, 陈正伟, 石吉勇, 等. 基于近红外高光谱图像的黄瓜叶片色素含量快速检测[J]. 农业机械学报, 2012, 43(5): 152-156.
[10] NIE Li-xing, DAI Zhong, MA Shuang-cheng. Enhanced accuracy of near-infrared spectroscopy for traditional chinese medicine with competitive adaptive reweighted sampling[J]. Analytical Letters, 2016, 49(14): 2 259-2 267.
[11] 霍迎秋, 张晨, 李宇豪, 等. 高光谱图像结合机器学习方法无损检测猕猴桃[J]. 中国农机化学报, 2019, 40(4): 71-77.
[12] 王海龙, 杨国国, 张瑜, 等. 竞争性自适应重加权算法和相关系数法提取特征波长检测番茄叶片真菌病害[J]. 光谱学与光谱分析, 2017, 37(7): 2 115-2 119.
[13] 廖宜涛, 樊玉霞, 成芳, 等. 连续投影算法在猪肉pH值无损检测中的应用[J]. 农业工程学报, 2010, 26(增刊1): 379-383.
[14] SUN Ye, XIAO Hui, TU Si-cong, et al. Detecting decayed peach using a rotating hyperspectral imaging testbed[J]. LWT-Food Science and Technology, 2018, 87: 326-332.
[15] 吴迪, 宁纪锋, 刘旭, 等. 基于高光谱成像技术和连续投影算法检测葡萄果皮花色苷含量[J]. 食品科学, 2014, 35(8): 57-61.
[16] 张婷婷, 赵宾, 杨丽明, 等. 基于高光谱成像技术结合SPA和GA算法测定甜玉米种子电导率[J]. 光谱学与光谱分析, 2019, 39(8): 2 608-2 613.
[17] 周竹, 刘洁, 李小昱, 等. 霉变板栗的近红外光谱和神经网络方法判别[J]. 农业机械学报, 2009, 40(增刊1): 109-112.
[18] 李静, 徐路路. 基于机器学习算法的研究热点趋势预测模型对比与分析: BP神经网络、支持向量机与LSTM模型[J]. 现代情报, 2019(4): 23-33.
[19] 李帅, 单国华, 贾丽霞, 等. 基于BP神经网络的棉花颜色级预测[J]. 棉纺织技术, 2019, 47(3): 68-71.
[20] 李丹, 何建国, 刘贵珊, 等. 基于高光谱成像技术的小黄瓜水分无损检测[J]. 红外与激光工程, 2014, 43(7): 2 393-2 397.