Non-Destructive Detection of Ready-to-Eat Sea Cucumber Freshness Based on Hyperspectral Imaging
WANG Hui-hui1,2, ZHANG Shi-lin1,2, LI Kai1,2, CHENG Sha-sha1, TAN Ming-qian1, TAO Xue-heng1,2, ZHANG Xu1,2*
1. National Engineering Research Center of Seafood, Dalian Polytechnic University，Dalian 116000, China
2. School of Mechanical Engineering and Automation, Dalian Polytechnic University, Key Laboratory for Seafood Processing Technology and Equipment of Liaoning Province, Dalian 116000, China
Abstract：Freshness is a key index for quality regulation and assurance during the processing and storage of ready-to-eat sea cucumbers. The usual freshness detection methods, sensory evaluation and physicochemical detection, are inadequate for mass standardized and industrial production. In this study, a nondestructive freshness detection method based on hyperspectral imaging was proposed for ready-to-eat sea cucumber (RTESC). The characteristic wavelengths and images were first selected using Principal Component Analysis (PCA) and band ratio algorithm. According to the rottenness mechanism of RTESC, the correlation model between the texture features of hyperspectral images and the freshness degree of RTESC was established to achieve a fast, non-destructive and non-invasive evaluation of RTESC freshness. The effective dimensional-reduction method was adopted to address the massive data of hyperspectral images. According to the spectral absorption characteristics of the sea cucumber body wall, the wavelengths (474 and 985 nm) with significant chemical absorption characteristics were used as dividing points for band division. Thus, five sub-bands and the full band (400～1 000 nm) were acquired for data processing. Next, the bands were optimized using Image Principle Component Analysis (IPCA). Based on the calculated weight coefficients, the band-ratio image at 686 and 985 nm was selected as the characteristic image. On that basis, the gray-gradient co-occurrence matrix (GGCM), gray-level co-occurrence matrix (GLCM), and local binary pattern (LBP) descriptor were constructed to extract texture features. Meanwhile, the measured total volatile basic nitrogen (TVB-N) contents were used as the criterion. Using these three types of texture features as the input data, three freshness evaluation models based on particle swarm optimization (PSO) and back propagation neural network (BPNN) were established. The detection accuracies of these three models are 90%, 95%, and 80%, respectively. The results show that, using the texture characteristics extracted by GGCM from the hyperspectral images, the detection performances are favorable. The present study provides theoretical foundations and technological supports for the development of fast and non-destructive detection methods for RTESC.
基金资助: Marine public welfare industry research funding(201505029), Liaoning Provincial Natural Science Foundation(201602055), National Natural Science Foundation of China (31501561)
通讯作者:
张 旭
E-mail: zhangxu_dlut@163.com
作者简介: WANG Hui-hui，(1982—)，associate professor，Dalian Polytechnic University, School of Mechanical Engineering and Automation e-mail:
whh419@126.com
引用本文:
王慧慧，张士林，李 凯，程沙沙，谭明乾，陶学恒，张 旭. 基于高光谱图像的即食海参新鲜度无损检测[J]. 光谱学与光谱分析, 2017, 37(11): 3632-3640.
WANG Hui-hui, ZHANG Shi-lin, LI Kai, CHENG Sha-sha, TAN Ming-qian, TAO Xue-heng, ZHANG Xu. Non-Destructive Detection of Ready-to-Eat Sea Cucumber Freshness Based on Hyperspectral Imaging. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(11): 3632-3640.
[1] Li Qi, Cao Rong, Guo Yingying, et al. Modern Food Science and Technology, 2015，31(12): 313.
[2] Zou Xiaobo, Li Zhihua, Shi Jiyong, et al. Food Science, 2014, 35(8): 89.
[3] Wang Huihui, Zheng Yuansong, Gu Wei, et al. Carpathian Journal of Food Science & Technology, 2016, 7(4): 145.
[4] Agnar H Sivertsen, Takashi Kimiya, Karsten Heia. Journal of Food Engineering, 2011, 103: 317.
[5] Wang Wanjiao, Wang Songlei, He Xiaoguang, et al. Food Science, 2015, 16: 112.
[6] Mostafa Khojastehnazhanda, Mohammad Hadi Khoshtaghazaa, Barat Mojaradib, et al. Food Research International, 2014, 56(11): 25.
[7] Pu Hongbin, Sun Dawen, Ma Ji, et al. Meat Science, 2014，(8): 81.
[8] Cheng J H, Sun D W, Zeng X A. Innovative Food Science & Emerging Technologies, 2014, 21: 179.
[9] Yao Zefeng, Da Wensun. Talanta, 2013, (109): 74.
[10] Piotr Baranowski, Wojciech Mazurek, Joanna Wozniak, et al. Journal of Food Engineering, 2012, 110(3): 345.
[11] Zu Qin, Deng Wei, Wang Xiu, et al. Spectroscopy and Spectral Analysis, 2013, 33(10): 2745.
[12] Gamal El Masry, Sun Dawen, Paul Allen. Food. Research Internation, 2011, 44: 2624.
[13] Tian Youwen, Cheng Yi, Wang Xiaoqi, et al. Transactions of the Chinese Society of Agricultural Engineering, 2014, 12(30): 132.
[14] Su Wenhao, Liu Guishan, He Jianguo, et al. Journal of Zhejiang University, 2014, 40(2): 189.
[15] Wei Xi, Wang Zhangwei, Yang Tingting, et al. Transactions of the Chinese Society for Agricultural, 2015, 46(3): 1000.
[16] Zhu Beiwei, Han Bing. Food and Fermentation Industries, 2004, 4(30): 132.
[17] Zhang Leilei, Li Yongyu, Peng Yankun, et al. Transactions of the Chinese Society of Agricultural Engineering，2012，28(7)：254.
[18] Cheng Y L. Electronic Science and Technology, 2011, 24(11)：66.
