Research on Almond Plumpness Detection Method Based on Terahertz Imaging Technology and Feature Extraction Method
HU Jun1, LÜ Hao-hao1, QIAO Peng1, HE Yong2, LIU Yan-de1*
1. School of Intelligent Electromechanical Equipment Innovation Research Institute, East China Jiaotong University，Nanchang 330013, China
2. School of Mechanical Engineering, Zhejiang University, Hangzhou 310027, China
Abstract：As a kind of nutrient-rich nut, it is of great economic value and practical significance to test the quality of almonds. Because of the almond hard shell, it is difficult for traditional detection methods to realize internal detection.In this paper, the emerging terahertz transmission imaging detection technology is used to study almond plumpness detection. Firstly, the terahertz spectral images of almonds with different fullness are acquired. Secondly, the terahertz spectra of sample free region, empty shell region and full almond region are extracted, respectively. To improve the accuracy of the model and reduce the computational effort, Competitive Adaptive Reweighting Sampling (CARS), Uninformative Variable Elimination (UVE), Successive Projections Algorithm (SPA), Monte Carlo Uninformative Variable Elimination (MCUVE) and Genetic Algorithm (GA) for feature extraction of terahertz spectral information. The corresponding Least squares support vector machine (LS-SVM), Random forest (RF) and K-nearest neighbor (KNN) qualitative discriminant models are established to detect and identify the full and empty regions of almonds.In addition, the terahertz feature image was to jpg format and then to RGB format, the shell image and kernel image were separated by G-channel extraction and image binarization, and the ratio of shell kernel pixels in the terahertz feature image was detected. The image of shell and kernel were separated by contour extraction and image binarization. The actual plumpness was the ratio of shell kernel pixels in the original image. The terahertz transmission imaging technique's feasibility for detecting the almond's plumpness was proved by calculating the error between the detection plumpness and the actual plumpness. The established KS-GA-RF model had the best identification effect, with an accuracy of 98.21%. According to the ratio of shell and kernel pixels, the corresponding detection and actual fullness were calculated, respectively, with an error of 16%. This study verified that combining terahertz graph and spectrum could well realize the visual detection of inner kernel plumpness of P. chinensis, providing a new idea for the accurate classification of almonds. It also delivers a theoretical reference for terahertz imaging to detect the plumpness of other nuts and has significant application value.
Key words：Plumpness of almond; Terahertz transmission imaging; Feature extraction; RF discriminant model
胡 军，吕豪豪，乔 鹏，贺 永，刘燕德. 基于太赫兹成像检测技术与特征提取方法结合巴旦木饱满度检测方法研究[J]. 光谱学与光谱分析, 2024, 44(07): 1896-1904.
HU Jun, LÜ Hao-hao, QIAO Peng, HE Yong, LIU Yan-de. Research on Almond Plumpness Detection Method Based on Terahertz Imaging Technology and Feature Extraction Method. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(07): 1896-1904.
[1] Khakrangin R, Mohamadzamani D, Javidan S M. Journal of Nuts, 2021, 12(1): 17.
[2] Sivaranjani A, Senthilrani S, Ashok Kumar B, et al. The Journal of Horticultural Science and Biotechnology, 2022, 97(2): 137.
[3] Karadağ A E, Kılıç A. Postharvest Biology and Technology, 2023, 198: 112229.
[4] Rong D, Xie L, Ying Y. Computers and Electronics in Agriculture, 2019, 162: 1001.
[5] Ríos-Reina R, Callejón R M, Amigo J M. Food Control, 2021, 130: 108365.
[6] Xu J, Xu D, Bai X, et al. Molecules, 2022, 27(20): 6776.
[7] Feng Z, Li W, Cui D. International Journal of Agricultural and Biological Engineering, 2022, 15(2): 204.
[8] Yu J, Ren S, Liu C, et al. The Journal of Agricultural Science, 2018, 156(9): 1103.
[9] Gao T, Zhang S, Sun H, et al. Journal of Food Process Engineering, 2022, 45(8): e14034.
[10] Sun X, Liu J. Journal of Infrared, Millimeter, and Terahertz Waves, 2020, 41(3): 307.
[11] Wang Q, Hameed S, Xie L, et al. Journal of Food Measurement and Characterization, 2020, 14(5): 2453.
[12] Di Girolamo F V, Pagano M, Tredicucci A, et al. Food Control, 2021, 123: 107700.
[13] Hu J, Shi H, Zhan C, et al. Foods, 2022, 11(21): 3498.
[14] Kubiczek T, Balzer J C. IEEE Access, 2022, 10: 88667.
[15] Sun X D, Cui D D, Shen Y, et al. Infrared Physics & Technology, 2022, 121: 104018.
[16] Fan W H, Burnett A, Upadhya P C, et al. Applied Spectroscopy, 2007, 61(6): 638.
[17] Dorney T D, Baraniuk R G, Mittleman D M. JOSA A, 2001, 18(7): 1562.
[18] Duvillaret L, Garet F, Coutaz J L. Applied Optics, 1999, 38(2): 409.
[19] Li Q, Huang Y, Song X, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2019, 214: 129.
[20] Ong P, Tung I C, Chiu C F, et al. Food Control, 2022, 136: 108886.
[21] Pang L, Wang L, Yuan P, et al. Infrared Physics & Technology, 2022, 123: 104143.
[22] Li J B, Zhang H L, Zhan B S, et al. Infrared Physics & Technology, 2020, 104: 103154.
[23] Zhou J, Hua Z. Applied Soft Computing, 2022, 123: 108964.
[24] Deng W, Yao R, Zhao H, et al. Soft Computing, 2019, 23(7): 2445.
[25] Jin G, Xu Y, Cui C, et al. Journal of the Science of Food and Agriculture, 2022, 102(13): 6123.
[26] Bo C, Lu H, Wang D. Multimedia Tools and Applications, 2018, 77(9): 10419.
[27] Poona N K, Van Niekerk A, Nadel R L, et al. Applied Spectroscopy, 2016, 70(2): 322.
[28] Kim M, Yeo Y, Shin H. Optics Communications, 2021, 497: 127198.
