The application of computer vision combining with deep leaning techniques for rapid discrimination of adulterated star anise powder

Authors

CHEN Jinxing, Fujian CCIC-Fairreach Food Safety Testing Co., Ltd., Fuzhou, Fujian 350008, ChinaFollow

Abstract

Objective: This study aims to design a novel approach, utilizing computer vision combining with deep learning, for rapid determination the adulteration in star anise powder. Methods: Collected the original images of star anise powder with varying adulteration ratios. Employing preprocessing and data enhancement techniques, an image dataset was curated. Subsequently, a SqueezeNet model was constructed and compared with five machine learning models, including Support Vector Machine （SVM）, K-Nearest Neighbor Learning （KNN）, Random Forest （RF）, Gradient Boosting Tree （GBT）, and Multilayer Perceptron （MLP）. Results: The highest accuracy achieved by the five machine learning models was only 66.37%, while the accuracy of the SqueezeNet model was 99.42%. The results showed that SqueezeNet model was better than these machine learning models in identifying the adulteration in star anise powder. Conclusion: The proposed detection method based on computer vision combining with SqueezeNet model can effectively identify the adulteration in star anise powder. This method is easy to operate, and provides a novel technique for the rapid detection of food adulteration.

Publication Date

1-30-2024

First Page

42

Last Page

47,69

DOI

10.13652/j.spjx.1003.5788.2023.60149

Recommended Citation

Jinxing, CHEN (2024) "The application of computer vision combining with deep leaning techniques for rapid discrimination of adulterated star anise powder," Food and Machinery: Vol. 39: Iss. 12, Article 7.
DOI: 10.13652/j.spjx.1003.5788.2023.60149
Available at: https://www.ifoodmm.cn/journal/vol39/iss12/7

References

[1] MUHSINAH A B, MAQBUL M S, MAHNASHI M H, et al. Antibacterial activity of Illicium verum essential oil against MRSA clinical isolates and determination of its phyto-chemical components[J]. J King Saud Univ Sci, 2022, 34: 101800.
[2] GAVAHIAN M, CHU Y, LORENZO J, et al. Essential oils as natural preservatives for bakery products: Understanding the mechanisms of action, recent findings, and applications[J]. Crit Rev Food Sci Nutr, 2020, 60（2）: 310-321.
[3] PATRA J K, DAS G, BOSE S, et al. Star anise （Illicium verum）: Chemical compounds, antiviral properties, and clinical relevance[J]. Phytother Res, 2020, 34（6）: 1 248-1 267.
[4] EL-SAYED S M, YOUSSEF A M. Potential application of herbs and spices and their effects in functional dairy products[J]. Heliyon, 2019, 5（6）: 1 989.
[5] VERMAAK I, VILJOEN A, LINDSTRM S W. Hyperspectral imaging in the quality control of herbal medicines: The case of neurotoxic Japanese star anise[J]. J Pharm Biomed Anal, 2013, 75: 207-213.
[6] ZHANG M T, SHI Y H, SUN W, et al. An efficient DNA barcoding based method for the authentication and adulteration detection of the powdered natural spices[J]. Food Control, 2019, 106: 106745.
[7] SHEN Y, VAN BEEK T A, CLAASSEN F W, et al. Rapid control of Chinese star anise fruits and teas for neurotoxic anisatin by direct analysis in real time high resolution mass spectrometry[J]. J Chromatogr A, 2012, 1 259: 179-186.
[8] JOSHI V C, SRINIVAS P V, KHAN I A. Rapid and easy identification of Illicium verum Hook. f. and its adulterant Illicium anisatum Linn. by fluorescent microscopy and gas chromatography[J]. J AOAC Int, 2005, 88（3）: 703-706.
[9] LU Y, WANG W, NI X Z, et al. Non-destructive discrimination of Illicium verum from poisonous adulterant using Vis/NIR hyperspectral imaging combined with chemometrics[J]. Infrared Phys Technol, 2020, 111: 103509.
[10] 高海生. 味精及香辛料掺假的鉴别检验（下）[J]. 物流工程与管理, 1995, 17（6）: 29-30. GAO H S. Identification test of adulteration of monosodium glutamate and spices （II）[J]. Logistics Eng Manag, 1995, 17（6）: 29-30.
[11] GOUTAM K S, SANTOS K D, POONAM S. A deep learning-based distracted driving detection solution implemented on embedded system[J]. Multimedia Tools and Applications, 2023, 82（8）: 11 697-11 720.
[12] WU X J, ZHAO Z L, TIAN R L, et al. Total synchronous fluorescence spectroscopy coupled with deep learning to rapidly identify the authenticity of sesame oil[J]. Spectrochim Acta, Part A, 2020, 244: 118841.
[13] JAHANBAKHSHI A, MOMENY M, MAHMOUDI M, et al. Classification of sour lemons based on apparent defects using stochastic pooling mechanism in deep convolutional neural networks[J]. Sci Hortic, 2020, 263: 109133.
[14] ARORA M, MANGIPUDI P, DUTTA M K. Deep learning neural networks for acrylamide identification in potato chips using transfer learning approach[J]. J Ambient Intell Hum Comput, 2021, 12（12）: 10 601-10 614.
[15] 夏亮. 基于轻量级卷积神经网络的人脸检测研究[D]. 广州: 广州大学, 2023: 2-7. XIA L. Research on face detection based on lightweight convolutional neural networks[D]. Guangzhou: Guangzhou University, 2023: 2-7.
[16] DENG L M, LI J, HAN Z Z. Online defect detection and automatic grading of carrots using computer vision combined with deep learning methods[J]. LWT-Food Sci Technol, 2021, 149（2）: 111832.
[17] MESA A R, CHIANG J Y. Multi-input deep learning model with RGB and hyperspectral imaging for banana grading[J]. Agriculture, 2021, 11（8）: 687.
[18] MOINO M J. Plum ripeness analysis in real environments using deep learning with convolutional neural networks[J]. Agronomy, 2021, 11（11）: 2 353.
[19] ASHWINKUMAR S, RAJAGOPAL S, MANIMARAN V, et al. Automated plant leaf disease detection and classification using optimal MobileNet based convolutional neural networks[J]. Mater Today: Proc, 2022, 51: 480-487.
[20] GANGOPADHYAY R, KULKARNI P T, BONONI A. Throughput performance of multiwavelength shufflenet with/without wavelength conversion[J]. J Opt Commun, 2003, 24（3）: 42-49.
[21] PATEL A. Unet based xception model for prostate cancer segmentation from MRI images[J]. Multimed Tools and Appl, 2021, 12: 1-17.
[22] PRADANA-LOPEZ S, PEREZ-CALABUIG A M, CANCILLA J C, et al. Deep transfer learning to verify quality and safety of ground coffee[J]. Food Control, 2021, 122: 107801.
[23] IZQUIERDO M, LASTRA-MEJíAS M, GONZáLEZ-FLORES E, et al. Visible imaging to convolutionally discern and authenticate varieties of rice and their derived flours[J]. Food Control, 2020, 110: 106971.
[24] SUHARJIT O, ELWIREHARDJA G N, PRAYOGA J S. Oil palm fresh fruit bunch ripeness classification on mobile devices using deep learning approaches[J]. Comput Electron Agric, 2021, 188: 106185.
[25] BERNARDO L S, DAMASEVICIUS R, DE ALBUQUERQUE V H C, et al. A hybrid two-stage squeezenet and support vector machine system for parkinson's disease detection based on handwritten spiral patterns[J]. Int J Appl Math Comput Sci, 2021, 31（4）: 31.
[26] 王文伟, 张雯. 基于局部二值模式和深度学习的人脸识别[J]. 计算机应用, 2015, 35（5）: 1 474-1 478. WANG W W, ZHANG W. Journal of computer applications[J]. J Comput Appl, 2015, 35（5）: 1 474-1 478.
[27] ZOU B X, LIN J R. Contour extraction research of image[J]. Computer Engineering and Applications, 2008, 44（25）: 161-165.