Hyperspectral Imaging Technique to Analyse Fruit Quality using Deep Learning: Apple perspective
Keywords:
Hyperspectral Imaging, Pixel wise NIR spectra, Lasso regression, Naïve Bayes classification, YOLOv5, Bruise DetectionAbstract
Apple is the world's most consumed fruit after banana. Bruising is one of the major causes of losses incurred by fruit and vegetable suppliers. This study aims to automate the identification of apple bruises using hyperspectral imaging [HIS] technology and the YOLOv5 algorithm, which is the latest convolutional neural network (CNN) model. Traditional methods of bruised apple detection with red-green-blue (RGB [Red-Green-Blue] images are not very efficient, as color and texture may not be the dominant features for apple bruise identification. There are apple species such as Golden Delicious and Gala, which have dark red skin, and for those species, most RGB-based models give inaccurate results [1,5]. In the present study, honey-crisp and red-delicious apple species were scanned using a Resonon Pika NIR-320 hyperspectral imaging camera. The chemical characteristics of the scanned samples were analyzed in the laboratory. Lab-based chemical analysis results were used for testing and validation purposes. The two identified chemical properties used in this work are sugar content and O-H [oxygen-hydrogen] bonds. The results of this study will assist in establishing a standard bruise-detection system for industrial applications. The test results showed that the proposed detection model could recognize apple bruises with a mean average precision of 0.95 (mAP) and the classification accuracy of the validation system was found to be 96.22%.
Downloads
References
Professor Da-Wen Sun , “Hyperspectral Imaging for Food Quality Analysis and Control”, Food Refrigeration and Computerized Food Technology, National University of Ireland, Dublin (University College Dublin) , 2010
. Mehl, P. M., Chen, Y. R., Kim, M. S., & Chan, D. E. “Development of hyperspectral imaging techniques for the detection of apple surface defects and contaminations.” Journal of Food Engineering, 61(1), 67–81 , 2004 .[Crossref]
. Shahin, M. A., Tollner, E. W., McClendon, R. W., & Arabnia, H. R. “Apple classification based on surface bruises using image processing and neural networks” Transactions of the ASAE, 45(5), 1619–1627, 2002. [Crossref]
. Kleynen, O., Leemans, V., & Destain, M. F. “Development of a multispectral vision system for the detection of defects on apples.” Journal of Food Engineering, 69(1), 41–49 , 2005 .[Crossref]
. LEI FENG, SUSU ZHU, LEI ZHOU, YIYING ZHAO, YIDAN BAO, CHU ZHANG , AND YONG HE “Detection of Subtle Bruises on Winter Jujube Using Hyperspectral Imaging With Pixel-Wise Deep Learning Method ” College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China Key Laboratory of Spectroscopy Sensing, Ministry of Agriculture and Rural Affairs, Hangzhou 310058, China , May 16, 2019 [Crossref]
. Meng Zhang & Guanghui Li “Visual detection of apple bruises using AdaBoost algorithm and hyperspectral imaging”, International Journal of Food Properties, 21:1, 1598-1607, DOI: 10.1080/10942912.2018.1503299 , 2018[Crossref]
Abbott, J. A., Lu, R., Upchurch, B. L., & Stroshine, R. L. “Technologies for non-destructive quality evaluation of fruits and vegetables”, Horticultural Review, 20, 1–120, 1997
. Wenqian Huangab, Baihai Zhang, Jiangbo Lib, Chi Zhang,Early “Detection of Bruises on Apples Using Near-infrared Hyperspectral Image” , School of Automation, Beijing Institute of Technology, No.5 Zhongguancun South Street, Beijing, China 100081; Dept. of Intelligent Detection, National Engineering Research Center of
Intelligent Equipment for Agriculture, No.11 Shuguang Garden Middle Road, Beijing, China 100097, 2013[Crossref]
Zongmei Gao, Yuanyuan Shao, Guantao Xuan, Yongxian Wang,Yi Liu, Xiang Han “Real-time hyperspectral imaging for the in-field estimation of strawberry ripeness with deep learning”, Center for Precision and Automated Agricultural Systems, Department of Biological Systems Engineering, Washington State University, Prosser, WA 99350, USA ,College of Mechanical and Electrical Engineering, Shandong Agricultural University, Tai'an 271018, China, Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China, College of Agriculture, Food and Natural Resources, University of Missouri, Columbia, MO 65211, USA , 27 April 2020.[Crossref]
Zhenzhu Su, Chu Zhang , Tianying Yan, Jianan Zhu, Yulan Zeng, Xuanjun Lu, Pan Gao, Lei Feng, Linhai He, Lihui Fan ,” Application of Hyperspectral Imaging for Maturity and Soluble Solids Content Determination of Strawberry With Deep Learning Approaches” , Institute of Biotechnology, Zhejiang University, Hangzhou, China, School of Information Engineering, Huzhou University, Huzhou, China, College of Information Science and Technology, Shihezi University, Shihezi, China, Key Laboratory of Oasis Ecology Agriculture, Shihezi University, Shihezi, China, College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou, China, Key Laboratory of Spectroscopy Sensing, Ministry of Agriculture and Rural Affairs, Hangzhou, China, Hangzhou Liangzhu Linhai Vegetable and Fruit Professional Cooperative, Hangzhou, China. 10 September 2021[Crossref]
Irina Torres-Rodríguez , María-Teresa Sánchez , José-Antonio Entrenas , Miguel Vega-Castellote , Ana Garrido-Varo and Dolores Pérez-Marín “Hyperspectral Imaging for the Detection of Bitter Almonds in Sweet Almond Batches”, Department of Animal Production, University of Cordoba, Rabanales Campus, 14071 Córdoba, Spain. Department of Bromatology and Food Technology, University of Cordoba, Campus of Rabanales, 14071 Córdoba, Spain. 9 May 2022[Crossref]
Hu, Z., Tang, J., Zhang, P. and Jiang, J., 2020. Deep learning for the identification of bruised apples by fusing 3D deep features for apple grading systems. Mechanical Systems and Signal Processing, 145, p.106922.[Crossref]
Jawale, D. and Deshmukh, M., 2017, April. Real time automatic bruise detection in (Apple) fruits using thermal camera. In 2017 International Conference on Communication and Signal Processing (ICCSP) (pp. 1080-1085).[Crossref]
Zhu, X. and Li, G., 2019. Rapid detection and visualization of slight bruise on apples using hyperspectral imaging. International journal of food properties, 22(1), pp.1709-1719[Crossref]
Yi-Chich Chu and Chun-Hung Chen “Development of an on-line apple bruised detection System” March 2017[Crossref]
Qi Pang,Wenqian Huang,Shuxiang Fan,Quan Zhou,Zheli Wang,Xi Tian “DETECTION OF EARLY BRUISES ON APPLES USING HYPERSPECTRAL IMAGING COMBINING WITH YOLOV3 DEEP LEARNING ALGORITHM” , 2021[Crossref]
I. Baek, C. Eggleton, S. Gadsden, M. Kim”Selection of optimal band for developing multispectral system inspecting apples for defects". 30 April ,2019.[Crossref]
Wenkai Che, Laijun Sun, Q. Zhang, Wenyi Tan, Dandan Ye, Dan Zhang, Yangyang Liu ” Pixel based bruise region extraction of apple using Vis-NIR hyperspectral imaging” Key Laboratory of Electronics Engineering, College of Heilongjiang Province, Heilongjiang University, Harbin 150080, China, 14 January.[Crossref]
Sakshi Goel , Mohit Kumar , Yogesh ”An Improved Segmentation Algorithm for Detecting Defects on Fruit Surface” Amity University Uttar Pradesh, Noida, India ,2019[Crossref]
YU TANG 1,2, SHENGJIE GAO1 , JIAJUN ZHUANG1 , CHAOJUN HOU1 , (Member, IEEE), YONG HE3 , (Member, IEEE), XUAN CHU1 , AIMIN MIAO1 , AND SHAOMING LUO2 “Apple Bruise Grading Using Piecewise Nonlinear Curve Fitting for Hyperspectral Imaging Data” 4 August ,2020.
. Sunghoon Kwon, Sangmi Han, Sangin Lee “A small review and further studies on the LASSO”. Department of Applied Statistics, Konkuk University Department of Statistics, Seoul National University Received, 2013. [Crossref]
. Dr. Irina Rish,”An Empirical Study of the Naïve Bayes Classifier” , T.J. Watson Research Center, January 2001. [Crossref]
. Kim, M. S., Chen, Y. R., & Mehl, P. M. . “Hyperspectral reflectance and fluorescence imaging system for food quality and safety”, 2001. [Crossref]
. Xingkui Zhu, Shuchang Lyu, Xu Wang, Qi Zhao “TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios”,26 Aug 2021[Crossref]
. Peiyuan Jiang, Daji Ergu*, Fangyao Liu, Ying Cai, Bo Ma “A Review of Yolo Algorithm Developments” Key Laboratory of Electronic and Information Engineering (Southwest Minzu University),2022 [Crossref]
. Xiaolin Zhu & Guanghui Li “Rapid detection and visualization of slight bruise on apples using hyperspectral imaging”,13 Sep 2019. [Crossref].
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
