Early bruising detection of 'Korla' pears by low-cost visible-LED structured-illumination reflectance imaging and feature-based classification models
文献类型: 外文期刊
作者: Mei, Mengwen 1 ; Cai, Zhonglei 1 ; Zhang, Xinran 1 ; Sun, Chanjun 2 ; Zhang, Junyi 1 ; Peng, Huijie 1 ; Li, Jiangbo 5 ; Shi, Ruiyao 5 ; Zhang, Wei 7 ;
作者机构: 1.Shihezi Univ, Coll Mech & Elect Engn, Shihezi, Peoples R China
2.Jiangsu Univ, Jiangsu Prov & Educ Minist, Synergist Innovat Ctr Modern Agr Equipment, Zhenjiang, Peoples R China
3.Xinjiang Prod & Construct Corps Key Lab Modern Agr, Shihezi, Peoples R China
4.Minist Educ, Engn Res Ctr Prod Mechanizat OasisCharacterist Cas, Shihezi, Peoples R China
5.Beijing Acad Agr & Forestry Sci, Intelligent Equipment Res Ctr, Beijing, Peoples R China
6.Natl Engn Res Ctr Informat Technol Agr, Beijing, Peoples R China
7.Anhui Univ Finance & Econ, Dept Comp Technol & Sci, Bengbu, Peoples R China
关键词: pears; early bruise detection; classification; machine learning; visible LED structured illumination
期刊名称:FRONTIERS IN PLANT SCIENCE ( 影响因子:5.6; 五年影响因子:6.8 )
ISSN: 1664-462X
年卷期: 2023 年 14 卷
页码:
收录情况: SCI
摘要: IntroductionNondestructive detection of thin-skinned fruit bruising is one of the main challenges in the automated grading of post-harvest fruit. The structured-illumination reflectance imaging (SIRI) is an emerging optical technique with the potential for detection of bruises.MethodsThis study presented the pioneering application of low-cost visible-LED SIRI for detecting early subcutaneous bruises in 'Korla' pears. Three types of bruising degrees (mild, moderate and severe) and ten sets of spatial frequencies (50, 100, 150, 200, 250, 300, 350, 400, 450 and 500 cycles m-1) were analyzed. By evaluation of contrast index (CI) values, 150 cycles m-1 was determined as the optimal spatial frequency. The sinusoidal pattern images were demodulated to get the DC, AC, and RT images without any stripe information. Based on AC and RT images, texture features were extracted and the LS-SVM, PLS-DA and KNN classification models combined the optimized features were developed for the detection of 'Korla' pears with varying degrees of bruising.Results and discussionIt was found that RT images consistently outperformed AC images regardless of type of model, and LS-SVM model exhibited the highest detection accuracy and stability. Across mild, moderate, severe and mixed bruises, the LS-SVM model with RT images achieved classification accuracies of 98.6%, 98.9%, 98.5%, and 98.8%, respectively. This study showed that visible-LED SIRI technique could effectively detect early bruising of 'Korla' pears, providing a valuable reference for using low-cost visible LED SIRI to detect fruit damage.
- 相关文献
作者其他论文 更多>>
-
Navigation line extraction algorithm for corn spraying robot based on YOLOv8s-CornNet
作者:Guo, Peiliang;Diao, Zhihua;Ma, Shushuai;He, Zhendong;Zhao, Suna;Zhao, Chunjiang;Li, Jiangbo;Zhang, Ruirui;Yang, Ranbing;Zhang, Baohua
关键词:agricultural robotics; computer vision; deep learning; navigation line extraction; network lightweight
-
Online detection of lycopene content in the two cultivars of tomatoes by multi-point full transmission Vis-NIR spectroscopy
作者:Li, Sheng;Wang, Qingyan;Shi, Ruiyao;Li, Jiangbo;Li, Sheng;Yang, Xuhai;Zhang, Qian
关键词:Tomato quality; Nondestructive evaluation; Chemometrics; Least angle regression; Model optimization
-
Detection of early decayed oranges by using hyperspectral transmittance imaging and visual coding techniques coupled with an improved deep learning model
作者:Cai, Letian;Zhang, Yizhi;Shi, Ruiyao;Li, Xuetong;Li, Jiangbo;Cai, Letian;Zhang, Junyi;Diao, Zhihua
关键词:Citrus decay detection; Sample expansion; Spectral visual encoding; Improved deep learning; Model optimization
-
Identification of early decayed oranges using structured-illumination reflectance imaging coupled with fast demodulation and improved image processing algorithms
作者:Li, Jiangbo;Lu, Yuzhen;Lu, Renfu
关键词:Citrus decay; Defect segmentation; Brightness transformation; Image enhancement; Classification
-
Determination of soluble solids content of multiple varieties of tomatoes by full transmission visible-near infrared spectroscopy
作者:Li, Sheng;Yang, Xuhai;Zhang, Qian;Li, Sheng;Li, Jiangbo;Wang, Qingyan;Shi, Ruiyao;Li, Sheng;Yang, Xuhai;Zhang, Qian;Li, Sheng;Yang, Xuhai;Zhang, Qian;Li, Sheng;Yang, Xuhai;Zhang, Qian
关键词:tomato; soluble solids content; online detection; full transmission; quantitative analysis model
-
Microfungi Associated with Peach Branch Diseases in China
作者:Zhou, Ying;Li, Shifang;Zhou, Ying;He, Zhizheng;Zhang, Wei;Liu, Mei;Song, Jinyan;Yan, Jiye;Zhou, Ying;Fan, Zaifeng;Manawasinghe, Ishara S.
关键词:diversity; peach diseases; morphology; phylogenetic analyses; new species; new records
-
Fast detection of the early decay in oranges using visible-LED structured- illumination imaging combined with spiral phase transform and feature-based classification model
作者:Cai, Zhonglei;Zhang, Junyi;Sun, Chanjun;Zhang, Yizhi;Shi, Ruiyao;Zhang, Junyi;Li, Jiangbo;Zhang, Yizhi;Zhang, Hailiang;Li, Jiangbo
关键词:oranges; early decay detection; structured-illumination imaging; spiral phase transform; classification model