Fast detection of the early decay in oranges using visible-LED structured- illumination imaging combined with spiral phase transform and feature-based classification model
文献类型： 外文期刊
作者： Cai, Zhonglei 1 ; Sun, Chanjun 2 ; Zhang, Yizhi 3 ; Shi, Ruiyao 3 ; Zhang, Junyi 1 ; Zhang, Hailiang 4 ; Li, Jiangbo 3 ;
作者机构： 1.Shihezi Univ, Coll Mech & Elect Engn, Shihezi 832003, Xinjiang, Peoples R China
2.Jiangsu Univ, Jiangsu Prov & Educ Minist Cosponsored Synergist I, Zhenjiang 212013, Jiangsu, Peoples R China
3.Beijing Acad Agr & Forestry Sci, Intelligent Equipment Res Ctr, Beijing 100097, Peoples R China
4.East China Jiaotong Univ, Coll Elect & Automat Engn, Nanchang 330013, Peoples R China
5.Natl Engn Res Ctr Informat Technol Agr, Beijing 100089, Peoples R China
关键词： oranges; early decay detection; structured-illumination imaging; spiral phase transform; classification model
期刊名称：INTERNATIONAL JOURNAL OF AGRICULTURAL AND BIOLOGICAL ENGINEERING （ 影响因子：2.2； 五年影响因子：2.5 ）
ISSN： 1934-6344
年卷期： 2024 年 17 卷 3 期
页码：
收录情况： SCI
摘要： The early decay of citrus can cause economic and serious food safety issues. The early decayed area has no obvious visual characteristics, making effective detection of this damage very difficult for the citrus industry. This study constructed a new detection system based on visible-light emitting diode (LED) structured-illumination imaging and proposed an effective methodology combined with a spiral phase transform (SPT) algorithm for the early detection of decayed oranges. Each sample obtained three phase-shifting pattern images with phase shifts of -2 pi/3, 0, and 2 pi/3 at a spatial frequency of 0.25 cycles/mm. Three strategies (i.e., the conventional three-phase-shifting method, 2-phase SPT, and 1-phase SPT) were used to demodulate the original patterned images to recover the direct component (DC) and amplitude component (AC) images. The partial least squares discriminant analysis (PLS-DA) and least squares support vector machine (LS-SVM) classification models were established based on the texture features of DC, AC, and RT (i.e. the ratio of AC to DC) images. Then, the random frog (RF) algorithm was used to simplify the optimal full-featured model. Finally, the LS-SVM model constructed using 7 texture features from the RT image obtained an average classification accuracy of 95.1% for all tested samples. This study indicates that the proposed structured-illumination imaging technique combined with 2-phase SPT and feature-based classification model can achieve the fast identification of early decayed oranges.
- 相关文献
作者其他论文 更多>>
-
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
-
Developing universal classification models for the detection of early decayed citrus by structured-illumination reflectance imaging coupling with deep learning methods
作者：Cai, Zhonglei;Li, Jiangbo;Cai, Zhonglei;Sun, Chanjun;Li, Jiangbo;Cai, Zhonglei;Zhang, Hailiang;Zhang, Yizhi;Li, Jiangbo
关键词：Citrus; Early detection; Image processing; Universal classification model; Deep learning
-
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
-
Fast Three-Dimensional Profilometry with Large Depth of Field
作者：Zhang, Wei;Han, Yu;Zhang, Manru;Zhu, Jiongguang;Li, Jiangbo
关键词：three-dimensional profilometry; large depth of field; time-domain Gaussian fitting; neural network
