Abstract
［Objective］ To achieve accurate and non -destructive testing of key quality indicators of fresh grapes,we proposed a dual -channel improved convolutional neural network (CNN ) method for fresh grape quality inspection.［Methods］ A fiber -optic spectrometer and a CCD camera were used to collect visible near -infrared spectra and characterize the image information of grape samples.The dual channel improved CNN model was established and the Gramian angular field (GAF ) was used to convert one -dimensional spectral data into two-dimensional images for the extraction of effective features from spectra data.The convolutional layers with different sizes of convolution kernels were designed to extract features from the converted spectral two -dimensional images and grape characterization images,thus enhancing the comprehensive perception ability of the CNN model.On this basis,the dropout method was used for the fully connected layer to reduce and fuse the extracted features,ultimately achieving accurate prediction of key indicators of grape quality.［Results］］ Compared with other three grape quality inspecting methods,the CNN method showed the root mean square error decreases of 50.48%,57.44%,and 49.56% and the correlation coefficient increases of 4.89%,3.13%,and 2.17%,respectively.［Conclusion］ The dual -channel improved CNN method can achieve non -destructive testing of key indicators of grape quality
Publication Date
2-18-2025
First Page
89
Last Page
94
DOI
10.13652/j.spjx.1003.5788.2024.60131
Recommended Citation
Dan, WANG; Fangfei, LIU; and Xiaofeng, JI
(2025)
"Fresh grape quality inspection based on dual-channel improved convolutional neural network,"
Food and Machinery: Vol. 40:
Iss.
12, Article 12.
DOI: 10.13652/j.spjx.1003.5788.2024.60131
Available at:
https://www.ifoodmm.cn/journal/vol40/iss12/12
References
[1] 陈纪算,姜齐永,卢利群,等.红外表面加热结合冷冻处理对葡萄自动脱皮效果的影响 [J].食品与生物技术学报,2023,42(2):66-72.CHEN J S,JIANG Q Y,LU L Q,et al.Effect of infrared surface heating combined with freezing treatment on automatic peeling of grapes [J].Journal of Food Science and Biotechnology,2023,42(2):66-72.
[2] ZHOU X J,LIU W Z,LI K,et al.Discrimination of maturity stages of cabernet sauvignon wine grapes using visible-near-infrared spectroscopy [J].Foods,2023,12(23):4 371.
[3] 周向辉.葡萄籽提取物营养成分组成及其生物学功能研究进展[J].食品与机械,2023,39(7):228-233,240.ZHOU X H.Research progress in nutritional composition and biological function of grape seed extracts [J].Food & Machinery,2023,39(7):228-233,240.
[4] 高升.基于近红外相机成像的红提串缺陷检测 [J].食品与机械,2023,39(1):146-151.GAO S.Defect detection method of red globe grapes bunches based on near infrared camera imaging [J].Food & Machinery,2023,39(1):146-151.
[5] 李泽平,郭俊先,郭阳,等.基于支持向量机的无核白葡萄串分级系统设计与测试 [J].食品与机械,2021,37(10):106-111,246.LI Z P,GUO J X,GUO Y,et al.Design and test of the grading system for kernel-free white grapes with support vector machine[J].Food & Machinery,2021,37(10):106-111,246.
[6] ZHANG X,ZHOU C X,SUN Q,et al.Prediction of solid soluble content of green plum based on improved CatBoost [J].Agriculture,2023,13(6):1 122.
[7] QIAO J L,SU G Q,YUAN L,et al.Effect of swelling agent treatment on grape fruit quality and the application of electronic nose identification detection [J].Frontiers in Plant Science,2024,14:1292335.
[8] 何东健,王鹏,牛童,等.基于改进残差网络的田间葡萄霜霉病病害程度分级模型 [J].农业机械学报,2022,53(1):235-243.HE D J,WANG P,NIU T,et al.Classification model of grape downy mildew disease degree in field based on improved residual network [J].Transactions of the Chinese Society for Agricultural Machinery,2022,53(1):235-243.
[9] FALASCHETTI L,MANONI L,RIVERA R C F,et al.A low-cost,low-power and real-time image detector for grape leaf esca disease based on a compressed CNN [J].IEEE Journal on Emerging and Selected Topics in Circuits and Systems,2021,11(3):468-481.
[10] 刘文政,周雪健,平凤娇,等.基于可见—近红外光谱的鲜食葡萄成熟品质关键指标检测 [J].农业机械学报,2024,55(2):372-383.LIU W Z,ZHOU X J,PING F J,et al.Detection of key indicators of ripening quality in table grapes based on visible-near-infrared spectroscopy [J].Transactions of the Chinese Society for Agricultural Machinery,2024,55(2):372-383.
[11] 仝钰,庞新宇,魏子涵.基于 GADF-CNN 的滚动轴承故障诊断方法 [J].振动与冲击,2021,40(5):247-260.TONG Y,PANG X Y,WEI Z H.Fault diagnosis method of rolling bearing based on GADF-CNN [J].Journal of Vibration and Shock,2021,40(5):247-260.
[12] ROSEBROCK A.Deep learning for computer vision with python-starter bundle [M].Baltimore:PyImageSearch,2017:189-190.
[13] 刘彩云,李慧颖,张倩玮,等.基于紫外可见光谱的红葡萄酒关键质量指标快速监测 [J].农业机械学报,2023,54(6):401-409.LIU C Y,LI H Y,ZHANG Q W,et al.Rapid monitoring of key quality indicators of red wines based on UV-Vis spectroscopy[J].Transactions of the Chinese Society for Agricultural Machinery,2023,54(6):401-409.
[14] 陈远哲,王巧华,高升,等.皮蛋凝胶品质含水率和弹性的高光谱预测及其可视化 [J].食品科学,2022,43(2):324-331.CHEN Y Z,WANG Q H,GAO S,et al.Hyperspectral imaging for prediction and visualization of water content and springiness as indicators of the gel quality of preserved eggs[J].Food Science,2022,43(2):324-331.
[15] 刘畅,吴丹丹,王宁,等.基于二维相关红外光谱对 pH值影响大豆分离蛋白二级结构含量的快速分析 [J].食品科学,2024,45(17):26-34.LIU C,WU D D,WANG N,et al.Two-dimensional correlation infrared spectroscopy for rapid analysis of the effect of pH on the secondary structure content of soybean protein isolate [J].Food Science,2024,45(17):26-34.
[16] 李嘉宜,丁义文,艾民珉.光谱检测技术在禽蛋品质评价中的应用研究进展 [J].食品安全质量检测学报,2024,15(2):185-195.LI J Y,DING Y W,AI M M.Research progress on the application of spectroscopic detection technology in the quality evaluation of poultry eggs [J].Journal of Food Safety & Quality,2024,15(2):185-195.
[17] XU M,SUN J,YAO K S,et al.Developing deep learning based regression approaches for prediction of firmness and pH in Kyoho grape using Vis/NIR hyperspectral imaging [J].Infrared Physics & Technology,2022,120:104003.
[18] YE W X,YAN T Y,ZHANG C,et al.Detection of pesticide residue level in grape using hyperspectral imaging with machine learning [J].Foods,2022,11(11):1 609.
