Intelligent identification  of film on cotton based on hyperspectral imaging and convolutional neural network

Liu, Zongbin; Zhao, Longmao; Xin, Yu; Zhang, Yiqing; Cui, Jianping; Ni, Chao; Zhang, Laigang

doi:10.1177/00368504221137461

Cited by 3 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the current landscape, a greater concentration of research endeavors are directed towards the detection of foreign fibers within cotton. Various technical methods, including machine vision ( Zhang et al., 2011 ; Zhang and Li, 2014 ), hyperspectral imaging ( Liu et al., 2022 ), and near-infrared spectroscopy ( Du et al., 2023 ), have been harnessed to detect foreign fibers present in both lint and seed cotton samples. Researchers have also delved into studies focusing on the identification of non-foreign fiber impurities, specifically plant-based impurities, within both seed and lint cotton.…”

Section: Introductionmentioning

confidence: 99%

Cotton-Net: efficient and accurate rapid detection of impurity content in machine-picked seed cotton using near-infrared spectroscopy

Li,

Zhou,

Zhang

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

Widespread adoption of machine-picked cotton in China, the impurity content of seed cotton has increased significantly. This impurity content holds direct implications for the valuation of seed cotton and exerts a consequential influence on the ensuing quality of processed lint and textiles. Presently, the primary approach for assessing impurity content in seed cotton primarily depends on semi-automated testing instruments, exhibiting suboptimal detection efficiency and not well-suited for the impurity detection requirements during the purchase of seed cotton. To address this challenge, this study introduces a seed cotton near-infrared spectral (NIRS) data acquisition system, facilitating the rapid collection of seed cotton spectral data. Three pretreatment algorithms, namely SG (Savitzky-Golay convolutional smoothing), SNV (Standard Normal Variate Transformation), and Normalization, were applied to preprocess the seed cotton spectral data. Cotton-Net, a one-dimensional convolutional neural network aligned with the distinctive characteristics of the seed cotton spectral data, was developed in order to improve the prediction accuracy of seed cotton impurity content. Ablation experiments were performed, utilizing SELU, ReLU, and Sigmoid functions as activation functions. The experimental outcomes revealed that after normalization, employing SELU as the activation function led to the optimal performance of Cotton-Net, displaying a correlation coefficient of 0.9063 and an RMSE (Root Mean Square Error) of 0.0546. In the context of machine learning modeling, the LSSVM model, developed after Normalization and Random Frog algorithm processing, demonstrated superior performance, achieving a correlation coefficient of 0.8662 and an RMSE of 0.0622. In comparison, the correlation coefficient of Cotton-Net increased by 4.01%. This approach holds significant potential to underpin the subsequent development of rapid detection instruments targeting seed cotton impurities.

show abstract

Section: Introductionmentioning

confidence: 99%

Cotton-Net: efficient and accurate rapid detection of impurity content in machine-picked seed cotton using near-infrared spectroscopy

Li,

Zhou,

Zhang

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

Cotton-YOLO: Improved YOLOV7 for rapid detection of foreign fibers in seed cotton

Li,

Ma,

et al. 2024

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

Analysis of progress in research on technology for the detection and removal of foreign fibers

Shunqi,

Kai,

Xichun

et al. 2024

Textile Research Journal

View full text Add to dashboard Cite

We focus in this review on the pre-processing devices used, the cotton pipeline, the rejection system, the acquisition and processing of information from images of raw cotton, and measurements of the rate of dynamic flow of the cotton stream. The results show that raw cotton fluffs into a material with a more uniform thickness, and adequately separating the cotton bunch can improve the subsequent detection and removal of foreign fibers in it. Moreover, research that combines the structure of the cotton pipeline with the optimization of the structure of the nozzle plate is important for improving the rejection of foreign fibers in cotton. Furthermore, a combination of multiple light sources and arrays of charge-coupled device cameras can improve the quality of images of raw cotton, but such key parameters as the power and wavelength of the source of light need to be optimized. As any single algorithm for image segmentation and feature extraction struggles to adapt to the identification of different kinds of foreign fibers, it is important to explore a combination of algorithms to this end, and to develop new techniques of foreign fiber detection based on deep learning. Finally, the structure and parameters of processing of the system for the identification and removal of foreign fibers are important, including the relative distance between the sensor and the nozzle, the width of the detection channel, and the rate of flow of the cotton stream.

show abstract

Intelligent identification of film on cotton based on hyperspectral imaging and convolutional neural network

Cited by 3 publications

References 30 publications

Cotton-Net: efficient and accurate rapid detection of impurity content in machine-picked seed cotton using near-infrared spectroscopy

Cotton-Net: efficient and accurate rapid detection of impurity content in machine-picked seed cotton using near-infrared spectroscopy

Cotton-YOLO: Improved YOLOV7 for rapid detection of foreign fibers in seed cotton

Analysis of progress in research on technology for the detection and removal of foreign fibers

Contact Info

Product

Resources

About