Zhang Yunlong, Zhang Laigang, Guo Zhijun, Zhang Ran
School of Mechanical and Automotive Engineering, Liaocheng University, Liaocheng 252000, China.
Institute of Information Science and Technology, Hunan Normal University, Changsha 410081, China.
Sensors (Basel). 2024 Sep 11;24(18):5892. doi: 10.3390/s24185892.
Due to the difficulty in distinguishing transparent and white foreign fibers from seed cotton in RGB images and in order to improve the recognition ability of deep learning (DL) algorithms for white, transparent, and multi-class mixed foreign fibers with different sizes in seed cotton, this paper proposes a method of combining hyperspectral imaging technology with a multi-module joint hierarchical residue network (MJHResNet). Firstly, a series of preprocessing methods are performed on the hyperspectral image (HSI) to reduce the interference of noise. Secondly, a double-hierarchical residual (DHR) structure is designed, which can not only obtain multi-scale information, but also avoid gradient vanishing to some extent. After that, a squeeze-and-excitation network (SENet) is integrated to reduce redundant information, improve the expression of model features, and improve the accuracy of foreign fiber identification in seed cotton. Finally, by analyzing the experimental results with advanced classifiers, this method has significant advantages. The average accuracy is 98.71% and the overall accuracy is 99.28%. This method has great potential for application in the field of foreign fiber identification in seed cotton.
由于在RGB图像中难以区分籽棉中的透明和白色外来纤维，且为了提高深度学习（DL）算法对籽棉中不同尺寸的白色、透明和多类混合外来纤维的识别能力，本文提出了一种将高光谱成像技术与多模块联合分层残差网络（MJHResNet）相结合的方法。首先，对高光谱图像（HSI）进行一系列预处理方法，以减少噪声干扰。其次，设计了一种双分层残差（DHR）结构，它不仅可以获取多尺度信息，还能在一定程度上避免梯度消失。之后，集成了挤压与激励网络（SENet）以减少冗余信息，提高模型特征的表达能力，并提高籽棉中外来纤维识别的准确率。最后，通过使用先进的分类器分析实验结果，该方法具有显著优势。平均准确率为98.71%，总体准确率为99.28%。该方法在籽棉外来纤维识别领域具有巨大的应用潜力。
