文献类型： 外文期刊

作者： Liu, Zongbin ¹ ; Zhao, Ling ¹ ; Yu, Xin ¹ ; Zhang, Yiqing ¹ ; Cui, Jianping ² ; Ni, Chao ³ ; Zhang, Laigang ¹ ;

作者机构： 1.Liaocheng Univ, Sch Mech & Automobile Engn, Liaocheng, Peoples R China

2.Res Inst Econ Crops, Xinjiang Acad Agr Sci, Urumqi, Peoples R China

3.Nanjing Forestry Univ, Coll Mech & Elect Engn, Nanjing, Jiangsu, Peoples R China

4.Liaocheng Univ, Sch Mech & Automobile Engn, Liaocheng 252059, Peoples R China

5.Res Inst Econ Crops, Xinjiang Acad Agr Sci, Urumqi 830091, Peoples R China

关键词： Cotton; film; short-wave near-infrared hyperspectral imaging; principal component analysis; convolutional neural network

期刊名称：SCIENCE PROGRESS （ 影响因子：2.1； 五年影响因子：2.6 ）

ISSN： 0036-8504

年卷期： 2022 年 105 卷 4 期

页码：

收录情况： SCI

摘要： The identification of the film on cotton is of great significance for the improvement of cotton quality. Most of the existing technologies are dedicated to removing colored foreign fibers from cotton using photoelectric sorting methods. However, the current technologies are difficult to identify colorless transparent film, which becomes an obstacle for the harvest of high-quality cotton. In this paper, an intelligent identification method is proposed to identify the colorless and transparent film on cotton, based on short-wave near-infrared hyperspectral imaging and convolutional neural network (CNN). The algorithm includes black-and-white correction of hyperspectral images, hyperspectral data dimensionality reduction, CNN model training and testing. The key technology is that the features of the hyperspectral image data are degraded by the principal component analysis (PCA) to reduce the amount of computing time. The main innovation is that the colorless and transparent film on cotton can be accurately identified through a CNN with the performance of automatic feature extraction. The experimental results show that the proposed method can greatly improve the identification precision, compared with the traditional methods. After the simulation experiment, the method proposed in this paper has a recognition rate of 98.5% for film. After field testing, the selection rate of film is as high as 96.5%, which meets the actual production needs.