项目名称: 基于近红外光谱和场发射扫描电镜图像信息融合的山羊绒品质检测的研究
项目编号: No.61265011
项目类型: 地区科学基金项目
立项/批准年度: 2013
项目学科: 无线电电子学、电信技术
项目作者: 吴桂芳
作者单位: 内蒙古农业大学
项目金额: 48万元
中文摘要: 项目针对当今山羊绒生产与交易过程中品质信息检测手段严重匮乏的问题,以内蒙古典型的山羊绒为研究对象,研究基于近红外光谱技术和场发射扫描电子显微镜成像技术的山羊绒品质检测方法。通过近红外光谱技术采集山羊绒的光谱信息,应用神经网络和遗传算法等模式识别方法建立山羊绒品质与特征光谱信息之间的耦合关系,建立山羊绒净绒率、回潮率、含脂率、含硫量和氨基酸含量的近红外光谱检测模型。通过电子显微成像技术采集绒毛的表面形态信息,从显微图像中提取山羊绒纤维表面鳞片的形态学特征参数和纹理学特征参数。在此基础上,开展近红外光谱和场发射扫描电子显微镜成像理论相结合的检测技术进行绒毛品山羊绒品质分级、品种鉴别、纺织性能鉴定等研究。本项目采用扫描电镜成像和光谱技术将绒毛表面微观信息及品质指标数字化,实现绒毛品质的计算机快速、无损、客观地检测,研究成果对其它天然纤维的品质检测与分级也有重要的应用价值。
中文关键词: 山羊绒;扫描电镜图像分析;近红外光谱;磨损;拉伸
英文摘要: Aiming at the problem and deficiency of current technologies in the information acquisition system of cashmere trading and production, in this project, by taking typical varieties Inner Mongolia cashmere as the research objects, the detection measurements of cashmere qualities and data mining techniques were developed based on near infrared spectroscopy and field-emission scanning electron microscope image processing technologies. The indexes of yield, moisture content protein, ash content, fat content of cashmere and wool materials were proposed by using infrared spectral techniques; on the other hand, the morphology characteristics includes geometric shape of fiber, texture feature and region properties of the scale of cashmere were studied based on field-emission scanning electron microscope image processing technologies. The relatively new data analysis methods such as back-propagation neural network, wavelet de-noised method, and genetic algorithm theories were used to build the quantitative relation models between near infrared spectroscopy and the features index of cashmere; morphology analysis methods of image were applied to build the quality evaluation models of cashmere fiber. On the basis, the studies of cashmere qualities grading, variety identification and spinning performance evaluation. This proj
英文关键词: Cashmere;Scanning electron microscope image processing;Infrared spectroscopy;Wear resistance;Tensile properties