摘要
根据电可调滤光器光谱特性,以偏最小二乘回归建模为基础,提出了使用波长贡献度初选后进行全组合特征波长提取的方法,并利用基于声光可调滤光器所采集的猪肉光谱图像及其所对应的挥发性盐基氮含量化学指标,对该特征光谱提取方法的性能进行测试验证。结果表明,该算法能够有效确定由电可调滤光器获取的光谱图像的特征波长。
An algorithm was proposed for the characteristic of the important wavelengths of the spectral images acquired by electronically tunable filters. The optimal wavelengths are determined by electing the candidates according to the wavelength-specific contributions based on a valid PLSR model firstly, and then followed by an exhaustive analysis of the combinations of the candidate wavelengths. The performance of the algorithm was tested using the spectral images of fresh pork acquired by an acousto-optical tunable filter-based spectral imager and the corresponding chemical indices of total volatile basic nitrogen. The results showed that the proposed algorithm could determine effectively the characteristic wave-lengths of the spectral images acquired by electronically tunable filters.
出处
《南京林业大学学报（自然科学版）》
CAS
CSCD
北大核心
2014年第2期137-140,共4页
Journal of Nanjing Forestry University：Natural Sciences Edition
基金
江苏省科技支撑计划(BE2011396)
高等学校博士学科点科研基金资助项目(20103204110006)
江苏省研究生创新工程项目(2011039)
关键词
电可调滤光器
光谱图像分析
光谱降维
偏最小二乘回归
spectral electronically tunable filter
spectral images analysis
spectral dimensionality reduction
partial least squares regression
