基于LCTF成像和ABS算法的小白菜光谱特征波段提取研究

基于液晶可调滤波器(LCTF)和CMOS组合的多光谱成像系统,在435~720nm波段范围内,以每隔5nm波段对小白菜叶片进行灰度值信息的提取,然后求出各个波段的灰度值平均值、标准差以及相关系数,并采用自适应波段选择法(ABS)提取出小白菜叶片的波段指数,最后通过波段指数的排序选取出小白菜叶片的有效特征波段。实验结果表明,用ABS的特征波段提取的算法,能够快速有效地获取小白菜叶片的光谱信息,在445nm、450nm、455nm、680nm、685nm、690nm、695nm和710nm波段具有较理想的波段指数值,有较大的光谱信息量。因此,这些波段可以很好地作为识别小白菜叶片的有效特征信息波段。

The research of extracting the characteristic wavebands for pakchoi applying for ABS algorithm based on the LCTF imaging techniques

Gray information of pakchoi leaves at the wavelength range of 435~720 nm with an interval of 5 nm are captured by using a multi-spectral imaging system which mainly consists of liquid crystal tunable filter (LCTF) and CMOS camera.Then, the average value, standard deviation and correlation coefficient for the gray value of images are calculated, and it has extracted the waveband index of pakchoi leaves by the way of adaptive band selection (ABS) method. Finally, the effective characteristic wavebands of pakchoi leaves are extracted through the sorting of waveband index.The experimental result shows that ABS algorithm using the extracted feature bands can quickly and efficiently obtain spectral information pakchoi leaves, and there are ideal waveband index values at 445 nm, 450 nm, 455 nm, 680 nm, 685 nm, 690 nm, 695 nm and 710 nm respectively, these wavebands have much discrete degree, rich multispectral information.therefore, these wavebands can be used as effective characteristic wavebands identification for pakchoi leaves.