用近红外高光谱图像区分不同品质的建筑涂料

Use of Near-Infrared Hyperspectral Images to Differentiate Architectural Coatings with Different Qualities

市场上出售的建筑涂料品种繁多,型号和品质不尽相同。利用高光谱技术区分不同品质的建筑涂料。获取同一颜色四个不同品质、不同品牌建筑涂料(品牌A,B,C,D)的近红外高光谱图像,利用ANOVA(analysis of variance)方法发现1 283和2 447nm为区分四个品牌涂料的最优波段。构建比值指数R_(1 283)/R_(2 447)并对其结果进行阈值分割,将分割结果与最大似然分类精度进行了对比。结果表明除品牌C与D之间J-M距离外,其他涂料间J-M距离均大于1.8;而R_(1 283)/R_(2 447)指数分割精度最低为87.54%,相应最大似然分类精度为95.63%,其他品牌涂料阈值分割与最大似然分类精度均达到90%以上。因此,R_(1 283)/R_(2 447)指数能够较好地区分不同品牌的建筑涂料。该研究结果可为建筑涂料识别、装修质量验收、合格评定提供技术支持。

Architectural coatings sold in market fall into many categories which mean different models and qualities.The research plans to differentiate different kinds of architectural coatings in quality using hyperspectral technology.Near-Infrared hyperspectral images of four kinds of architectural coatings（in a descending quality order of brand A,B,C,and D）in same color were acquired.The optimal wavelengths were selected at 1 283 and 2 447 nm to differentiate the four kinds of coatings through ANOVA（Analysis of Variance）method.The band ratio index of R_（1 283）/R_（2 447） was built and the results were segmented into the corresponding coatings,and the accuracies of segmentation were compared with that from Maximum Likely Classification（MLC）.The results indicated all J-M distances are more than 1.8except between C and D;the lowest accuracy of 87.54%in segmentation and 95.63%in MLC were both from brand D,and others＇ accuracies all were over 90% in both ratio index and MLC.Therefore,the ratio index R_（1 283）/R_（2 447） could be used to distinguish different kinds of architectural coatings.Also,the research could provide support for identification,quality acceptance,as well as conformity assessment of architectural coatings.