光谱学与光谱分析
光譜學與光譜分析
광보학여광보분석
SPECTROSCOPY AND SPECTRAL ANALYSIS
2015年
2期
443-446
,共4页
张毛毛%杨忠%吕斌%刘亚娜%孙学东
張毛毛%楊忠%呂斌%劉亞娜%孫學東
장모모%양충%려빈%류아나%손학동
装饰纸%可见光光谱%主成分分析%表面视觉特征%分类
裝飾紙%可見光光譜%主成分分析%錶麵視覺特徵%分類
장식지%가견광광보%주성분분석%표면시각특정%분류
Decorative papers%Visible spectroscopy%Principal component analysis (PCA)%Visual characteristics%Classification
装饰纸作为现代家居产品中必不可少的重要饰面材料之一,不仅具有良好的装饰效果,还可以大大地改善材料的表面性能。然而,装饰纸外观质量的控制(如色差的评价和控制),仍然是制约装饰纸产业发展的重要因素之一。利用人眼来判别和控制往往因人而异,偏主观而非客观。因此,寻找一种客观、有效的方法来代替人的视觉感官来快速判别具有重要意义。本研究利用可见光光谱结合主成分分析法对不同类别装饰纸进行了模式识别分类研究,探讨了该技术的可行性。结果表明:(1)可见光光谱与表征装饰纸表面视觉特性的参数之间呈现出显著的相关性,相关系数都达到了0.85以上,多数均达到0.99,说明可见光光谱中包含有描述装饰纸表面视觉特征的参数;(2)利用装饰纸表面的可见光光谱结合主成分分析方法所建立的模式识别模型,对不同装饰纸表面视觉特征类型进行模式识别时,正确率达到94%~100%,说明可见光光谱分析技术有潜力成为装饰纸表面视觉特征快速、客观、有效识别和分类的新技术。
裝飾紙作為現代傢居產品中必不可少的重要飾麵材料之一,不僅具有良好的裝飾效果,還可以大大地改善材料的錶麵性能。然而,裝飾紙外觀質量的控製(如色差的評價和控製),仍然是製約裝飾紙產業髮展的重要因素之一。利用人眼來判彆和控製往往因人而異,偏主觀而非客觀。因此,尋找一種客觀、有效的方法來代替人的視覺感官來快速判彆具有重要意義。本研究利用可見光光譜結閤主成分分析法對不同類彆裝飾紙進行瞭模式識彆分類研究,探討瞭該技術的可行性。結果錶明:(1)可見光光譜與錶徵裝飾紙錶麵視覺特性的參數之間呈現齣顯著的相關性,相關繫數都達到瞭0.85以上,多數均達到0.99,說明可見光光譜中包含有描述裝飾紙錶麵視覺特徵的參數;(2)利用裝飾紙錶麵的可見光光譜結閤主成分分析方法所建立的模式識彆模型,對不同裝飾紙錶麵視覺特徵類型進行模式識彆時,正確率達到94%~100%,說明可見光光譜分析技術有潛力成為裝飾紙錶麵視覺特徵快速、客觀、有效識彆和分類的新技術。
장식지작위현대가거산품중필불가소적중요식면재료지일,불부구유량호적장식효과,환가이대대지개선재료적표면성능。연이,장식지외관질량적공제(여색차적평개화공제),잉연시제약장식지산업발전적중요인소지일。이용인안래판별화공제왕왕인인이이,편주관이비객관。인차,심조일충객관、유효적방법래대체인적시각감관래쾌속판별구유중요의의。본연구이용가견광광보결합주성분분석법대불동유별장식지진행료모식식별분류연구,탐토료해기술적가행성。결과표명:(1)가견광광보여표정장식지표면시각특성적삼수지간정현출현저적상관성,상관계수도체도료0.85이상,다수균체도0.99,설명가견광광보중포함유묘술장식지표면시각특정적삼수;(2)이용장식지표면적가견광광보결합주성분분석방법소건립적모식식별모형,대불동장식지표면시각특정류형진행모식식별시,정학솔체도94%~100%,설명가견광광보분석기술유잠력성위장식지표면시각특정쾌속、객관、유효식별화분류적신기술。
As one of the most important decorative materials for the modern household products,decorative papers impregnated with melamine not only have better decorative performance,but also could greatly improve the surface properties of materials. However,the appearance quality (such as color-difference evaluation and control)of decorative papers,as an important index for the surface quality of decorative paper,has been a puzzle for manufacturers and consumers.Nowadays,human eye is used to dis-criminate whether there exist color difference in the factory,which is not only of low efficiency but also prone to bring subj ective error.Thus,it is of great significance to find an effective method in order to realize the fast recognition and classification of the decorative papers.In the present study,the visible spectroscopy coupled with principal component analysis (PCA)was used for the pattern recognition of decorative papers with different visual characteristics to investigate the feasibility of visible spectrosco-py to rapidly recognize the types of decorative papers.The results showed that the correlation between visible spectroscopy and visual characteristics (L*,a* and b*)was significant,and the correlation coefficients were up to 0. 85 and some was even more than 0. 9 9 ,which might suggest that the visible spectroscopy reflected some information about visual characteristics on the sur-face of decorative papers.When using the visible spectroscopy coupled with PCA to recognize the types of decorative papers,the accuracy reached 94%~100%,which might suggest that the visible spectroscopy was a very potential new method for the rapid, objective and accurate recognition of decorative papers with different visual characteristics.