本文選題：高光譜圖像 + 墨粉種類鑒別��； 參考：《發(fā)光學(xué)報(bào)》2017年05期

【摘要】：為了使用快速、無損的方法區(qū)分激光打印文件使用的墨粉種類,利用高光譜成像技術(shù)結(jié)合化學(xué)計(jì)量法對(duì)6種激光打印墨粉的光譜數(shù)據(jù)進(jìn)行建模和種類鑒別的研究。利用可見-近紅外高光譜成像儀采集400~1 000 nm波段內(nèi)的光譜數(shù)據(jù),采用Savitzky Golay平滑、標(biāo)準(zhǔn)化、多元散射校正和標(biāo)準(zhǔn)正態(tài)變量變換4種方法分別對(duì)光譜數(shù)據(jù)進(jìn)行預(yù)處理,而后分別建立隨機(jī)森林(RF)、K最近鄰(KNN)、支持向量機(jī)(SVM)、偏最小二乘判別分析(PLS-DA)和簇類獨(dú)立軟模式(SIMCA)模型,進(jìn)而實(shí)現(xiàn)激光打印墨粉的種類鑒別。利用準(zhǔn)確率、拒識(shí)率和誤識(shí)率3個(gè)指標(biāo)作為模型評(píng)價(jià)標(biāo)準(zhǔn)。實(shí)驗(yàn)結(jié)果顯示,SVM和PLS-DA模型的效果最佳,準(zhǔn)確率為100%,拒識(shí)率和誤識(shí)率為0。基于可見-近紅外高光譜成像技術(shù)可以實(shí)現(xiàn)激光打印墨粉的快速種類鑒別。
[Abstract]:In order to use fast and lossless methods to distinguish the toner types used in laser printing documents, the spectral data of six laser printed toner were modeled and identified by hyperspectral imaging technique combined with chemometrics. The spectral data were collected by using a visible-near infrared hyperspectral imager in the wavelength of 400,000nm. The spectral data were preprocessed by Savitzky Golay smoothing, standardization, multivariate scattering correction and standard normal variable transformation. Then, the following models were established, such as KNN, SVMN, PLS-DAA and SIMCA, respectively, and the classification of laser printing toner was realized by using the model of random forest fission K nearest neighbor, support vector machine (SVM), partial least squares discriminant analysis (PLS-DA) and cluster independent soft mode (Simca), respectively. The accuracy rate, rejection rate and error rate are used as the evaluation criteria of the model. Experimental results show that SVM and PLS-DA model have the best effect, the accuracy is 100 and the rejection rate and false recognition rate are 0. Based on visible-near-infrared hyperspectral imaging technology, laser printing toner can be quickly identified.
【作者單位】： 文件檢驗(yàn)鑒定公安部重點(diǎn)實(shí)驗(yàn)室(中國刑警學(xué)院);浙江警察學(xué)院刑事科學(xué)技術(shù)系;司法部司法鑒定科學(xué)技術(shù)研究所;
【基金】：文件檢驗(yàn)鑒定公安部重點(diǎn)實(shí)驗(yàn)室(中國刑事警察學(xué)院)課題(2015KFKT09) 浙江警察學(xué)院校局合作項(xiàng)目(2016XJY014)資助~~
【分類號(hào)】：TP334.8;TP391.41
，

本文編號(hào)：1875256