摘要： 文件的真实性是当前诉讼审查阶段的重要工作，可擦笔在司法案件中常被用来进行伪造文书、合同等犯罪行为。针对其油墨成分、笔迹修改等方面的辨识是文件检验领域的重点研究。特殊热感变色颜料是可擦笔油墨的主要成分，其变色原理是随着温度变化会产生笔迹的消失与复现，在65 ℃以上颜色褪去，在-18 ℃以下颜色复现。对其进行种属认定可以对案件证据的真实性进行鉴别，为案件诉讼过程提供支持。高光谱的超高光谱分辨率对高分子材料具有较好的特征选择性，能够有效的对常见油墨成分进行数据采集。该实验收集22个品牌共45份可擦笔油墨样本，可以分为碳化钨笔珠、子弹头笔珠、全针管、半针管四种类型，统一采集450~950 nm波段的高光谱信息。关于光谱数据背景噪声冗余的问题，选用主成分分析法（PCA）对数据进行降维处理，提取特征变量。基于降维后的数据选用不同类型的希尔伯特变换（HT）进行信号滤波，进一步选择有效信号，提升建模效果。样本识别上选用多层感知器（MLP）和径向基函数神经网络（radial basis function neural network，RBFNN）两种人工神经网络模型，基于23维主成分提取的特征变量类建模准确率分别为81%，84%，通过希尔伯特高通滤波处理后可以将分类准确率提升至88.9%，92%，能够有效提升识别准确率。为进一步区分不同样本的种类，选择Fisher判别分析方法进行建模，各样本原始数据在FDA模型中识别准确率为44%，经最优PCA-HT处理的FDA建模准确率为93.3%，能够区分出不同的可擦笔油墨类型。结果表明，PCA能够在保留光谱有效信息的基础上进行降维，提升模型精度并且缩短运行时间，相较于原始光谱数据建模效果较好，通过希尔伯特变换后的光谱数据能够进一步完善有效光谱信息，使得建模准确率进一步提升。该实验确定PCA-HT-FDA模型为最佳可擦笔油墨高光谱识别模型，能够为司法鉴定人员提供一定参考。
关键词：可擦笔；高光谱；滤波器；希尔伯特变换；模式识别
Abstract：The authenticity of documents is an important work in the current stage of litigation review. In judicial cases, erasablepens are often used to forge documents, contracts and other criminal acts. The identification of ink composition and handwriting modification is the key research in the field of document inspection. Special thermal color pigment is the main component of erasable ink; its color principle is that temperature change will produce the disappearance and recurrence of handwriting, color fades above 65℃, and color recurrence below -18 ℃. The identification of its species can identify the authenticity of the case evidence and provide support for the litigation process of the case. The ultra-high spectral resolution of hyperspectrum has good feature selectivity for polymer materials, which can effectively collect data for common ink components. In this experiment, a total of 45 erasable pen ink samples from 22 brands were collected, which can be divided into four types: tungsten carbide pen beads, bullet pen beads, full needle tube and half needle tube, and the hyperspectral information of 450~950 nm band was collected uniformly. As for the redundancy of background noise in spectral data, the principal component analysis (PCA) was used to reduce the dimensionality of the data and extract the feature variables. Based on the dimensionality reduction data, different Hilbert transform (HT) types were used for signal filtering, and effective signals were further selected to improve the modeling effect. Two artificial neural network models, Multilayer Perceptron (MLP) and radial basis function neural network (RBFNN), were selected for sample recognition. The feature variable class modeling accuracy based on 23-dimensional principal component extraction is 81% and 84%, respectively. After the Hilbert high-pass filtering processing, the classification accuracy can be increased to 88.9% and 92%, effectively improving recognition accuracy. In order to further distinguish the types of different samples, Fisher discriminant analysis method was selected for modeling. The identification accuracy of the original data of each sample in the FDA model was 44%, and the FDA modeling accuracy of the optimal PCA-HT treatment was 93.3%, which could distinguish different types of erasable ink. The results show that PCA can reduce the dimension based on retaining the effective spectral information, improving the model accuracy and shortening the running time. Compared with the original spectral data, the modeling effect is good, and the spectral data after the Hilbert transform can further improve the effective spectral information to further improve the modeling accuracy. This experiment determined the optimal PCA-HT-FDA model and the best erasable ink hyperspectral identification model, which can provide a certain reference for forensic experts.
王晓宾，张傲林，邹颖芳，杨 蕾. 基于希尔伯特滤波的可擦笔油墨光谱模式识别[J]. 光谱学与光谱分析, 2024, 44(05): 1338-1345.
WANG Xiao-bin, ZHANG Ao-lin, ZOU Ying-fang, YANG Lei. Spectral Pattern Recognition of Erasable Ink Based on Hilbert Filter. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(05): 1338-1345.
[1] ZHAO Yu-xuan，ZENG Le-yang-zi，LI Kai-kai（赵昱萱，曾乐洋子，李开开）. Spectroscopyand Spectral Analysis（光谱学与光谱分析），2021，41(8): 2420.
[2] Sauzier G, Mcgann J, Lewis S W, et al. Analytical Methods，2018，10(47)：5613.
[3] Kumar R, Sharma V. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2017, 175: 67.
[4] Devassy B M, George S. Forensic Science International, 2020, 311: 110194.
[5] Reed G, Savage K, Edwards D, et al. Science & Justice: Journal of the Forensic Science Society, 2014, 54(1): 71.
[6] Sugawara S. Forensic Chemistry, 2017，6：44.
[7] WANG Shu-yue，YANG Yu-zhu，HE Wei-wen，et al（王书越，杨玉柱，何伟文，等）. Journal of Instrumental Analysis（分析测试学报），2021，40（10）：1489.
[8] YANG Lu，HUANG Jian-hua，CHEN Xin-nan，et al（杨 璐，黄建华，陈欣楠，等）. Journal of Instrumental Analysis（分析测试学报），2020，39（7）：844.
[9] Davis L J, Saunders C P, Hepler A, et al. Forensic Science International, 2012, 216(1-3): 146.
[10] WANG Xiao-bin, MA Xiao, WANG Xin-cheng（王晓宾，马 枭，王新承）. Laser & Optoelectronics Progress（激光与光电子学进展）, 2020, 57(15): 153005.
[11] WANG Jie, TAN Bing-chong, TAO Xing-zhu, et al（王 洁，谭冰冲，陶星竹，等）. Journal of Infrared and Millimeter Waves（红外与毫米波学报），2022, 41(3): 589.
[12] WANG Ju-xiang, WANG Kai(王菊香，王 凯). Chinese Journal of Analysis Laboratory(分析试验室)，2018，37(7)：821.
[13] WANG Xiao-bin，MA Xiao，YANG Lei，et al（王晓宾，马 枭，杨 蕾，等）. Laser & Optoelectronics Progress（激光与光电子学进展），2021，58（1）：0130002.
[14] WEI Chen-jie, WANG Ji-fen, FAN Lin-yuan, et al（卫辰洁，王继芬，范琳媛，等）. China Plastics（中国塑料），2020，34（12）：59.
[15] WANG Ju-xiang, WANG Kai（王菊香，王 凯）. Chinese Journal of Analysis Laboratory（分析试验室），2018，37(7)：821.
[16] Wei Chenjie，Wang Jifen，He Xinlong，et al. Microchemical Journal，2021，163：105924.
[17] HE Xin-long，WANG Ji-fen，HE Ya，et al（何欣龙，王继芬，何 亚，等）. Laser Journal（激光杂志），2019，40 （11）：33.
