HE Shao-yan1, CHEN Shun-er1, ZHAI Hao-tian1, LIU Wei-ping1,2
(1. Department of Electronic Engineering, Jinan University, Guangzhou 510632, China; 2. Key Laboratory of Optoelectronic Information and Sensing Technologies of Guangdong Higher Educational Institutes, Jinan University, Guangzhou 510632, China)
Abstract： Computer forensics and identification for traditional Chinese painting arts have caught the attention of various fields. Rice paper’s feature extraction and analysis methods are of high significance for the rice paper is an important carrier of traditional Chinese painting arts. In this paper, rice paper’s morphological feature analysis is done using multi spectral imaging technology. The multispectral imaging system is utilized to acquire rice paper’s spectral images in different wavelength channels, and then those spectral images are measured using texture parameter statistics to acquire sensitive bands for rice paper’s feature. The mathematical morphology and grayscale statistical principle are utilized to establish a rice paper’s morphological feature analytical model which is used to acquire rice paper’s one-dimensional vector. For the purpose of evaluating these feature vectors' accuracy, they are entered into the support vector machine(SVM) classifier for detection and classification. The results show that the rice paper’s feature is out loud in the spectral band 550 nm, and the average classification accuracy of feature vectors output from the analytical model is 96%. The results indicate that the rice paper’s feature analytical model can extract most of rice paper’s features with accuracy and efficiency.
Key words： rice paper; multispectral imaging; texture analysis; mathematical morphology
CLD number： TP391.41 Document code： A
Article ID： 1674-8042(2014)04-0046-06 doi： 10.3969/j.issn.1674-8042.2014.04.009
References
[1] WU Shi-xin. Rice paper and its identify. Paper and Paper Making, 2006, 25(4): 70-71.
[2] LIU Ren-qing. Theory of rice paper—the sixth research of paper. Paper and Paper Making, 2011, 30(3): 68-69.
[3] WU Shi-xin. Three key processes in rice paper production. China Pulp & Paper Industry, 2010, 31(13): 76-78.
[4] JIANG Ying-xue. Rice paper uesd for painting and calligraphy in China. Master thesis. Jilin: Jilin University, 2007: 4-5.
[5] WANG Li-zhen. Research on the performance of rice paper in duplication artware. Master thesis. Nanjing: Nanjing Forestry University, 2010: 4-5.
[6] SUN Jing-hua. Study on modeling and simulation of rice paper in virtual painting. Master thesis. Dalian: Dalian University of Technology, 2012: 4-6.
[7] ZHAI Hao-tian, HUANG Hong-bin, HE Shao-yan, et al. Rice paper classification study based on signal processing and statistical methods in image texture analysis. In: Proceedings of the 13th IEEE/ACIS International Conference on Computer and Information Science, Taiyuan, China, 2014.
[8] XIE Chuan-qi. Study on the early detection of early blight on tomato leaves using hyperspectral imaging technique based on spectroscopy and testure. Spectroscopy and Spectral Analysis, 2013, 33(6): 1603-1607.
[9] WU Di, CHEN Xiao-jing, HE Yong. Application of multispectral image texture to discriminating tea categories based on DCT and LS-SVM. Spectroscopy and Spectral Analysis, 2009, 29(5): 1382-1385.
[10] WU Di, CHEN Xiao-jing,HE Yong. Study on application of multi-spectral image texture to discriminating. Spectroscopy and Spectral Analysis, 2009, 29(1): 222-225.
[11] Shih F Y, Mitchell O R. A mathematical morphology approach to Euclidean distance transformation. IEEE Transactions on Image Processing, 1992, 1(2): 197-204.
[12] Klingler J W Jr, Vaughan C L, Fraker T D Jr, et al. Segmentation of echocardiographic images using mathematical morphology. IEEE Transactions on Biomedical Engineering, 1988, 35(11): 925- 934.
[13] GONG Hui. Theory and application of mathematical morphology in mathematical space. Beijing: Science Press, 1997: 344-354.
基于多光谱成像技术的宣纸形态学特征分析
何少岩1， 陈舜儿1， 翟浩田1， 刘伟平1,2
(1. 暨南大学 电子工程系, 广东 广州 510632；2. 暨南大学 广东省高等学校光电信息与传感技术重点实验室, 广东 广州 510632)
摘要:国画艺术品的科技取证与鉴别受到各领域的关注。 宣纸作为国画的重要载体， 其特征提取和分析方法有较高的研究意义。 本文使用多光谱成像技术对宣纸进行形态学特征分析。 实验采用多光谱成像系统获取宣纸在不同波长通道下的光谱图片， 继而采用纹理参数统计对光谱图像进行测量， 获得宣纸特征的敏感波段； 采用数学形态学和灰度统计原理建立宣纸形态学特征分析模型， 得到一维特征向量。 为了评价特征向量的准确度， 实验将特征向量输入到支持向量机（SVM）分类器进行检测分类。 结果表明， 宣纸的差异化特征在550 nm波段下最为明显； 由模型输出的特征向量分类正确率为96%。 本文提出的宣纸分析模型能够将大部分种类的宣纸特征准确提取， 并具有一定的高效性。
关键词:宣纸； 多光谱成像； 特征分析； 数学形态学
引用格式：HE Shao-yan, CHEN Shun-er, ZHAI Hao-tian, et al. Analysis of rice paper’s morphological features based on multispectral imaging technology. Journal of Measurement Science and Instrumentation, 2014, 5(4): 46-51. [doi: 10.3969/j.issn.1674-8042.2014.04.009]
[full text view]
