Automated recognition of wood used in traditional Japanese sculptures by texture analysis of their low-resolution computed tomography data

详细信息    查看全文

• 作者：Kayoko Kobayashi ; Masanori Akada ; Toshiyuki Torigoe…
• 关键词：Wood identification ; Pattern recognition ; Texture analysis ; Gray ; level co ; occurrence matrix ; X ; ray computer tomography
• 刊名：Journal of Wood Science
• 出版年：2015
• 出版时间：December 2015
• 年：2015
• 卷：61
• 期：6
• 页码：630-640
• 全文大小：1,321 KB
• 参考文献：1.IAWA Committee (1989) IAWA list of microscopic features for hardwood identification. Wheeler EA, Baas P, Gasson PE (eds) IAWA Bulletin (N.S.) 10:219鈥?32
  2.IAWA Committee (2004) IAWA list of microscopic features for softwood identification. Richter HG, Grosser D, Heinz I, Gasson P (eds) IAWA Bulletin (N.S.) 1:1鈥?0
  3.Schimleck LR, Michell AJ, Vinden P (1966) Eucalypt wood classification by NIR spectroscopy and principal components analysis. Appita J 49:319鈥?24
  4.Watanabe K, Abe H, Kataoka Y, Noshiro S (2011) Species separation of aging and degraded solid wood using near infrared spectroscopy. Jpn J Histor Bot 19:117鈥?24
  5.Horikawa Y, Mizuno-Tazuru S, Sugiyama J (2015) Near-infrared spectroscopy as a potential method for identification of anatomically similar Japanese diploxylons. J Wood Sci 61:251鈥?61CrossRef
  6.Mizuno S, Torizu R, Sugiyama J (2010) Wood identification of a wooden mask using synchrotron X-ray micro-tomography. J Archaeol Sci 37:2842鈥?845CrossRef
  7.Khalid M, Lee ELY, Yusof R, Nadaraj M (2008) Design of an intelligent wood species recognition system. Int J Simul Sys Sci Technol 9:9鈥?9
  8.Bremananth R, Nithya B, Saipriya R (2009) Wood species recognition using GLCM and correlation. In: Proceedings of the 3rd International Conference on Advances in Recent Technologies in Communication and Computing, Kottayam, Kerala, India, pp 615鈥?19. doi:10.鈥?109/鈥婣rTCom.鈥?009.鈥?0
  9.Filho PLP, Oliveria LS, Britto AS Jr, Sabourin R (2010) Forest species recognition using color-based features. In: 20th International Conference on Pattern Recognition (ICPR), Istanbul, Turkey, pp 4178鈥?181. doi:10.鈥?109/鈥婭CPR.鈥?010.鈥?015
  10.Hermanson JC, Wiiedenhoeft AC (2011) A brief review of machine vision in the context of automated wood identification systems. IAWA J 32(2):233鈥?50
  11.Pan S, Kudo M (2011) Segmentation of pores in wood microscopic images based on mathematical morphology with a variable structuring element. Comput Electron Agric 75:250鈥?60CrossRef
  12.Yusof R, Rosli NR, Khalid M (2010) Using Gabor filters as image multiplier for tropical wood species recognition system. In: 12th International Conference on Computer Modelling and Simulation (UKSim), Cambridge, United Kingdom, pp 289鈥?94
  13.Khalid M, Yusof R, Khairuddin ASM (2011) Tropical wood species recognition system based on multi-feature extractors and classifiers. In: Proceedings of 2011 2nd International Conference on Instrumentation Control and Automation (ICA), Bandung, Indonesia, pp 6鈥?1
  14.Martins J, Oliveira LS, Nisgoski S, Sabourin R (2013) A database for automatic classification of forest species. Machine Vision Appl 24:567鈥?78CrossRef
  15.Wang HJ, Zhang GQ, Qi HN (2013) Wood recognition using image texture features. PLoS One 8(10):e76101. doi:10.鈥?371/鈥媕ournal.鈥媝one.鈥?076101 PubMedCentral CrossRef PubMed
  16.Yuliastuti E, Suprijanto, Sasi SR (2013) Compact computer vision system for tropical wood species recognition based on pores and concentric curve. In: Proceedings of 2013 3rd International Conference on Instrumentation Control and Automation (ICA), Bali, Indonesia, pp 198鈥?02
  17.Yusof R, Khalid M, Khairuddin ASM (2013) Application of kernel-genetic algorithm as nonlinear feature selection in tropical wood species recognition system. Comput Electron Agric 93:68鈥?7CrossRef
  18.Yadav AR, Anand RS, Dewal ML, Gupta S (2014) Analysis and classification of hardwood species based on Coiflet DWT feature extraction and WEKA workbench. In: International Conference on Signal Processing and Integrated Networks (SPIN), Noida, India, pp 9鈥?3
  19.Martins JG, Oliveira LS, Britto AS Jr, Sabourin F (2015) Forest species recognition based on dynamic classifier selection and dissimilarity feature vector representation. Machine Vision Appl 26:279鈥?93CrossRef
  20.Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3:610鈥?21CrossRef
  21.R Core Team (2014) R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. http://鈥媤ww.鈥婻-project.鈥媜rg/鈥?/span> . Accessed 7 Aug 2014
  22.Bordese M, Alini W (2013) biOps: Image processing and analysis. R package version 0.2.2. http://鈥婥RAN.鈥婻-project.鈥媜rg/鈥媝ackage=鈥媌iOps . Accessed 7 Aug 2014
  23.Albregtsen F (1995) Statistical texture measures computed from gray level cooccurrence matrices. In: Technical Note, Department of Informatics, University of Oslo, Norway
  24.Venables WN, Ripley BD (2002) Modern applied statistics with S, 4th edn. Springer, New YorkCrossRef
  
• 作者单位：Kayoko Kobayashi (1)
  Masanori Akada (2)
  Toshiyuki Torigoe (3)
  Setsuo Imazu (2)
  Junji Sugiyama (1)
  
  1. Research Institute for Sustainable Humanosphere, Kyoto University, Gokasho, Uji, Kyoto, 611-0011, Japan
  2. Kyushu National Museum, Dazaifu, Fukuoka, 818-0118, Japan
  3. Nara National Museum, Nara, Nara, 630-8213, Japan
  
• 刊物类别：Biomedical and Life Sciences
• 刊物主题：Life Sciences
  Wood Science and Technology
  Materials Science
  Characterization and Evaluation Materials
  
• 出版者：Springer Japan
• ISSN：1611-4663

文摘

The identification of wood species used in the cultural artifacts is important in terms of their preservation and inheritance. However, a nondestructive method is required, and wood samples must be partly cut off in conventional methods such as microscopy. In this study, we constructed a novel system for wood identification using image recognition of X-ray computed tomography images of eight major species used in Japanese wooden sculptures. Texture analyses of the computed tomography images were carried out using the gray-level co-occurrence matrix, from which 15 textural features were calculated. The k-nearest-neighbor algorithm combined with cross validation was applied for classification and evaluation of the system. Input datasets with a variation in image qualities (resolution, gray level, and image size) were investigated using this novel system, and the accuracy was greater than 98 % when the input images had a certain quality level. Although there are still technical problems to be overcome, progress in the development of automated identification is extremely encouraging in that such an approach has the potential to make a valuable contribution in adding scientific species notion to the artifacts; otherwise, only the literal documents are available. Keywords Wood identification Pattern recognition Texture analysis Gray-level co-occurrence matrix X-ray computer tomography