基于计算机的木材特征提取和分类识别技术研究综述

编号 lyqk008152

中文标题 基于计算机的木材特征提取和分类识别技术研究综述

作者 黄鹏桂  赵璠  李晓平  关成  张严风  吴章康 

作者单位 1. 西南林业大学大数据与智能工程学院, 昆明 650224;
2. 西南林业大学国家林业和草原局木材与木竹制品质量检验检测中心, 昆明 650224

期刊名称 世界林业研究 

年份 2020 

卷号 33

期号 1

栏目编号 1

栏目名称 专题论述 

中文摘要 木材由于内部结构和组成成分的差异，使不同种类木材表现出完全不同的理化性质，并决定其不同的用途和商业价格，因此针对木材的分类识别研究具有重要的应用价值。木材分类识别通常经过木材特征提取和基于特征的分类识别这2个步骤。目前木材特征提取主要利用计算机视觉、光谱分析等技术。木材分类识别是基于木材特征的数字化，这一部分可利用计算机算法实现自动识别，较以往人工识别可大幅提高准确度。文中通过分析近20年来木材特征提取和分类识别的相关文献，介绍各种基于计算机的木材特征提取与分类识别技术的特点及适用范围，并结合计算机技术的发展方向探讨木材特征提取与分类识别技术的发展趋势，以期为构建更准确的木材分类识别技术提供参考。

关键词 木材识别  特征提取  特征识别  计算机技术 

基金项目 国家自然科学基金项目（31870551）；西南林业大学科研启动基金项目（111807）。

英文标题 Review of Computer-based Wood Feature Extraction and Identification

作者英文名 Huang Penggui, Zhao Fan, Li Xiaoping, Guan Cheng, Zhang Yanfeng, Wu Zhangkang

单位英文名 1. College of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, China;
2. National Forestry and Grassland Administration Center for Quality Supervision and Testing of Wood and Bamboo Products, Southwest Forestry Unive

英文摘要 The differences in internal structure and composition bring wood completely different physical and chemical properties, and determine their uses and commercial prices. Therefore, the research on wood identification technology is of important value. As a biomass material, wood has the strong variability in structure and component characteristics, which imposes challenges to the research on wood identification technology. Generally, the wood identification technology can be divided into two steps:feature extraction and feature-based identification. At present, computer vision and spectral analysis are the main technology used to extract wood features. And the technology of wood identification is based on the digitalization of wood feature using the computer algorithms, which can improve the accuracy than manual identification. This paper reviews and analyzes the related literature om the wood feature extraction and identification in the past 20 years, introduces the characteristics and applicable scope of a range of computer based technology for wood feature extraction and classification, and discusses the development trend of the technology of wood feature extraction and classification with the development of computer technology, with the expectation to provide references to build a more accurate wood identification technology.

英文关键词 wood identification;feature extraction;feature recognition;computer technology

起始页码 44

截止页码 48

投稿时间 2019/4/7

最后修改时间 2019/7/2

作者简介 黄鹏桂,男,硕士生,从事林业信息工程研究,E-mail:1744182303@qq.com。

通讯作者介绍 赵璠,男,副教授,硕士生导师,从事林业信息工程研究,E-mail:fzhao@swfu.edu.cn。

E-mail 赵璠，fzhao@swfu.edu.cn

分类号 S781.1

DOI 10.13348/j.cnki.sjlyyj.2019.0074.y

参考文献 [1] 杨羽昆,陈绍志,赵荣,等.中国主要木材交易市场发展时空变化分析[J].世界林业研究,2018,31(3):48-51.
[2] VINCENT J F.Structure of wood[J].Current Opinion in Solid State&Materials Science,1998,3(3):228-231.
[3] FULLER G E.Wood identification[J].Botanical Gazette,1934,96(2):386-387.
[4] WHEELER E A,BAAS P.Wood identification-a review[J].IAWA Journal,1998,19(3):241-264.
[5] MILLER R B. Wood identification via computer[J].IAWA Bulletin,1980,1(4):154-160.
[6] SUYKENS J A K,VANDEWALLE J,MOOR B D.Optimal control by least squares support vector machines[J].Neural Networks,2001,14(1):23-35.
[7] MITCHELL T M. Machine learning and data mining[J].Computer Study,1999,42(2):110-114.
[8] JAIN A K,MAO J,MOHIUDDIN K.Artificial neural networks:a tutorial[J].Computer,1996(3):31-44.
[9] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet classification with deep convolutional neural networks[C].Advances in Neural Information Processing Systems,California,USA,2012.
[10] PITAS I.Digital image processing algorithms and applications[J].IEEE Signal Processing Magazine,2002,18(2):58-58.
[11] 赵景尧,蔡英春.数字图像相关技术及其在木材科学研究中的应用[J].世界林业研究,2015,28(6):53-57.
[12] HERMANSON J C,WIEDENHOEFT A C.A brief review of machine vision in the context of automated wood identification systems[J].IAWA Journal,2011,32(2):233-250.
[13] FAUGERAS O.Three-dimensional computer vision,a geometric viewpoint[J].Robotica,1993,12(5):475-475.
[14] 洪继光.灰度-梯度共生矩阵纹理分析方法[J].自动化学报,1984,10(1):22-25.
[15] MANJUNATH B S,MA W Y.Texture features for browsing and retrieval of image data[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,1996,18(8):837-842.
[16] 白雪冰,王克奇,王辉.基于灰度共生矩阵的木材纹理分类方法的研究[J].哈尔滨工业大学学报,2005,37(12):1667-1670.
[17] TOU J Y,LAU P Y,TAY Y H.Computer vision-based wood recognition system[C].International Workshop on Advanced Image Technology,Kuala Lumpur,2007.
[18] WANG B H,WANG H J,QI H N.Wood recognition based on grey-level co-occurrence matrix[C].International Conference on Computer Application and System Modeling,Taiyuan,China,2010.
[19] PRAMUNENDAR R A,SUPRIYANTO C,NOVIANTO D H,et al.A classification method of coconut wood quality based on Gray Level Co-occurrence matrices[C]. International Conference on Robotics and Automation,Hong Kong,2013.
[20] 戴天虹,王克奇,白雪冰,等.基于神经网络和颜色特征对木材进行分级的分析[J].森林工程,2006,22(1):18-20.
[21] 王亚超.基于小波变换的木材图像处理技术研究[D].呼和浩特:内蒙古农业大学,2013.
[22] SUGIARTO B,PRAKASA E,WARDOYO R,et al.Wood identification based on histogram of oriented gradient (HOG) feature and support vector machine (SVM) classifier[C].Information Systems and Electrical Engineering,Yogyakarta,Indonesia,2017.
[23] 胡爱华,邢世岩,巩其亮.基于FTIR的银杏木材鉴别研究[J].中国农学通报,2009,25(4):88-92.
[24] 马明宇,王桂芸,黄安民,等.人工神经网络结合近红外光谱用于木材树种识别[J].光谱学与光谱分析,2012,32(9):2377-2381.
[25] 张蓉,徐魁梧,张丽沙,等.基于红外光谱的5种红木树种识别探讨[J].林业工程学报,2014,28(2):95-99.
[26] 王学顺,孙一丹,黄安民.木材红外光谱的树种识别研究[J].森林工程,2015,31(6):65-70.
[27] 王学顺,孙一丹,黄敏高.基于BP神经网络的木材近红外光谱树种识别[J].东北林业大学学报,2015,43(12):82-85.
[28] LAZARESCU C,HART F,PIROUZ Z,et al.Wood species identification by near-infrared spectroscopy[J].International Wood Products Journal,2017,8(1):32-35.
[29] NISGOSKI S,OLIVEIRA A A D,MUNIZ G I B D,et al.Artificial neural network and SIMCA classification in some wood discrimination based on near-infrared spectra[J].Wood Science,2017,51(4):929-942.
[30] LAVINE B K,DAVIDSON C,MOORES A J,et al.Raman spectroscopy and genetic algorithms for the classification of wood types[J]. Applied Spectroscopy,2001,55(8):960-966.
[31] LEBOW P K,BRUNNER C C,MARISTANY A G,et al.Classification of wood surface features by spectral reflectance[J].Wood Fiber Science,2007,28(1):74-90.
[32] PIURI V,SCOTTI F.Design of an automatic wood types classification system by using fluorescence spectra[J].IEEE Transactions on Systems,Man,Cybernetics,Part C,2010,40(3):358-366.
[33] JAVIER T S,Salvador N,Mario F F,et al.Functional nonparametric classification of wood species from thermal data[J].Journal of Thermal Analysis Calorimetry,2011,104(1):87-100.
[34] MARIO F F,JAVIER T S,ABHIRUP M,et al.A comprehensive classification of wood from thermogravimetric curves[J].Chemometrics Intelligent Laboratory Systems,2012,118(1):159-172.
[35] 张洁,夏兆鹏,袁鹏飞,等.大果紫檀和奥氏黄檀乙醇低毒微损鉴别[J].西南林业大学学报,2015,35(4):75-80.
[36] MANKOWSKI M,BOYD B,HASSAN B,et al.GC-MS Characterizations of termiticidal heartwood extractives from wood species utilized in Pakistan[C].The International Research Group On Wood Protection,Hawaii,USA,2016.
[37] 张毛毛,蒋劲东,刘波,等.实时直接分析质谱技术在木材识别研究中的应用[J].木材工业,2019,33(1):29-33.
[38] ROJAS J,ALPUENTE J,POSTIGO D,et al.Wood species identification using stress-wave analysis in the audible range[J].Applied Acoustics,2011,72(12):934-942.
[39] 王英.基于DNA技术识别樟科木材[D].南京:南京林业大学,2017.
[40] SADEGHI B H M.A BP-neural network predictor model for plastic injection molding process[J].Journal of Materials Processing Technology,2000,103(3):411-416.
[41] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J/OL].(2014-09-04)[2019-04-07]. https://arxiv.org/abs/1409.1556.
[42] SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions[J/OL].(2014-09-17)[2019-04-07]. https://arxiv.org/abs/1409.4842.
[43] 殷亚方,姜笑梅,焦立超,等.新版GB/T 18107《红木》标准解读[J].木材工业,2018,32(5):23-26.
[44] PAN S J,YANG Q.A survey on transfer learning[J].IEEE Transactions on Knowledge Data Engineering,2010,22(10):1345-1359.
[45] DAY O,KHOSHGOFTAAR T M.A survey on heterogeneous transfer learning[J].Journal of Big Data,2017,4(1):29.
[46] GIRSHICK R,DONAHUE J,DARRELL T,et al.Region-based convolutional networks for accurate object detection and segmentation[J].IEEE Transactions on Pattern analysis Machine Intelligence,2016,38(1):142-158.
[47] REN S,HE K,GIRSHICH R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2017,39(6):1137-1149.
[48] HE K,GKIOXARI G,DOLLAR P,et al.Mask R-CNN[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2017,6(99):2961-2969.

PDF全文 浏览全文