为解决市场上常见木材单板的快速识别问题,开发基于图像比对的常用树种木材单板的识别技术,使常用树种木材单板的识别变得简单,以常见装饰单板的彩色图像为对象,颜色直方图为单板颜色的量化指标,利用相关系数算法,开展了RGB、HSV和Gray颜色空间下木材单板图像的检索技术研究。结果表明:在建立常见树种木材单板图像数据库的基础上,利用颜色直方图可以对木材单板进行检索及识别; 不同颜色空间下,RGB和HSV直方图检索准确率优于Gray直方图,前两者准确率为99%,而后者仅为88%。分析认为,基础数据库中各树种标准图片的选取是影响检索准确率的重要因素,各树种的标准图片应包含该树种最大的颜色差异,且能明显区别于其他树种。
Abstract
To solve the problem of quick identification of typical wood veneers, color images of common decorative veneers were studied using color histogram as quantitative index of veneer colors, and image retrieval techniques of wood veneers in terms of RGB, HSV and Gray color spaces were investigated based on the algorithm of correlation coefficient, in order to develop a new wood veneer recognition technique based on image comparison allowing for simplification of the recognition process. Result showed that the color histogram could be used for retrieving and recognizing wood veneers once the basic image database of the common wood species veneer was set up. The histogram retrieval accuracies of RGB and HSV are better than Gray histogram, and the accuracy of the first two is 99%, but the latter is only 88%. The selection of representative images of wood species in the basic database is an important factor which affects the retrieval accuracy. Moreover, the selected representative image of each species should contain its maximum color difference, differing significantly from other species.
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Kam A H. Content based image retrieval through object extraction and quering[C]//Proceeding of the IEEE Workshop on Content-based Access of Image and Video Libraries, 2000.
[2] Datta R, Li J, Wang J Z. Content-based image retrieval approaches and trends of the new age[C]//Proceedings of the 7th International Workshop on Multimedia Information Retrieval. ACM, 2005,7(11):253-262.
[3] 樊昀,王润生.面向内容检索的彩色图像分割[J].计算机研究与发展,2002,39(3):376-381.
Fan Y,Wang R S. Color image segmentation for content based image retrieval[J]. Journal of Computer Research and Development,2002,39(3):3766-381.
[4] 徐海荣. 基于内容的图像检索及其相关技术研究[D].济南:山东大学,2004.
Xu H R. Research on content-based image retrieval and related technology[D].Jinan:Shandong University,2004.
[5] Pun C M, Wong C F. Fast and robust color feature extraction for content-based image retrieval [J].International Journal of Advancements in Computing Technology, 2011, 3(6):75-83.
[6] Kim N W, Kim T Y, Choi J S.Edge-based spatial descriptor using color vector angle for effective image retrieval [J]. Modeling Decisions for Artificial Intelligence,2005,3558:365-375.
[7] Li X L. Image retrieval based on perceptive weighted color blocks[J]. Pattern Recognition Letters,2003,24(12):1935-1941.
[8] 宁晶晶, 周海英. 压缩基础上利用纹理进行图像检索的方法研究 [J]. 计算机应用与软件, 2011, 28(6): 254-256.
Ning J J, Zhou H Y.Study on image retrieval methods with texture on the basis of compression[J]. Computer Applications and Software, 2011, 28(6): 254-256.
[9] Kao C C, Lai Y T, Lin C H. An efficient reflection invariance region-based image retrieval framework [J]. International Journal of Imaging Systems and Technology, 2010, 20(2):155-161.
[10] 杨旭,杨新,田雪. 一种鲁棒的二维图像形状检索方法[J]. 模式识别与人工智能, 2010, 23(5): 738-744.
Yang X, Yang X, Tian X. Robust approach for 2D shape-based image retrieval [J]. Pattern Recognition and Artificial Intelligence, 2010, 23(5): 738-744.
[11] Fauqueur J, Boujemaa N. Region-based image retrieval:fast coarse segmentation and fine color description[J].Journal of Vision Languages and Computing, 2004, 15(1):69-95.
[12] 陈秀新, 贾克斌. 三维量化颜色直方图在彩色图像检索中的应用[J]. 计算机应用与软件, 2012, 29(9): 31-32.
Chen X X, Jia K B. Application of three-dimensional quantised colour histogram in colour image retrieval[J]. Computer Applications and Software, 2012, 29(9): 31-32.
[13] 张求慧. 珍贵木材纹理特征的量化表达[J].家具,2014,35(2):34-38.
Zhang Q H. Fractal characterization of surface texture features of valuable wood[J].Furniture, 2014,35(2):34-38.
[14] 谢永华,钱玉恒,白雪冰.基于小波分解与分形维的木材纹理分类[J].东北林业大学学报,2010,38(12):118-120.
Xie Y H, Qian Y H, Bai X B. Classification of wood texture based on wavelet transform and fractal dimension[J].Journal of Northeast Forestry University,2010,38(12):118-120.
[15] 杨少春,王克奇,戴天虹,等.基于直方图的木材表面颜色分类研究[J].森林工程,2008,24(1):34-36.
Yang S C, Wang K Q, Dai T H, et al. A study of color classification on wood surface based on histogram[J].Forest Engineering,2008,24(1):34-36.
[16] 尹建新,楼雄伟,黄美丽.灰度直方图在木材表面缺陷检测中的应用[J].浙江林学院学报,2008,25(3):272-276.
Yin J X, Lou X W, Huang M L. Application of grey histogram to wood surface defects' detection[J].Journal of Zhejiang Forestry College,2008,25(3):272-276.
[17] Zhao P. Robust wood species recognition using variable color information[J]. Optik-International Journal for Light and Electron Optics,2013,124(17):2833-2836.
[18] 张永利,郑秀萍,雷文礼.基于量化颜色空间的彩色图像检索算法[J].计算机仿真, 2007,27(10): 194-196.
Zhang Y L, Zheng X P, Lei W L. Method of color image retrieval based on quantified color space[J]. Computer Simulation, 2007,27(10): 194-196.
[19] 冀亚丽. 基于内容的鲁棒的图像检索方法的研究与系统实现[D]. 重庆: 西南师范大学, 2005.
Ji Y L. Research and application about robust image retrieval approach based on content[D].Chongqing: Southwest Normal University,2005.
[20] 王志国.局部特征算法SURF的GPU加速研究与实现[D].北京:清华大学,2011.
Wang Z G.Study and implementation of GPU acceleration on local feature[D].Beijing:Tsinghua University,2011.
基金
收稿日期:2014-11-25 修回日期:2015-05-06
基金项目:中央级公益性科研院所基本科研业务费专项资金项目(CAFINT2013C06)
第一作者:陈勇平,助理研究员。*通信作者:郭文静,研究员。E-mail: guowj@caf.ac.cn。
引文格式:陈勇平,郭文静,王正. 基于颜色直方图的木材单板图像检索技术研究[J]. 南京林业大学学报:自然科学版,2015,39(5):129-134.
PDF(4009454 KB)
