Improved Otsu Method Based on Histogram Oblique Segmentation for Segmentation of Rotary Kiln Flame Image
-
摘要: 因受窑内高温、高粉尘等因素的影响,氧化铝回转窑火焰图像中往往存在噪声.针对现有火焰图像分割算法存在抗噪性差和计算时间长等问题,对斜分最大类间方差法(Otsu法)进行改进,提出一种基于改进斜分Otsu法的回转窑火焰图像分割算法.该算法采用简化的距离测度函数作为阈值选取标准,以减少计算量和便于多阈值扩展; 采用基于后处理原理的图像分割方式,以进一步增强算法的抗噪性; 运用分子动理论优化算法实现加快计算速度.某厂氧化铝回转窑火焰图像的分割实验表明,该算法抗噪性强,运算速度快,能较为精确地分割出火焰图像的背景区、黑把子、火焰区、辐射带、物料区等区域.Abstract: Influenced by high temperature, high dust and other factors, an alumina rotary kiln flame image often contains noise. The existing algorithms for flame image segmentation have deficiencies such as poor anti-noise capability, long computing time and so on. This paper proposes an improved Otsu method based on histogram oblique segmentation for the segmentation of alumina rotary kiln flame images. To reduce the amount of calculation and be convenient for multi-threshold extension, a simplified distance measure function is used as the threshold selection criterion. To further enhance the anti-noise capability, a post-processing based segmentation method is adopted. And a kinetic-molecular theory based optimization algorithm (KMTOA) is used to accelerate the calculation speed. The segmentation experiments of rotary kiln flame image show that the proposed method has stronger anti-noise capability, faster calculation speed, and can more precisely get the background area, black handle, flame area, illuminated area and the material area.
-
[1] Li Wei-Tao, Wang Dian-Hui, Chai Tian-You. Flame image-based burning state recognition for sintering process of rotary kiln using heterogeneous features and fuzzy integral. IEEE Transactions on Industrial Informatics, 2012, 8(4): 780-790 [2] Jiang Hui-Yan, Wang Xiao-Dan, Zhou Xiao-Jie, Chai Tian-You. Study on soft sensor for temperature of burning zone based on SVR. Journal of System Simulation, 2008, 20(11): 2951-2955(姜慧研, 王晓丹, 周晓杰, 柴天佑. 基于SVR的回转窑烧成带温度软测量方法的研究. 系统仿真学报, 2008, 20(11): 2951-2955) [3] Zhang Xiao-Gang, Chen Hua, Zhang Jing, Liu Xiao-Yan. Intelligent predictive control strategy applied to sintering temperature in rotary kiln based on image feedback. Control Theory & Applications, 2007, 24(6): 995-998(张小刚, 陈华, 章兢, 刘小燕. 基于图像反馈的回转窑烧结温度智能预测控制. 控制理论与应用, 2007, 24(6): 995-998) [4] Li Wei-Tao, Wang Dian-Hui, Chai Tian-You. Burning state recognition of rotary kiln using ELMs with heterogeneous features. Neurocomputing, 2013, 102(15): 144-153 [5] Li Shu-Tao, Wang Yao-Nan, Zhang Chang-Fan. Neural network control system for rotary kiln based on features of combustion flame. Acta Automatica Sinica, 2002, 28(4): 591-595(李树涛, 王耀南, 张昌凡. 基于燃烧火焰图像特征的回转窑神经网络控制系统. 自动化学报, 2002, 28(4): 591-595) [6] Zhang Xing. The study and implement of the segmentation of the flame images of the rotary kiln [Master dissertation], Northeastern University, China, 2006, 43-45 (张星. 回转窑火焰图像分割方法的研究与实现[硕士学位论文]. 东北大学, 中国, 2006, 43-45) [7] Yi Zheng-Ming, Lv Zi-Jian, Liu Zhi-Ming. Flame image processing and its characteristic extraction for alumina rotary kiln. Chinese Journal of Scientic Instrument, 2006, 27(8): 969-972(易正明, 吕子剑, 刘志明. 氧化铝回转窑火焰图像处理与特征提取. 仪器仪表学报, 2006, 27(8): 969-972) [8] Chen Hua, Zhang Jing, Zhang Xiao-Gang, Hu Yi-Han. A robust-ELM approach based on Parzen windows estimation for kiln sintering temperature detection. Acta Automatica Sinica, 2012, 38(5): 841-849(陈华, 章兢, 张小刚, 胡义函. 一种基于Parzen窗估计的鲁棒ELM 烧结温度检测方法. 自动化学报, 2012, 38(5): 841-849) [9] Liu Jian-Zhuang, Li Wen-Qing. Automatic thresholding of gray-level pictures using two-dimension Otsu method. Acta Automatica Sinica, 1993, 19(1): 101-105(刘健庄, 栗文清. 灰度图像的二维Otsu自动阈值分割法. 自动化学报, 1993, 19(1): 101-105) [10] Wu Yi-Quan, Wu Wen-Yi, Pan Zhe. A fast iterative algorithm of the Otsu threshold based on two-dimensional histogram oblique segmentation. Journal of Engineering Graphics, 2009, (5): 89-96(吴一全, 吴文怡, 潘 喆. 二维直方图区域斜分Otsu阈值分割的快速迭代算法. 工程图学学报, 2009, (5): 89-96) [11] Zhao Feng, Fan Jiu-Lun. Three-dimensional Otsu's method with non local spatial gray information. Computer Engineering and Application, 2013, 49(3): 30-39(赵凤, 范九伦. 融合非局部空间灰度信息的三维Otsu法. 计算机工程与应用, 2013, 49(3): 30-39) [12] Chen Q, Zhao L, Lu J, Kuang G, Wang N, Jiang Y. Modified two-dimensional Otsu image segmentation algorithm and fast realization. Measurement, 2011, 44(10): 1828-1848 [13] Sathya P D, Kayalvizhi R. Amended bacterial foraging algorithm for multi-level thresholding of magnetic resonance brain images. IET Image Processing, 2012, 6(4): 426-433 [14] Zhou De-Long, Zong Jun-Bin. Minimum error thresholding based on two dimensional histogram. In: Proceedings of 2009 WRI World Congress on Computer Science and Information Engineering. Los Angeles, California, NewYork, USA, 2009, 7: 169-175 [15] Cuevas E, Sencion F, Zaldivar D, Perez-cisneros M, Sossa H. A multi-threshold segmentation approach based on artificial cee colony optimization. Applied Intelligence, 2012, 37(3): 321-336 [16] Zhang Ai-Hua, Yu Sheng-Sheng, Zhou Jin-Li. A post-processing method of two-dimensional thresheolding image segmentation. Journal of Huazhong University of Science and Technology, 2002, 30(10): 59-61(张爱华, 余胜生, 周敬利. 一种二维直方图阈值化图像分割的后处理方法. 华中科技大学学报, 2002, 30(10): 59-61) [17] Fan Chao-Dong, Ouyang Hong-Lin, Zhang Ying-Jie, Ai Zhao-Yang. Optimization algorithm based on Kinetic-molecular theory. Journal of Central South University, 2013, 20(12): 3504-3512 [18] Zhang Hong, Fan Jiu-Lun. Two-dimensional Arimoto entropy linear-type threshold segmentation method. Acta Photonica Sinica, 2013, 42(2): 234-240(张弘, 范九伦. 二维Arimoto熵直线型阈值分割法. 光子学报, 2013, 42(2): 234-240)
点击查看大图
计量
- 文章访问数: 1397
- HTML全文浏览量: 70
- PDF下载量: 969
- 被引次数: 0