Segmentation of Surface Defects in Cold Rolling of Thin Strip by using Threshold Decomposition
-
摘要: 为分割具有低对比度和噪声复杂的冷轧极薄带钢缺陷,在二维Otsu分割算法的基础上进行了改进。为了避免在一个很大的二维空间上搜索阈值,分解二维Otsu分割算法的二维直方图,分别在图像像素灰度直方图和像素邻域灰度直方图上进行阈值求解,并将获得的阈值作为最佳分割阈值。为改善分解过程中忽略的边缘和噪声影响,将平衡因子加入到像素邻域灰度分割阈值求解中。最后通过大量实验对二维Otsu分割算法、量子粒子群双阈值分割算法和改进分割算法的分割结果进行对比分析。实验表明,该算法能够快速高效地分割出冷轧极薄带钢表面的各种缺陷。Abstract: Two-dimensional Otsu algorithm was improved in order to segment the defects of low contrast and complex noise in cold rolling of thin strip. In order to avoid searching threshold in a large two-dimensional space, two-dimensional Otsu algorithm of two-dimensional histogram has decomposed. The algorithm solves threshold in the image pixel gray histogram and gray histogram neighborhood pixels respectively. The balance factor to the pixel neighborhood grayscale was added in solving the segmentation threshold and using the threshold as the best image segmentation threshold. Finally, the segmentation result was analyzed through a large number of experiments, comparing with two-dimensional Otsu algorithm, Quantum-behaved particle swarm optimization (QPSO) and improved algorithm. The results show that the method can quickly and efficiently split out various defects on the surface of cold rolled thin strip in computer vision.
-
Key words:
- cold rolled thin strip /
- Otsu /
- decomposition /
- threshold
-
[1] 吴贵芳,徐科,杨朝霖.钢板表面质量在线监测技术[M].北京:科学出版社,2010 Wu G F, Xu K, Yang Z L. Steel plate surface quality on-line monitoring technology[M]. Beijing:Science Press, 2010 (in Chinese) [2] 谢光伟,仲兆准,钟胜奎,等.带钢表面图像缺陷区域的分割方法[J].计算机系统应用,2014,23(10):239-243 Xie G W, Zhong Z Z, Zhong S K, et al. Methods of defect region segmentation for strip surface image[J]. Computer Systems & Applications, 2014,23(10):239-243 (in Chinese) [3] 管声启,师红宇,王燕妮.基于图像零均值化的带钢缺陷检测[J].钢铁研究学报,2013,25(4):59-62 Guan S Q, Shi H Y, Wang Y N. Strip steel defect detection based on zero-mean method[J]. Journal of Iron and Steel Research, 2013,25(4):59-62 (in Chinese) [4] 汪海洋,潘德炉,夏德深.二维Otsu自适应阈值选取算法的快速实现[J].自动化学报,2007,33(9):968-971 Wang H Y, Pan D L, Xia D S. A fast algorithm for two-dimensional Otsu adaptive threshold algorithm[J]. Acta Automatica Sinica, 2007,33(9):968-971 (in Chinese) [5] 徐帅华,管声启,陈龙龙,等.小波分解在带钢缺陷检测中的应用[J].计算机与现代化,2014,(7):146-149 Xu S H, Guan S Q, Chen L L, et al. Application of wavelet decomposition in steel strip defect detection[J]. Computer and Modernization, 2014,(7):146-149 (in Chinese) [6] Choi S H, Yun J P, Seo B, et al. Real-time defects detection algorithm for high-speed steel bar in coil[J]. Enformatika, 2007,19:66-70 [7] Helen R, Kamaraj N, Selvi K, et al. Segmentation of pulmonary parenchyma in CT lung images based on 2D Otsu optimized by PSO[C]//Proceedings of 2011 International Conference on Emerging Trends in Electrical and Computer Technology. Nagercoil, India:IEEE, 2011:536-541 [8] Zhu Q D, Jing L Q, Bi R S. One-dimensional threshold average decomposition for two-dimensional Ostu algorithm[C]//Proceedings of Chinese Control and Decision Conference. Xuzhou, China:IEEE, 2010:2783-2788 [9] 范九伦,赵凤.灰度图像的二维Otsu曲线阈值分割法[J].电子学报,2007,35(4):751-755 Fan J L, Zhao F. Two-dimensional Otsu's curve thresholding segmentation method for gray-level images[J]. Acta Electronica Sinica, 2007,35(4):751-755 (in Chiness) [10] 范九伦,赵凤,张雪峰.三维Otsu阈值分割方法的递推算法[J].电子学报,2007,35(7):1398-1402 Fan J L, Zhao F, Zhang X F. Recursive algorithm for three-dimensional Otsu's thresholding segmentation method[J]. Acta Electronica Sinica, 2007,35(7):1398-1402 (in Chiness) [11] 刘金,唐权华,余志斌,等.基于三维直方图降维和重建的快速最小误差阈值法[J].电子与信息学报,2014,36(8):1859-1865 Liu J, Tang Q H, Yu Z B, et al. Fast minimum error thresholding based on dimension reduction and rebuilding of the 3-dimensional histogram[J]. Journal of Electronics & Information Technology, 2014, 36(8):1859-1865 (in Chinese) [12] 吴一全,樊军,吴诗婳.改进的二维Otsu法阈值分割快速迭代算法[J].电子测量与仪器学报,2011,25(3):218-225 Wu Y Q, Fan J, Wu S H. Fast iterative algorithm for image segmentation based on an improved two-dimensional Otsu thresholding[J]. Journal of Electronic Measurement and Instrument, 2011,25(3):218-225 (in Chinese) [13] 冯斌,王璋,孙俊.基于量子粒子群算法的Ostu图像阈值分割[J].计算机工程与设计,2008,29(13):3429-3431,3434 Fen B, Wang Z, Sun J. Image threshold segmentation with Ostu based on quantum-behaved particle swarm algorithm[J]. Computer Engineering and Design, 2008,29(13):3429-3431,3434 (in Chinese) [14] 崔兆华,高立群,欧阳海滨,等.融合全局最好和声搜索算法的模糊C均值聚类图像分割[J].中国图象图形学报,2013,18(9):1133-1141 Cui Z H, Gao L Q, Ouyang H B, et al. Improved fuzzy C-means clustering combined with the global best harmony search algorithm for image segmentation[J]. Journal of Image and Graphics, 2013,18(9):1133-1141 (in Chinese) [15] 宋克臣,颜云辉,彭怡书,等.引入局部信息的带钢缺陷图像凸优化活动轮廓分割模型[J].机械工程学报,2012,48(20):1-7 Song K C, Yan Y H, Peng Y S, et al. Convex active contour segmentation model of strip steel defects image based on local information[J]. Journal of Mechanical Engineering, 2012,48(20):1-7 (in Chinese)
点击查看大图
计量
- 文章访问数: 194
- HTML全文浏览量: 35
- PDF下载量: 3
- 被引次数: 0