Stippled Direct Part Mark Location Based on Self-adaptive Super-pixels Segmentation
-
摘要: 为解决点刻式直接零件标志(Direct part mark, DPM)码基本单元分割困难、区域定位欠精确等问题, 提出使用超像素分割和谱聚类相结合的算法,对含有DPM区域的图像进行初步分割和精确定位. 首先为提高超像素分割的准确、快速和完整性,本文利用近邻传播聚类思想实现自动聚类得到超像素区域, 并引入边缘置信度调整超像素边缘,形成自适应边缘简单线性迭代聚类 (Adaptive edge simple linear iterative clustering, AE-SLIC)算法. 该算法改进了简单线性迭代聚类(Simple linear iterative clustering, SLIC)超像素分割算法存在的未明确界定超像素区域边缘信息和分割数目无法自适应确定等问题; 其次,将超像素作为谱聚类中图的顶点进行二次聚类, DPM区域内超像素因相似度高而被聚集为一类, 从而完成点刻式DPM区域的精确定位.经实验测试和分析,本文算法得到的超像素分割结果在完整性、 运算复杂度等方面优于常见的超像素分割算法.与基于像素点运算的传统定位算法相比, 本文算法具有良好的实时性、定位准确率和鲁棒性.
-
关键词:
- 超像素 /
- 自适应边缘简单线性迭代聚类算法 /
- 谱聚类 /
- 精确定位
Abstract: In order to solve the problem existing in segmentation and location of the stippled direct part mark (DPM) code, this paper combines the advantages of super-pixels segmentation and spectral clustering algorithm to pre-segment and precisely locate the DPM area. First, we propose an adaptive edge simple linear iterative clustering (AE-SLIC) super-pixels segmentation algorithm to achieve accurate, fast and integral segmentation. The super-pixels are generated by affinity propagation automatically and edges of super-pixels are adjusted by edge confidence in AE-SLIC, which has improved the problems of unclear definition of edge and non-adaptive number of super-pixels in the simple linear iterative clustering (SLIC) algorithm. Second, the super-pixels are treated as the vertexes of spectral clustering. Then the location of stippled DPM code is completed by the clustered group of the super-pixels. The experimental results demonstrate the superior performance of the AE-SLIC algorithm in terms of segmentation accuracy and computation efficiency. Through comparison with the traditional location algorithm based on the operation of pixels, the proposed algorithm shows its property of real-time, location accuracy and robustness to the noise disturbance. -
[1] Information Technology Automatic Identification and Data Capture Techniques-Guidelines for Direct Part Marking (DPM), ISO/IEC TR 24720-2008 (E), 2008. [2] [2] Ha J E. A new method for detecting data matrix under similarity transform for machine vision applications. International Journal of Control Automation and Systems, 2011, 9(4): 737-741 [3] [3] Wang W, He W P, Lei L, Guo G F. Polluted and perspective deformation DataMatrix code accurate locating based on multi-features fusion. Chinese Journal of Electronics, 2014, 23(3): 550-556 [4] Wang Wei, He Wei-Ping, Lei Lei, Guo Gai-Fang, Niu Jin-Bo. Accurate location of polluted DataMatrix code from multiple views. Journal of Computer-Aided Design and Computer Graphics, 2013, 25(9): 1345-1353(王伟, 何卫平, 雷蕾, 郭改放, 牛晋波. 污染及多视角下DataMatrix码精确定位. 计算机辅助设计与图形学学报, 2013, 25(9): 1345-1353) [5] [5] Chu C H, Yang D N, Pan Y L, Chen M S. Stabilization and extraction of 2D barcode for camera phones. Multimedia Systems, 2011, 17(2): 113-133 [6] [6] Yang H J, Jiang X D, Kot A C. Accurate localization of four extreme corners for barcode images captured by mobile phones. In: Proceedings of the 17th IEEE International Conference on Image Processing. Hong Kong, China: IEEE, 2010. 3897-3900 [7] Han Shou-Dong, Zhao Yong, Tao Wen-Bing, Sang Nong. Gaussian super-pixel based fast image segmentation using graph cuts. Acta Automatica Sinica, 2011, 37(1): 11-20(韩守东, 赵勇, 陶文兵, 桑农. 基于高斯超像素的快速Graph Cuts图像分割方法. 自动化学报, 2011, 37(1): 11-20) [8] [8] Felzenswalb P F, Huttenlocher D P. Efficient graph-based image segmentation. International Journal of Computer Vision, 2004, 59(2): 167-181 [9] [9] Shi J, Malik J. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888-905 [10] Moore A, Prince S, Warrell J, Mohammed U, Jones G. Superpixel lattices. In: Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK: IEEE, 2008. 1-8 [11] Liu M Y, Tuzel O, Ramalingam S, Chellappa R. Entropy rate superpixel segmentation. In: Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI: IEEE, 2011. 2097-2104 [12] Levinshtein A, Stere A, Kutulakos K N, Fleet D J, Dickinson S J, Siddiqi K. Turbopixels: fast superpixels using geometric flows. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(12): 2290-2297 [13] Vedaldi A, Soatto S. Quick shift and kernel methods for mode seeking. In: Proceedings of the 2008 Computer Vision ECCV 2008. Berlin, Heidelberg: Springer, 2008. 705-718 [14] Zhu Jian-Yong, Gui Wei-Hua, Yang Chun-Hua, Wu Jia, Zhou Wen-Zhen. Reagent dosage control based on bubble size random distribution for copper roughing. Acta Automatica Sinica, 2014, 40(10): 2089-2097(朱建勇, 桂卫华, 阳春华, 吴佳, 周文振. 基于泡沫尺寸随机分布的铜粗选药剂量控制. 自动化学报, 2014, 40(10): 2089-2097) [15] Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Ssstrunk S. SLIC Superpixels. EPFL Technical Report 149300, Swiss Federal Institute of Technology in Lausanne, Swiss, 2010. [16] Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Ssstrunk S. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282 [17] Ren C Y, Reid I. gSLIC: A Real-time Implementation of SLIC Superpixel Segmentation. Technical Report, Department of Engineering, University of Oxford, UK, 2011. [18] Lucchi A, Li Y P, Smith K, Fua P. Structured image segmentation using kernelized features. In: Proceedings of the 12th European Conference on Computer Vision ECCV 2012. Berlin, Heidelberg: Springer, 2012. 400-413 [19] Lin C H, Chen C C, Lee H L, Liao J R. Fast K-means algorithm based on a level histogram for image retrieval. Expert Systems with Application, 2014, 41(7): 3276-3283 [20] Frey B J, Dueck D. Clustering by passing messages between data points. Science, 2007, 315(5814): 972-976 [21] Zhang Jian-Peng, Chen Fu-Cai, Li Shao-Mei, Liu Li-Xiong. Data stream clustering algorithm based on density and affinity propagation techniques. Acta Automatica Sinica, 2014, 40(2): 277-288(张建朋, 陈福才, 李邵梅, 刘力雄. 基于密度与近邻传播的数据流聚类算法. 自动化学报, 2014, 40(2): 277-288) [22] Wang Pei-Zhen, Mao Xue-Qin, Mao Xue-Fei, Gao Shang-Yi, Zhang Dai-Lin. Coke micrograph segmentation based on mean shift and edge confidence. Journal of Image and Graphics, 2010, 15(10): 1478-1484(王培珍, 毛雪芹, 毛雪菲, 高尚义, 张代林. 基于均值偏移和边缘置信度的焦炭显微图像分割. 中国图象图形学报, 2010, 15(10): 1478-1484) [23] Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, CA, USA: IEEE, 2005. 886-893 [24] Applying Data Matrix Identification Symbols on Aerospace Parts, NASA-STD-6002 A, 2008. [25] Zhou Lin, Ping Xi-Jian, Xu Sen, Zhang Tao. Cluster ensemble based on spectral clustering. Acta Automatica Sinica, 2012, 38(8): 1335-1342(周林, 平西建, 徐森, 张涛. 基于谱聚类的聚类集成算法. 自动化学报, 2012, 38(8): 1335-1342) [26] Shen J J, Hsu P W. A fragile associative watermarking on 2D barcode for data authentication. International Journal of Network Security, 2008, 7(3): 301-309
点击查看大图
计量
- 文章访问数: 1915
- HTML全文浏览量: 79
- PDF下载量: 1488
- 被引次数: 0