针对传统条码识读方法对微小数据矩阵（DM）码定位精度低、速度慢等问题,提出了以Harris角点作为高频特征,构建高斯金字塔过滤背景金属纹理角点,引入径向基函数平滑角点密度图,通过阈值分割以及区域生长粗定位候选区域,计算2步最小外接矩形并校正实现精定位,最后建立筛选模型选择适应值最大的候选区域为DM码区域.实验表明,提出的采用角点检测和区域生长定位检测算法对受到金属纹理、局部遮挡、磨损划痕以及光照不均等干扰的微小DM码具有很强的鲁棒性,精定位准确率高,仅耗时25ms,比传统方法提高了30倍.
Focusing on the deficiencies of traditional data matrix (DM) code localization methods in speed and precision, we proposed a code localization method that structured Gaussian pyramid to extract Harris corner features. Corner density map was smoothed by radial basis function, and rough candidate regions were obtained by threshold and region growing. Next, we computed two stage minimum-area encasing rectangle to implement accurate localization. Finally, we chose the candidate region with maximum score based on three properties of DM code as the real DM region. The result shows that our method which used corner detection and regional growth is robust to the various interferences with high accuracy, such as metal texture, high reflection, scratch marks and occlusion on DM code. The localization time is 25ms, which is 30 times faster than the compared methods.
［1］TIANFIELD H. Advanced life-cycle model for complex product development via stage-aligned information-substitutive concurrency and detour［J］. International Journal of Computer Integrated Manufacturing, 2010, 14(3): 281-303.
［2］LI X S, HE W P, LEI L, et al. Laser direct marking applied to rasterizing miniature Data Matrix Code on aluminum alloy［J］. Optics & Laser Technology, 2016, 77: 31-39.
［3］HUANG Q, CHEN W, HUANG X, et al. Data matrix code localization based on finder pattern detection and bar code border fitting［J］. Mathematical Problems in Engineering, 2012, 2: 199-210.
［4］LENG B. A data matrix-based mutant code design and recognition research［C］∥International Conference on Image and Graphics. Washington, D.C., USA: IEEE Computer Society, 2007: 570-574.
［5］LEONG L K, WANG Y. Extraction of 2d barcode using keypoint selection and line detection［C］∥Paci-fic-Rim Conference on Multimedia. Bangkok, Thailand: Springer Berlin Heidelberg. 2009: 826-835.
［6］HA J E. A new method for detecting data matrix under similarity transforms for machine vision applications［J］. International Journal of Control Automation & Systems, 2011, 9(4): 737-741.
［7］王伟, 何卫平, 雷蕾, 等. 污染及多视角下Data Matrix码精确定位［J］. 计算机辅助设计与图形学学报, 2013, 25(9): 1345-1353.
WANG Wei, HE Weiping, LEI Lei, et al. Accurate location of polluted Data Matrix code from multiple views［J］. Journal of Computer-Aided Design & Computer Graphics, 2013, 25(9): 1345-1353.
［8］HU H, XU W, HUANG Q. A 2D barcode extraction method based on texture direction analysis［C］∥International Conference on Image & Graphics. ［S.l.］: IEEE, 2010: 759-762.
［9］王伟, 何卫平, 雷蕾, 等. 复杂金属背景下二维条码区域的快速定位［J］. 天津大学学报(自然科学与工程技术版), 2013, 46(6): 531-538.
WANG Wei, HE Weiping, LEI Lei, et al. Speedy location of 2D barcode region under complicated metal background［J］. Journal of Tianjin University (Science and Technology), 2013, 46(6): 531-538.
［10］王娟, 王萍, 王港. 基于自适应超像素分割的点刻式DPM区域定位算法研究［J］. 自动化学报, 2015, 41(5): 991-1003.
WANG Juan, WANG Ping, WANG Gang . Stippled direct part mark location based on self-adaptive super-pixels segmentation［J］. Acta Automatica Sinica, 2015, 41(5): 991-1003.
［11］PARIKH D, JANCKE G. Localization and segmentation of a 2D high capacity color barcode［C］∥Applications of Computer Vision. CO, USA: IEEE Computer Society, 2008: 1-6.
［12］CHU C H, YANG D N, PAN Y L, et al. Stabilization and extraction of 2D barcodes for camera phones［J］. Multimedia Systems, 2011, 17(2): 113-133.
［13］LOWE D G. Distinctive image features from scale-invariant keypoints［J］. International Journal of Computer Vision, 2004, 60(2): 91-110.
［14］XU W, MCCLOSKEY S. 2D Barcode localization and motion deblurring using a flutter shutter camera［C］∥Applications of Computer Vision. Hawaii, USA: IEEE, 2011: 159-165.
［15］OHTSU N. A threshold selection method from gray-level histograms［J］. IEEE Transactions on Systems, Man, and Cybernetics, 2007, 9(1): 62-66.
［16］FREEMAN H, SHAPIRA R. Determining the minimum-area encasing rectangle for an arbitrary closed curve［J］. Communications of the ACM, 1975, 18(7): 409-413.
