基于Mean Shift的芯片X光图像层次分割算法.pdfVIP

传感器与微系统（Transducer and Microsystem Technologies） ２０１６ 年 第 ３５ 卷 第 ６ 期 ＤＯI：１０. １３８７３ / J. １０００—９７８７（２０１６）０６—０１２８—０４ 基于 Ｍｅaｎ Ｓｈｉｆｔ的芯片 X光图像层次分割算法 宋淑娟，吴静静，安 伟，秦 煜，张 洪，周德强 （江南大学 机械工程学院，江苏 无锡 214122） 摘 要：针对芯片 X光图像多目标、背景复杂、灰度分布不均匀的特点，提出一种基于 Mean Shift 的层次 分割算法。运用旋转缩放不变的模板匹配定位算法定位芯片并确定其兴趣区域（ROI），从而实现外层分 割。再运用 Mean Shift算法对芯片模板图像和芯片 ROI 图像进行统计聚类分析，分别计算原图像金线模 式类的灰度平均值，以芯片模板图像的金线模式类的平均灰度为基准，对芯片 ROI 的聚类图像采用优化 阈值进行自适应阈值分割，从而实现内层分割。实验结果表明：与传统的均值偏移分割算法相比，该方法 的多目标分割准确，可靠性高。 关键词：Mean Shift；层次分割；兴趣区域；自适应阈值 中图分类号：TP３９１ 文献标识码：A 文章编号：１０００—９７８７（２０１６）０６—０１２８—０４ Ｍｅaｎ Ｓｈｉｆｔ-baｓｅd ｈｉｅｒaｒｃｈｉｃal ｓｅgmｅｎｔaｔｉｏｎ algｏｒｉｔｈm ｏｆ X-ｒay ｉmagｅ ｏｆ ｃｈｉｐｓ SONG Shu-juan，WU Jing-jing，AN Wei，QIN Yu，ZHANG Hong，ZHOU De-qiang （Ｓｃｈｏｏl ｏｆ Ｍｅｃｈaｎｉｃal Ｅｎgｉｎｅｅｒｉｎg，Jｉaｎgｎaｎ Uｎｉｖｅｒｓｉｔy，Wｕxｉ 214122，Cｈｉｎa） Ａbｓｔｒaｃｔ：To overcome segmentation difficulties induced by multiple targets of interests，redundant background and inhomogeneous gray levels of the X ray image，a hierarchical segmentation algorithm based on Mean Shift is proposed. The algorithm is achieved through two layer segmentation. The outer layer segmentation is to locate the positions and determine their regions of interests（ROI）for all single chips in the X ray by the matching algorithm with the template of scale invariance and rotation invariance. The inner layer segmentation is to extract sub objects，i. e.，gold lines，balls and PAD of each chip by clustering and analyzing the ROI image and template image using the Mean Shift algorithm. Then calculates mean gray values of gold lines pattern regions for ROI and template images respectively. Finally，according to the mean gray values of sub patterns in the template，design an optimized threshold and segment the ROI image by the adaptive threshold segmentation algorithm. The experimental results show that the proposed segmentation algorithm achieves more accurate and reliable results compared with traditional algorithms. Kｅy ｗｏｒdｓ：Mean Shift；hierarchical segmentation；region of interest（ROI）；adapti