﻿ 基于改进模板匹配的晶圆划切算法 Algorithm for Wafer Slicing Based on Improved Template Matching

Journal of Image and Signal Processing
Vol.06 No.03(2017), Article ID:21262,8 pages
10.12677/JISP.2017.63017

Algorithm for Wafer Slicing Based on Improved Template Matching

Chenshu Gao, Rui Zhai, Jian Xue*, Ke Lv

School of Engineering Science, University of Chinese Academy of Sciences, Beijing

Received: Jun. 15th, 2017; accepted: Jul. 3rd, 2017; published: Jul. 6th, 2017

ABSTRACT

Nowadays the domestic industrial applications of wafer automatic slicing mainly adopt gray-based template matching method. However, its calculation is quite time-consuming with low slicing efficiency. This paper proposes an improved template matching algorithm based on geometric edge to achieve the goal of accelerating the traditional algorithm. It generates appropriate edge template by Canny edge detection; calculates the gradient direction of template edge curve, which is used to calculate similarity as matching information; optimizes the searching strategy by using the similarity threshold determination. Then, the rough traversal matching is implemented at the top layer of the image pyramid and the matching process continues layer by layer until the bottom. The result of experiment shows that the algorithm proposed in this paper performs high robustness, which can obtain good matching result under different conditions of objectives, including uniform or non-uniform illumination and partial occlusion. Besides, it meets the real-time requirement while the accuracy is ensured, which can be applied to practical industry of automatic wafer image slicing.

Keywords:Template Matching, Geometric Features, Similarity Measures Function, Image Pyramid Layer

1. 引言

2. 模板匹配简介

3. 优化的模板匹配方法

3.1. 加速的相似性度量计算方法

(1)

(2)

(3)

3.2. 相似性度量的停止标准

1) 提取出模板图像的边缘信息后，将边缘点分为2部分。设模板边缘点数为n，n1、n2分别为两部分的边缘点个数，且n1 + n2 = n，第1部分n1个零散点作为试探点，即先选择离模板左上角距离最远的边缘点作为第1点，再在到第1点的距离最远的边缘点作为第2个点；在剩余的边缘点中，选择到前面两点距离和最大的点作为第3点，依次而得到n1个点作为第1部分的点，剩余的边缘点作为第2部分，

2) 计算第1部分n1个点的部分相似度量值，计算完后与设定的阈值判断若，则停止计算本次相似度量值，

3) 若，则在的基础上，继续计算第2部分n2个点的部分相似度量值，从而得到完整的相似度量值，停止计算本次相似度量值。

3.3. 图像金字塔加速策略

(4)

Figure 1. Flow chart of stopping criteria optimization algorithm

4. 检测结果与分析

Figure 2. Image pyramid layer

Figure 3. Template matching result 1

Figure 4. Template matching result 2

Figure 5. Template matching result 3

Table 1. Comparision of this algorithm with the traditional matching algorithm based on edge and gray

5. 结束语

Algorithm for Wafer Slicing Based on Improved Template Matching[J]. 图像与信号处理, 2017, 06(03): 139-146. http://dx.doi.org/10.12677/JISP.2017.63017

1. 1. 马金奎, 等. 机器视觉测试系统[J]. 工具技术, 2004(9): 129-132.

2. 2. 杨云龙, 刘金荣. 全自动划片机自动对准技术的研究[J]. 电子工业专业设备, 2004, 100(3): 47.

3. 3. 王明权, 王宏智. 全自动划片机的关键技术研究[J]. 电子工业专用设备, 2007, 145: 31-32.

4. 4. 汪宏昇, 史铁林. 高精密机器视觉对准系统的研究与设计[J]. 光学技术, 2004, 30(2): 235.

5. 5. http://baike.baidu.com/view/1345922.html

6. 6. Li, Y., Zhang, X.D. and Bao, Y.L. (2012) Method Based on Feature Template Matching to Identify Special Icons in Map. Journal of Electronic Measurement and Instrument, 26, 605-609.

7. 7. 王静, 王海亮, 向茂生, 等. 基于非极大值抑制的圆目标亚像素中心定位[J]. 仪器仪表学报, 2012, 33(7): 1460- 1468.

8. 8. 张浩鹏, 王宗义. 基于灰度方差和边缘密度的车牌定位算法[J]. 仪器仪表学报, 2011, 32(5): 1095-1102.

9. 9. 傅卫平, 秦川, 刘佳, 等. 基于SIFT算法的图像目标匹配与定位[J]. 仪器仪表学报, 2011, 32(1): 163-169.

10. 10. Huttenlocher, D.P., Klanderman, G.A. and Rucklidge, J. (1993) Comparing Images Using the Hausdorff Distance. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15, 850-863. https://doi.org/10.1109/34.232073

11. 11. Ulrich, M., Steger, C. and Baumgartner, A. (2003) Real-Time Object Recognition Using a Modified Generalized Hough Transform. Pattern Recognition, 36, 2557-2570. https://doi.org/10.1016/S0031-3203(03)00169-9

12. 12. Paramanand, C. and Rajagopalan, A.N. (2010) Efficient Geometric Matching with Higher-Order Features. Optical Society of America, 27, 739-748. https://doi.org/10.1364/JOSAA.27.000739

13. 13. Brown, L.G. (1992) A Survey of Image Registration Techniques. Department of Computer Science, Columbia University, New York.

14. 14. Zitova, B. and Flusser, J. (2003) Image Registration Methods: A Survey. Image and Vision Computing, 23-34.

15. 15. Shark, L.K., Kurekin, A.A. and Matuszewski, B.J. (2007) Development and Evaluation of Fast Branch-and-Bound Algorithm for Feature Matching Based on Line Segments. Pattern Recognition, 40, 1432-1450. https://doi.org/10.1016/j.patcog.2006.10.022

16. 16. 杨通钰, 彭国华. 基于NCC的图像匹配快速算法[J]. 现代电子技术, 2010(22): 107-109.

17. 17. 黄真宝, 陈阳. 图像匹配中NCC算法的一种快速实现方法[J]. 信息化研究, 2011(4): 48-52.

18. NOTES

*通讯作者。