The template matching method has been widely utilized in the defect detection of wafer surfaces. However, the traditional matching approaches are limited by illumination, noise, and deformation, which cannot meet the requirements of accuracy and robustness. In this paper, a novel multiple targets localization method, named Normalized Cross-correlation Adaptive Variable Step-Size Dynamic Template (NCC-AVSSDT) matching, is proposed to improve the accuracy and efficiency of image localization, which combines the advantages of NCC and AVSSDT. The AVSSDT method is utilized to dynamically adjust the scanning step size based on the NCC matching coefficients. This approach optimizes the scanning process, accelerating convergence toward the optimal matching position. Experimental results verify the accuracy and robustness of the proposed method under different conditions, especially when dealing with rotational variations and variations in noise textures. Therefore, NCC-AVSSDT can be used to perform multiple targets localization of chip image in nearly real-time. Three experiment types were used for comprehensive evaluations, including multiple targets, noise, and rotation angles. Experimental results show that NCC-AVSSDT is much better than the sequential similarity detection algorithm and mean absolute deviation methods in terms of multiple targets (0.667 vs 0.811 s, 0.832 s) and success rate (100% vs 35%, 20%).

中文翻译：

---

基于归一化互相关自适应变步长动态模板匹配的多目标定位新方法

模板匹配法在晶圆表面缺陷检测中得到了广泛的应用。然而，传统的匹配方法受到光照、噪声和变形的限制，无法满足精度和鲁棒性的要求。本文结合NCC和AVSSDT的优点，提出了一种新颖的多目标定位方法，即归一化互相关自适应可变步长动态模板（NCC-AVSSDT）匹配，以提高图像定位的精度和效率。 。利用AVSSDT方法根据NCC匹配系数动态调整扫描步长。这种方法优化了扫描过程，加速收敛到最佳匹配位置。实验结果验证了该方法在不同条件下的准确性和鲁棒性，特别是在处理旋转变化和噪声纹理变化时。因此，NCC-AVSSDT可用于近乎实时地对芯片图像进行多目标定位。采用多目标、噪声、旋转角度三种实验类型进行综合评价。实验结果表明，NCC-AVSSDT在多目标（0.667 vs 0.811 s、0.832 s）和成功率（100% vs 35%、20%）方面均明显优于序贯相似性检测算法和平均绝对偏差方法。