Enhanced GPT Correlation for 2D Projection Transformation Invariant Template Matching
Enhanced GPT Correlation for 2D Projection Transformation Invariant Template Matching
复制标题
用于 2D 投影变换不变模板匹配的增强 GPT 相关性
DOI：
10.1007/978-3-319-24947-6_36
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
Toru Wakahara and Yukihiko Yamashita
中科院分区：
文献类型：
--
作者：
T. Uehara;T. Tanaka;and S. Fiori;Toru Wakahara and Yukihiko Yamashita
本文提出了一种改进的二维投影变换不变模板匹配技术——GPT （Global projection transformation）关联。关键思想有三个方面。首先，我们证明了任意有8个参数的二维投影变换（PT）可以用一个更简单的表达式来近似。其次，使用更简单的PT表达式，我们提出了一个有效的计算模型，用于确定PT的次优8个参数，这些参数最大化了PT叠加输入图像与模板之间的归一化互相关值。第三，通过逐次迭代法得到PT的最优8个参数。使用模板及其带有随机噪声的人为扭曲图像作为输入图像的实验表明，该方法远优于之前的GPT相关方法。此外，该方法对手写数字进行k-NN分类，通过其抗失真模板匹配能力，显示出较高的识别精度。
This paper describes a newly enhanced technique of 2D projection transformation invariant template matching, GPT (Global Projection Transformation) correlation. The key ideas are threefold. First, we show that arbitrary 2D projection transformation (PT) with a total of eight parameters can be approximated by a simpler expression. Second, using the simpler PT expression we propose an efficient computational model for determining sub-optimal eight parameters of PT that maximize a normalized cross-correlation value between a PT-superimposed input image and a template. Third, we obtain optimal eight parameters of PT via the successive iteration method. Experiments using templates and their artificially distorted images with random noise as input images demonstrate that the proposed method is far superior to the former GPT correlation method. Moreover,k-NN classification of handwritten numerals by the proposed method shows a high recognition accuracy through its distortion-tolerant template matching ability.