欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
掌纹图像预处理主要包括图像分割和图像增强。在分析现有掌纹图像预处理方法中存在的不足之后，提出了一种新的掌纹图像预处理方法。该方法以手掌外侧轮廓作为定位参考线，首先实现手掌定位；然后以手掌的最大内切圆圆心为掌纹图像坐标系的原点构建坐标系，并截取出该圆的内接正方形区域内的掌纹图像，以完成图像分割。另外，该方法将模糊理论引入到反锐化掩模系统框架中，并用方向可调滤波器替代传统反锐化掩模算法中的Laplacian滤波器来获取掌纹图像中的高频成分，以实现在线掌纹图像的增强。实验结果表明，该方法不仅在手指完全并拢的情况下，仍然能提取出掌纹中心子图，而且能有效增强掌纹图像中主线和皱纹线的对比度。
英文摘要：
The preprocessing of palmprint includes the palmprint segmentation and the palmprint image enhancement. According to the shortcomings of the existing preprocessing methods, in this paper, we propose a new preprocessing method of palmprint. The method uses the outside boundary of a palm as the reference line to align a palmprint. It also includes the usage of the center of the largest inscribed circle as the origin of the coordination system of palmprint and extracts the center part of the palmprint, which complete the palmprint segmentation. In addition, to enhance the contrast of palm images, this method introduces the fuzzy set theory into the unsharp masking scheme and replaces a Laplacian filter with steerable filters to extract the high frequency components. The experiment results demonstrate the method can not only extract the center part of palmprint, even under the circumstance of adducting the all of fingers, but also enhance the contrast of principle lines and wrinkles synchronously.
同期刊论文项目
同项目期刊论文
A Novel Coupled Bi-directional Diffused Image Inpainting Model with Morphological Invariant Property
期刊信息
位置：