A multiscale directional operator and morphological tools for reconnecting broken ridges in fingerprint images
- 作者：M.A. Oliveira ; N.J. Leite
- 关键词：Fingerprints ; Multiscale directional information ; Mathematical morphology ; Image enhancement
- 刊名：Pattern Recognition
- 出版年：2008
- 期刊代码：100_00313203
- 类别：cp
- 出版时间：January 2008
- 卷：41
- 期：1
- 页码：367-377
- 文件大小：1594 K
摘要
In this paper, we introduce a multiscale operator which, together with some morphological tools, can be used to reconnect broken components of fingerprint images. This operator, which can be applied to both binary and gray-scale pictures, extracts the orientation field of an image by taking into account information parameters of sets of pixels in a given neighborhood and located in different directions. It has proved to be very robust to noise and outperforms the gradient- and directional mask-based methods, generally used for orientation field definition. Although we illustrate its application in the fingerprint domain, the approach described here can be easily extended to images whose components exhibit well-defined directional information.