|
|
|
| A robust method to extract features from palm image |
| DU Le-Qiang1,2, CHEN Wen-Zhi1, NIE Dui1, ZHANG San-yuan1 |
|
|
|
Abstract A robust method was proposed to extract palmprint features from low resolution color images. Firstly, mean shift algorithm is used to cluster color blocks; secondly, Ostu binarization method is used for segmentation; thirdly, the feature points are extracted with KLT corner detector, to which an orientation is assigned according to the most fast varying gradient direction. The keypoint descriptor can be constructed relative to this orientation so that it’s invariant to image rotation. The location, orientation and rotation invariant local descriptors of keypoints make up of the features of a palm image. In recognition, testing palm features are matched to the template features for initial correspondences, then random sample consensus (RANSAC) is used to confirm the final matching. Plenty of experiments showed that palmprints could be recognized with high accuracy. The method has no limitation to palm rotation, very loose limitation to palm distance and pose, which further proves its robusticity.
|
|
Published: 28 September 2009
|
|
|
鲁棒的掌纹图像特征提取方法
提出了一种基于低分辨率彩色图像的鲁棒的掌纹图像特征提取方法.采用均值平移算法对彩色图像帧中像素进行聚类,应用Ostu二值化方法分割出手掌,并提取出有效掌纹区域.采用KLT角点检测算法提取出有效掌纹区域内的特征点,给每个特征点赋予方向,并根据局部区域特征构造方向不变的特征向量,所有特征点及其特征向量的集合构成了掌纹图像特征.在识别时只须在两个特征点集之间查找匹配对应,并通过随机采样一致性检验最大一致集中内点个数是否大于自适应域值来确定两个手掌是否匹配.利用该算法对网络摄像头采集的手掌样本进行了实验测试,获得了较高的识别精度与性能.该算法对手掌的距离、方向、姿势没有特殊要求,是一种鲁棒高效的掌纹图像特征提取方法.
|
|
| [1] YAMATO K, HARA Y. Fingerprint identification system by ravine thinning [J]. The Transactions of the IEICE, 1988, J71-D(2): 329-335.
[2] SHU W, ZHANG D. Automated personal identification by palmprint [J]. Optical Engineering, 1998, 37(8): 2359-2362.
[3] ZHANG D, KONG W K, YOU J, et al. Online palmprint identification [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(9): 1041-1050.
[4] NOH J S, RHEE K H. Palmprint identification algorithm using Hu invariant moments and Otsu binarization [C]∥ Proceedings of the Fourth Annual ACIS International Conference on Computer and Information Science. Washington DC: IEEE, 2005: 94-99.
[5] ITO K, AOKI T, NAKAJIMA H, et al. A palmprint recognition algorithm using phase-based image matching [C]∥ 2006 IEEE International Conference on Image Processing. Atlanta: IEEE, 2006: 2669-2672.
[6] LI W X, ZHANG D, XU Z Q. Palmprint recognition based on Fourier transform [J]. Journal of Software, 2002，5(13): 879-886.
[7] ZOU W M, ZHANG D, WANG K Q. Bidirectional PCA with assembled matrix distance metric for image recognition [J]. IEEE Transactions on Systems, Man and Cybernetics, Part B, 2006, 36(4): 863-872.
[8] LU Y H, JIANG L K, KONG J, et al. An adaptive and robust hand-based personal identification [C]∥ IEEE Mediterranean Electrotechnical Conference. Benalmádena: IEEE, 2006: 494-497.
[9] OTSU N. A threshold selection method from gray-level histograms [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66.
[10] SHI J, TOMASI C. Good features to track [C]∥ IEEE Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 1994: 593-600.
[11] CHENG Y. Mean shift, mode seeking, and clustering [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8): 790-799.
[12] FUKUNAGA K, HOSTETLER L D. The estimation of the gradient of a density function, with applications in pattern recognition [J]. IEEE Transactions on Information Theory， 1975, 21(1): 32-40.
[13] COMANICIU D, MEER P. Mean shift: a robust approach [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603-619.
[14] 李文新,夏胜雄,张大鹏,等. 基于主线特征的双向匹配的掌纹识别新方法[J]. 计算机研究与发展, 2004, 41(6): 996-1002.
LI Wen-xing, XIA Sheng-xun, ZHANG Da-peng, et al. A new palmprint identification method using bi-directional matching based on major line features [J]. Journal of Computer Research and Development, 2004, 41(6): 996-1002.
[15] TOMASI C, KANADE T. Detection and tracking of point features [R]. Pittsburgh: Carnegie Mellon University, 1991.
[16] LOWE G D. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[17] FISCHLER A M, BOLLES R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography [J]. Communications of ACM, 1981, 24(6): 381-389.
[18] LOWE G D. Local feature view clustering for 3D object recognition [C]∥ Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Kauai: IEEE, 2001: 682-688. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
