Semi-automatic Eyebrow Segmentation Based on Watershed and K-means Algorithm
-
摘要: 为了从原始图像中快速、稳定地提取纯眉毛图像,提出了一种融合分水岭和K-均值算法的眉毛图像分割方法,即W-K算法.首先通过手工在眉毛图像上画上几条线标注部分眉毛点和非眉毛点,其次利用分水岭算法产生蓄水盆,再使用K-均值算法对蓄水盆进行聚类,最后通过眉毛点筛选实现纯眉毛图像的分割.实验结果表明,该方法在分割纯眉毛图像的过程中具有速度快、效果好的优点,可用于眉毛识别的前期预处理,并有助于提高识别结果的准确率.Abstract: To extract a pure eyebrow image from an original image rapidly and steadily,an eyebrow segmentation method based on watershed and K-means algorithm was presented,which was called W-K algorithm.First,a number of eyebrow pixels and non-eyebrow pixels by manually scratching several simple lines on an original eyebrow image were labeled;Second,the watershed algorithm was used to produce catchment basins,and them were clustered by K-means algorithm;Finally,a pure eyebrow image was extracted by eyebrow pixel filtering.Experiment results show that it can segment pure eyebrow images in high speed and good performance for preprocessing to improve eyebrow recognition accuracy.
-
Keywords:
- eyebrow /
- image segmentation /
- watershed algorithm /
- K-means clustering
-
-
[1] LI Yu-jian,FU Cui-hua.Eyebrow recognition:a newbiometric technique[C]∥Proceedings of the NinthIASTED International Conference on Signal and ImageProcessing.Honolulu:ACTA Press Anaheim,2007:506-510.
[2] CHEN Ying-nong,HAN Chin-chuan,WANG Cheng-tzu,et al.Face recognition using nearest feature spaceembedding[J].IEEE Transactions on Pattern Analysis andMachine Intelligence,2011,33(6):1073-1086.
[3] 李玉鑑,付翠花.一种基于特征串比较的眉毛识别方法[J].北京工业大学学报,2008,34(1):103-108.LI Yu-jian,FU Cui-hua.Eyebrow recognition bycomparison of feature strings[J].Journal of BeijingUniversity of Technology,2008,34(1):103-108.(inChinese) [4] 黄琰,李玉鑑,曹俊彬.基于HMM和神经网络的眉毛识别方法[J].计算机科学,2009,36(4A):36-38.HUANG Yan,LI Yu-jian,CAO Jun-bin.Eyebrowrecognition based on hidden Markov models and neuralNetwork[J].Computer Science,2009,36(4A):36-38.(in Chinese) [5] 张晨光,李玉鑑.基于半监督学习的眉毛图像分割算法[J].计算机工程与应用,2009,45(21):139-141.ZHANG Chen-guang,LI Yu-jian.Eyebrow imagesegmentation based on semi-supervised learning[J].Computer Engineering and Applications,2009,45(21):139-141.(in Chinese) [6] LUC Vincent,PIEERE Soille.Watersheds in digitalspaces:an efficient algorithm based on immersionsimulations[J].IEEE Transactions on Pattern Analysisand Machine Intelligence,1991,13(6):583-598.
[7] 查宇飞,牛江龙,毕笃彦.基于多分辨率的分水岭图像分割算法[J].计算机工程,2006,32(19):202-204,207.ZHA Yu-fei,NIU Jiang-long,BI Du-yan.Algorithm ofwatershed image segmentation based on multiresolution[J].Computer Engineering,2006,32(19):202-204,207.(in Chinese) [8] 袁方,孟增辉,于戈.对k-means聚类算法的改进[J].计算机工程与应用,2004,36:177-178.YUAN Fang,MENG Zeng-hui,YU Ge.Improved k-meansclustering algorithm[J].Computer Engineering andApplications,2004,36:177-178.(in Chinese)
计量
- 文章访问数: 10
- HTML全文浏览量: 1
- PDF下载量: 6
下载:
