一种改进蚁群算法的睫毛提取

睫毛检测是虹膜识别预处理阶段的一个重要环节，本文提出一种基于改进蚁群算法的睫毛提取方法。该方法首先通过引入睫毛区域内、外方向因子使得人工蚂蚁能快速聚集到睫毛边缘，并且通过采取全局和局部两种策略来对信息素进行更新，然后使用 OTSU算法根据所得图像的信息素浓度把图像分割成睫毛边缘和非睫毛边缘两部分。最后，对分割出的睫毛边缘进行整合、除噪，得到最终的睫毛。实验结果表明：该方法提取睫毛的效果较其他相关算法有明显的提高；并且当人工蚂蚁间距取约 25 pixels的时候，算法既能保证睫毛检测的速度又能保证睫毛检测的效果。

Abstract

Eyelash detection is an important step during the period of iris recognition preprocessing. An eyelash extraction algorithm based on improved ant colony algorithm is proposed. Firstly, by introducing direction factor of inside the eyelash region and outside the eyelash region, the artificial ant can gather to the eyelash-edge quickly, increasing pheromone intensity of eyelash-edge and decreasing that of non-eyelash-edge. At the same time, global and local strategies are taken respectively to update pheromone. After that, the OTSU algorithm is used to segment eyelash edge according to the pheromone intensity of image. Finally, by integrating the eyelash-edge and deleting the noise, the eyelash can be obtained. Experimental results show that, compared with other concerned algorithms, the effect of the proposed method is better than that of others, and when the distance between artificial ants is about 25 pixels, the algorithm can not only ensure eyelash detection speed but guarantee the detection effect.

参考文献

[1] WANIKIN K，DAVID Z. Detecting eyelash and reflection for accurate iris segmentation [J]. International Journal of Pattern Recognition and Artificial Intelligence(S0218-0014)，2003，17(6)：1025-1034.

[2] HUANG J Z，WANG Y H，TAN T N，et al. A new iris segmentation method for recognition [C]// Proceedings of the 17th International Conference on Pattern Recognition. Cambridge，UK，Aug 26，2004，8：554-557.

[3] ALI S A，LOAY D，GEROGE E. Iris Recognition System Based on Texture Features [J]. International Journal of Network Security(S1816-353X)，2014，6：1-11.

[4] AYDI W，KAMOUN L，MASMOUDI N. A Fast and Accurate Eyelids and Eyelashes Detection Approach for Iris Segmentation [J]. Journal of Multimedia Processing and Technologies(S0976-4127)，2012，3(4)：166-173.

[5] 苑玮琦，徐露，林忠华 . 一种新的虹膜图像预处理方法 [J].光电子 ·激光，2009，20(2)：234-239. YUAN Weiqi，XU Lu，LING Zhonghua. A novel method of iris image preprocessing [J]. Journal of Optoelectronics. Laster， 2009，20(2)：234-239.

[6] 来毅，路陈红，卢朝阳 . 用于虹膜识别的眼睑及眼睫毛遮挡检测 [J].计算机辅助设计与图形学报， 2007，19(3)：346-350.

LAI Yi，LU Chenhong，LU Zhaoyang. Eyelid and eyelash occlusions detection for iris recognition [J]. Journal of Computer-Aided Design & Computer Graphics，2007，19(3)：346-350.

[7] 贾永红. 数字图像处理 [M].武汉：武汉大学出版社， 2009：146-149. JIA Yonghong. Digital Image Processing [M]. Wuhan：Wuhan University Press，2009：146-149.

[8] COLORNI A，DORIGO M，MANIEZZO V，et al. Distributed optimization by ant colonies [C]// Proceedings of ECAL91 (European Conference on Artificial Life)，Paris，France，1991：134-142.

[9] 许川佩，蔡震，胡聪. 基于蚁群算法的数字微流控生物芯片在线测试路径优化 [J].仪器仪表学报， 2014，35(6)：1417-1424. XU Chuanpei，CAI Zhen，HU Chong. On-line test path optimization for digital microfluidic biochips based on ant colony algorithm [J]. Chinese Journal of Scientific Instrument，2014，35(6)：1417-1424.

[10] 王家林，吴正国，杨宣访 . 基于蚁群神经网络的线性直流电源故障诊断 [J].仪器仪表学报， 2009，30(3)：515-520. WANG Jialin，WU Zhengguo，YANG Xuanfang. Fault diagnosis of linear DC electric source based on ant colony algorithm and neural network [J]. Chinese Journal of Scientific Instrument，2009，30(3)：515-520.

[11] SUSMITA G，MEGHA K，ANINDYA H，et al. Use of aggregation pheromone density for image segmentation [J]. Pattern Recognition Letters(S0167-8655)，2009，30(3)：939-949.

[12] RAL P，DUTTA M. Image edge detection using modified ant colony optimization algorithm based on weighted heuristics [J]. International Journal of Computer Application(S0975-8887)，2013，68(5)：5-9.

[13] PANIGRAHY M P，AHMED S. Image edge detection based on ACO technique [J]. International Journal of Computer Science and Telecommunications(S2047-3338)，2013，4(1)：42-46.

[14] ZHANG Jian，ZHOU Jiliu，HE Kun，et al. Image edge detection using quantum ant colony optimization [J]. International Journal of Digital Content Technology and its Application(JDCTA)(S1975-9339)，2012，6(11)：187-195.

[15] TYAGI Y，PUNTAMBEKAR T A，SEXENA P，et al. A hybrid approach to edge detection using ant colony optimization and fuzzy logic [J]. Internal Journal of Hybrid Information Technology(S1738-9968)，2012，5(1)：37-46.

[16] YE Z G，MOHAMADIAN H，YE Y M. Quantitative analysis of feature detection using adaptive canny edge detector and enhanced colony optimization [J]. International Journal of Modeling and Optimization(S2010-3679)，2012，2(4)：384-390.

朱立军, 苑玮琦. 一种改进蚁群算法的睫毛提取[J]. 光电工程, 2016, 43(6): 44. ZHU Lijun, YUAN Weiqi. An Eyelash Extraction Method Based on Improved Ant Colony Algorithm[J]. Opto-Electronic Engineering, 2016, 43(6): 44.

一种改进蚁群算法的睫毛提取

关于本站 Cookie 的使用提示

全站搜索

一种改进蚁群算法的睫毛提取

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索