Pruning the Seg-Edge Bilateral Constraint Fully Convolutional Network for Iris Segmentation | |
Hui Zhang1![]() ![]() ![]() | |
2021-09-30 | |
会议名称 | International Conference on Image and Graphics |
会议日期 | December 26 – 28, 2021 |
会议地点 | Haikou, China |
摘要 | Iris semantic segmentation in less-constrained scenarios is the basis of new generation of iris recognition technology. In this paper, we reexamined our approach iris segmentation framework, named Seg-Edge bilateral constraint network (SEN), which contains an edge map generating network which passes detailed edge information from low level convolutional layers to iris semantic segmentation analysis layers and segmentation-edge bilateral constraint structure for focusing on interesting objects. To reduce the number of network parameters, we propose pruning filters and corresponding feature maps that are identified as useless by 𝑙1-norm and 𝑙2-norm, which results in a lightweight iris segmentation network while keeping the performance almost intact or even better. A novel 𝑙1-norm or [𝑙1-norm, 𝑙2-norm] clustering based pruning method is proposed to improve pruning effect and avoid the time consuming manual design. Experimental results suggest that the proposed SEN structure outperforms the state-of-the-art iris segmentation methods, and the clustering based pruning methods outperform manual design in both compression ratio and accuracy. |
七大方向——子方向分类 | 生物特征识别 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57456 |
专题 | 模式识别实验室 |
通讯作者 | Zhaofeng He |
作者单位 | 1.Beijing IrisKing Co., Ltd., Beijing, China 2.Institute of Automation Chinese Academy of Sciences, Beijing, China 3.Beijing University of Posts and Telecommunications, Beijing, China |
推荐引用方式 GB/T 7714 | Hui Zhang,Junxing Hu,Jing Liu,et al. Pruning the Seg-Edge Bilateral Constraint Fully Convolutional Network for Iris Segmentation[C],2021. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
7-4-ICIG.pdf(962KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论