一种鲁棒的基于对抗结构的生物特征ROI提取方法  

A Robust ROI Extraction Method for Biometrics Using Adversarial Structure

作　　者：刘凤 刘浩哲 张文天 陈嘉树 沈琳琳[1,2,3] 王磊 LIU Feng;LIU Hao-Zhe;ZHANG Wen-Tian;CHEN Jia-Shu;SHEN Lin-Lin;WANG Lei(College of Computer Science and Software Engineering,Shenzhen University(SZU),Shenzhen 518060;Branch of Shenzhen University,Shenzhen Institute of Artificial Intelligence and Robotics for Society,Shenzhen 518060;Branch of Shenzhen University,Guangdong Key Laboratory of Intelligent Information Processing,Shenzhen 518060;School of Electronic Information and Artificial Intelligence,Shaanxi University of Science and Technology,Xi'an 710021;Shenzhen Institutes of Advanced Technology,Chinese Academic of Sciences,Shenzhen 518055)

机构地区：[1]深圳大学计算机与软件学院,深圳518060 [2]深圳市人工智能与机器人研究院深圳大学分部,深圳518060 [3]广东省智能信息处理重点实验室深圳大学分部,深圳518060 [4]陕西科技大学电子信息与人工智能学院,西安710021 [5]中国科学院深圳先进技术研究院,深圳518055

出　　处：《自动化学报》2023年第6期1339-1353,共15页Acta Automatica Sinica

基　　金：国家自然科学基金(62076163,91959108,61672357);深圳市基础研究基金(JCYJ20190808163401646,JCYJ20180305125822769);腾讯“犀牛鸟”深圳大学青年教师科学研究基金资助。

摘　　要：感兴趣区域(Region of interest,ROI)提取在生物特征识别中,常用于减少后续处理的计算消耗,提高识别模型的准确性,是生物识别系统中预处理的关键步骤.针对生物识别数据,提出了一种鲁棒的ROI提取方法.方法使用语义分割模型作为基础,通过增加全局感知模块,与分割模型形成对抗结构,为模型提供先验知识,补充全局视觉模式信息,解决了语义分割模型的末端收敛困难问题,提高了模型的鲁棒性和泛化能力.在传统二维(2D)指纹、人脸、三维(3D)指纹和指纹汗孔数据集中验证了方法的有效性.实验结果表明,相比于现有方法,所提出的ROI提取方法更具鲁棒性和泛化能力,精度最高.Region of interest(ROI)extraction is an initial and key step in biometrics since it can not only facilitate more accurate feature extraction but also can reduce the computational cost.This paper proposes a more robust ROI extraction method for biometric image.The method uses semantic segmentation network as the basis.By adding the global perceptual loss module(i.e.,adversarial structure)into the loss function of the learning model,prior knowledge is provided to try to make the model know the global pattern information.Furthermore,global perceptual loss module solves the problem of terminal convergence and improve the robustness of the ROI extraction.The effectiveness of the proposed method is validated on the 2D fingerprint,face,3D fingerprint and sweat pore datasets,respectively.Comparisons with other ROI extraction methods also shows the outstanding performance of the proposed method.

关 键 词：感兴趣区域提取 语义分割 对抗结构 生物特征 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]