区域注意力机制引导的双路虹膜补全  

Region attention mechanism based dual human iris completion technology

作　　者：张志礼 张慧 王甲 夏玉峰 刘亮[1] 李佩佩 何召锋 Zhang Zhili;Zhang Hui;Wang Jia;Xia Yufeng;Liu Liang;Li Peipei;He Zhaofeng(Beijing University of Posts and Telecommunications,Beijing 100876,China;Beijing IrisKing Tech Co.,Ltd.,Beijing 100084,China)

机构地区：[1]北京邮电大学,北京100876 [2]北京中科虹霸科技有限公司,北京100084

出　　处：《中国图象图形学报》2022年第5期1669-1681,共13页Journal of Image and Graphics

基　　金：国家自然科学基金项目(62176025,62076232,62006227)。

摘　　要：目的虹膜识别是一种稳定可靠的生物识别技术,但虹膜图像的采集过程会受到多种干扰造成图像中虹膜被遮挡,比如光斑遮挡、上下眼皮遮挡等。这些遮挡的存在,一方面会导致虹膜信息缺失,直接影响虹膜识别的准确性,另一方面会影响预处理(如定位、分割)的准确性,间接影响虹膜识别的准确性。为解决上述问题,本文提出区域注意力机制引导的双路虹膜补全网络,通过遮挡区域的像素补齐,可以显著减少被遮挡区域对虹膜图像预处理和识别的影响,进而提升识别性能。方法使用基于Transformer的编码器和基于卷积神经网络(convolutional neural network,CNN)的编码器提取虹膜特征,通过融合模块将两种不同编码器提取的特征进行交互结合,并利用区域注意力机制分别处理低层和高层特征,最后利用解码器对处理后的特征进行上采样,恢复遮挡区域,生成完整图像。结果在CASIA(Institute of Automation,Chinese Academy of Sciences)虹膜数据集上对本文方法进行测试。在虹膜识别性能方面,本文方法在固定遮挡大小为64×64像素的情况下,遮挡补全结果的TAR(true accept rate)(0.1%FAR(false accept rate))为63%,而带有遮挡的图像仅为19.2%,提高了43.8%。结论本文所提出的区域注意力机制引导的双路虹膜补全网络,有效结合Transformer的全局建模能力和CNN的局部建模能力,并使用针对遮挡的区域注意力机制,实现了虹膜遮挡区域补全,进一步提高了虹膜识别的性能。ObjectiveHuman iris image recognition has achieved qualified accuracy based on most recognized databases.But,the real captured iris images are presented low-quality occlusion derived from the light spot,upper and lower eyelid,leading to the quality lossin iris recognition and segmentation.Recent development of deep learning has promoted the great progress image completion method.However,since most convolutional neural networks(CNNs)are difficult to capture global cues,iris image completion remains a challenging task in the context of the large corrupted regions and complex texture and structural patterns.Most CNNs are targeted on local features extraction with unqualified captured global cues in practice.Current transformer architecture has been introduced to visual tasks.The visual transformer harnesses complex spatial transforms and long-distance feature dependencies for global representations in terms of self-attention mechanism and multi-layer perceptron(MLP)structure.Visual transformers have their challenges to identify ignored local feature details in related to the discriminability decreases between background and foreground.The CNN-based convolution operations targets on local features extraction with unqualified captured global representations.The visual transformer based cascaded selfattention modules can capture long-distance feature dependencies with local feature loss details.We illustrate a region attention mechanism based dual iris completion network,which uses the bilateral guided aggregation layer to fuse convolutional local features with transformer-based global representations within interoperable scenario.To improve recognition capability,the impact of the occluded region on iris image pre-processing and recognition can be significantly reduced based on the missing iris information completion.MethodA region attention mechanism based dual iris completion network contains a Transformer encoder and a CNN encoder.Specifically,we use the Transformer encoder and the CNN encoder to extract the global

关 键 词：虹膜补全 虹膜识别 虹膜分割 TRANSFORMER 卷积神经网络(CNN) 注意力 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]