多源异质虹膜图像识别方法研究

本项目面向国家公共安全需求和虹膜识别学科发展前沿，把握视觉传感网和智能手机等泛在成像平台为虹膜图像获取与识别提供的新机遇，从基础数据、图像重建、特征分析、距离度量、信息融合等多个层次研究多源异质虹膜图像识别的理论和方法，通过图像处理和模式识别的方法消除成像器件、成像光源、成像距离、成像场景等因素对多源异质虹膜图像数据的外在影响，探寻隐藏在复杂多变虹膜图像数据中稳定不变的身份关联信息，突破面向视频监控和移动互联网成像平台鲁棒识别中远距离、可见光谱、低分辨率虹膜图像的关键技术，建设跨设备和跨场景的虹膜识别验证系统，实现从受控受限到无处不在虹膜识别的重大技术跨越，推动我国智能安防产业的自主创新和科技进步，满足我国关键领域对高精度身份识别技术的迫切需求。

The Visual Internet of Things and Mobile Internet provide ubiquitous sensors and processors for acquisition and recognition of iris images. However, it is a grand challenge to match heterogeneous iris images captured by iris devices, CCTV cameras, and mobile phones. The theory and method for robust recognition of heterogeneous iris images are studied in this project. The main research tasks include constructing heterogeneous iris image database, development of novel super-resolution, feature analysis, metric learning and information fusion methods for heterogeneous iris images. The objective of our research is to achieve robust heterogeneous iris matching against the variations of sensors, illuminators, imaging distance and imaging conditions based on image processing and pattern recognition methods. This project will improve the application range of iris recognition, facilitate progress of science and technology in Chinese intelligent security industry and meet the requirements of reliable personal identification technology in China.