A novel unsharp mask sharpening method in preprocessing for face recognition

摘要：

　　Face recognition is widely used in public security field.Surveillance video is a major source of probe faces for suspects search.For economic reasons,most social monitors are equipped with analog cameras.When Signals are displayed on PC,interlaced effect will appear.However,after the application of existing methods of de-interlacing,images would lose definition and identification rate would reduce.We proposed a novel sharpening method based on unsharp mask for preprocessing in face recognition..In this paper,we compared different methods of image sharpening.Then we showed the algorithm implementation under the framework of DirectShow.Proposed method makes significant improvement in image clarity and algorithm complexity.

关键词： Unsharp mask Analog surveillance video Face recognition DirectShow

作者: Xie Lanchi Guo Jingjing Li Zhihui

作者单位: Institute of Forensic Science Ministry of Public Security Beijing, China

会议类型: 国际会议

会议名称: 2015 Fifth International Conference on Instrumentation and Measurement,Computer,Communication and Control (IMCCC2015)(第五届仪器测量、计算机通信与控制国际会议)

会议地点: 秦皇岛

会议语种:英文

页码: 378-381

在线出版日期: 2015-09-18（万方平台首次上网日期，不代表论文的发表时间）