Automatic face detection system for street view images

Author

Xin Yang ; Xingang Wang

Author_Institution

Res. Center of Precision Sensing & Control, Inst. of Autom., Beijing, China

fYear

2012

fDate

11-14 Dec. 2012

Firstpage

2260

Lastpage

2263

Abstract

As street view images have been widely used in digital maps, detecting and blurring faces in these images for privacy protection is highly needed. In this paper, an automatic face detection system for street view images is constructed. Firstly, image pre-processing is used to increase image´s global contrast. Then, head-shoulder detection based on combined-HOG features is applied to locate faces roughly. After that, multi-angle face detection and Bayes face detection based on skin segmentation are used to get faces´ locations precisely from the located head-shoulder regions. Experiments conducted show high precision and robustness of the system.

Keywords

Bayes methods; data privacy; face recognition; feature extraction; image segmentation; object detection; skin; Bayes face detection; automatic face detection system; combined-HOG feature; digital map; face blurring; face location; head-shoulder detection; head-shoulder region location; image global contrast; image preprocessing; multiangle face detection; privacy protection; skin segmentation; street view image;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Biomimetics (ROBIO), 2012 IEEE International Conference on

Conference_Location

Guangzhou

Print_ISBN

978-1-4673-2125-9

Type

conf

DOI

10.1109/ROBIO.2012.6491305

Filename

6491305