Road-sign segmentation and recognition in natural scenes

Author

Siyan, Yang ; Xiaoying, Wu ; Qiguang, Miao

Author_Institution

Shaanxi Radio & TV Univ., Xi´´an, China

fYear

2011

fDate

14-16 Sept. 2011

Firstpage

1

Lastpage

4

Abstract

The detection and recognition of road-sign is an important part of achieving intelligent vehicle. In the system, we use the HSI space to detect the road-sign which has been proposed. After detection, we use a method which we proposed for segmentation to get all road-signs in the image. Then we use the ratio of the size of road-sign and the size of the rectangle which is minimal and contain the road-sign to define the shape of the road-sign. Finally, in order to achieve real-time, we abstract hu moment of road-sign and use SVM for recognition in our system. Hundreds of images have been tested, and the system show high ratio of recognition and process rapidly.

Keywords

image colour analysis; image recognition; image segmentation; road traffic; support vector machines; HSI space; SVM method; intelligent vehicle; road-sign image detection; road-sign image recognition; road-sign image segmentation; Educational institutions; Image color analysis; Image segmentation; Intelligent vehicles; Roads; Shape; Support vector machines; HSI space; detect shape; hu moment; svm;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, Communications and Computing (ICSPCC), 2011 IEEE International Conference on

Conference_Location

Xi´an

Print_ISBN

978-1-4577-0893-0

Type

conf

DOI

10.1109/ICSPCC.2011.6061777

Filename

6061777