Title :
Hardware centric automatic recognition of road signs
Author :
Hashemi, Ashkan ; Thornberg, Benny
Author_Institution :
Dept. of Inf. Technol. & Media, Mid Sweden Univ., Sundsvall, Sweden
Abstract :
In this paper we present a novel and robust algorithm for automatic recognition of road signs by using histogram of oriented gradient (HOG) as the main feature and minimum distance classifier (MDC) to classify numbers written on speed limit road signs. It also describes how other geometrical properties can be added to feature vector in order to increase the robustness of proposed algorithm.
Keywords :
geometry; image classification; object recognition; traffic engineering computing; HOG; MDC; feature vector; geometrical properties; hardware centric automatic recognition; histogram of oriented gradient; minimum distance classifier; number classification; speed limit road signs; Hardware; Image color analysis; Image recognition; Image segmentation; Roads; Support vector machine classification; Training; Image processing; color space; histogram of oriented gradients; minimum distance classifier;
Conference_Titel :
Computer Applications and Industrial Electronics (ISCAIE), 2012 IEEE Symposium on
Conference_Location :
Kota Kinabalu
Print_ISBN :
978-1-4673-3032-9
DOI :
10.1109/ISCAIE.2012.6482088
