Recognition of Traffic Sign Using Support Vector Machine and Fuzzy Cluster

Author(s):

Muthukumaresan.T , Christian College of Engineering & Technology Oddanchatram, Dindigul, Tamilnadu-624619, India; Kirubakaran.B, Christian College of Engineering & Technology Oddanchatram, Dindigul, Tamilnadu-624619, India; Kumaresan.D, Christian College of Engineering & Technology Oddanchatram, Dindigul, Tamilnadu-624619, India; Akhil Satheesan, Christian College of Engineering & Technology Oddanchatram, Dindigul, Tamilnadu-624619, India; Jaya Prakash.A, Christian College of Engineering & Technology Oddanchatram, Dindigul, Tamilnadu-624619, India

Keywords:

BHOG, MSER, SVM, FEZZY

Abstract:

Traffic sign recognition plays an important role in driver assistant systems and intelligent autonomous vehicles. Its real-time performance is highly desirable in addition to its recognition performance. This system aims to deal with real-time traffic sign recognition, i.e., localizing what type of traffic sign appears in which area of an input image at a fast processing time. Our detection module is based on traffic sign proposal extraction and classification built upon a color probability model and color HOG(Histogram of Orientated Gradients). HOG technique performs conversion of original image into gray color then applies red or blue color for foreground. Maximally Stable External Region (MSER) take stable object in the previous output by the use of multiple frames. Next Support Vector Machine(SVM) fetch the object from MSER output and compares with database. At the same time fuzzy pattern cluster technique fetch the MSER output and apply the RGB(RED,GREEN,BLUE) colors then compares with the database images. In the above two methods, the one which produce the output first is considered. Then voice output narrating the traffic sign is produced.

Other Details:

Manuscript Id	:	IJSTEV2I10051
Published in	:	Volume : 2, Issue : 10
Publication Date	:	01/05/2016
Page(s)	:	190-197

Download Article