An Investigative Approach towards Various Image Segmentation Algorithms Used for Traffic Sign Recognition
Abhinav V. Deshpande *
School of Electronics Engineering (SENSE), Vellore Institute of Technology (VIT), Vellore, Tamil Nadu, India.
*Author to whom correspondence should be addressed.
Abstract
As far as the safety of a driver is concerned, more focus should be put on correct interpretation and information which is conveyed by a traffic sign, while driving a vehicle along the road. A sign board can be thought of as an emblem which disseminates important and meaningful information regarding the potential hazards prevailing among road users comprising roadways cladded with snowfall, construction worksites or repairing of roads taking place and telling the people to follow an alternative route. It alerts the person who is passing through the road about the maximum possible extremity that his vehicle is trying to achieve indicating slowing down the speed of vehicle since chances of having collision cannot be ruled out. With constant increasing of the training database size, not only the recognition accuracy, but also the computation complexity should be considered in designing a feasible recognition approach. The traffic sign images were acquired from the image database and were subjected to some pre-processing techniques such as applying Histogram of Oriented Gradients algorithm which consists of extraction of the HOG features from an image with the help of cell size as well as around the corner points and contrast stretching of color images that are present in the image database. In the future, we will concentrate on detecting, recognizing as well as classifying a particular sign board.
Keywords: Color, shape, Histogram of Oriented Gradients (HOG), contrast stretching, cell size