TRAFFIC SIGN DETECTION USING DEEP LEARNING

Convolutional Neural Networks mostly use deep learning algorithms to detect and identify traffic signs till now but they are lacking in so many ways. This paper will give a really effective method for traffic sign detection and identification using convolutional neural networks. Convolutional Neural Networks are used for road sign detection and classification as it takes an input image and then assigns weights to different aspects in the image and then differentiate them from each other. Other classification algorithms require much longer preprocessing than the ConvNet. The filters which are there in primitive methods are engineered manually with training. These filters are learned by the ConvNets. Neurons respond to stimuli in the receptive field only, which is a restricted region of the visual field. The temporal and spatial dependencies of an image can be successfully captured by applying the relevant filters. To understand the sophistication of an image in a better way, the network can be trained. After reducing the parameters and weights reusability, the architecture fits better with the image dataset. The architecture of the system is designed in such a way that it extracts important features from the traffic sign's images and classifies them under various categories. Keywords— Dataset, Road Sign, ConvNet, Deep learning.