The objective of this paper is to design Convolutional Neural Network (CNN) Classifier using Keras API with
Tensorflow as backend to identify traffic or road signs with high accuracy and low loss. The code is written in Python
programming language. Deep Learning domain based CNN, in recent years, have made extraordinary progress in the field of
image classification and object identification. The network is trained, validated and tested using German Traffic Sign Detection
Benchmark dataset which comprises of 43 categories of signs and around 52,000 distinct traffic sign color images.
Implementation of this network into an accessory device assumes a significant place inside the automobiles which can ensure
safety to driver’s life and is considered as a very useful feature for self-driving automobiles. Artificial Intelligence is advancing
and progressing rapidly in such a way that this technology has turned out to be a game changer in almost all sectors like
Automobile, Medical, Social media, Analytics.
