Image Classification using CNN for Traffic Signs in Pakistan

TL;DR

This paper explores training CNN-based image classification models for traffic signs in Pakistan, emphasizing environment-specific data and dataset expansion to improve accuracy in underdeveloped country settings.

Contribution

It introduces a CNN approach fine-tuned on Pakistan's traffic sign dataset, highlighting environment-specific training and dataset augmentation for better accuracy.

Findings

Pre-trained German traffic sign data improved model accuracy.

Dataset expansion increased classification precision.

Fine-tuning on local data enhanced model performance.

Abstract

The autonomous automotive industry is one of the largest and most conventional projects worldwide, with many technology companies effectively designing and orienting their products towards automobile safety and accuracy. These products are performing very well over the roads in developed countries. But can fail in the first minute in an underdeveloped country because there is much difference between a developed country environment and an underdeveloped country environment. The following study proposed to train these Artificial intelligence models in environment space in an underdeveloped country like Pakistan. The proposed approach on image classification uses convolutional neural networks for image classification for the model. For model pre-training German traffic signs data set was selected then fine-tuned on Pakistan's dataset. The experimental setup showed the best results and accuracy from the previously conducted experiments. In this work to increase the accuracy, more dataset was collected to increase the size of images in every class in the data set. In the future, a low number of classes are required to be further increased where more images for traffic signs are required to be collected to get more accuracy on the training of the model over traffic signs of Pakistan's most used and popular roads motorway and national highway, whose traffic signs color, size, and shapes are different from common traffic signs.