• ADARI KUMAR NAIDU
• K.ARUN BABU
• K.JAHNAVI
• S.SIVARAM
• K.SONY NAVYA

Convolutional neural networks are currently the most popular deep learning methods for traffic signal classification[1], but because to the inherent limitations of the max pooling layer, they are unable to capture the position, view, and orientation of the images. The deep learning architecture known as capsule networks is used in this paper to provide a novel strategy for the detection of traffic signs that achieves exceptional performance on the German traffic sign dataset. A capsule network is made up of capsules, which are collections of neurons that use the dynamic routing and route by agreement algorithms to describe an object's position and orientation[2]. Our method reduces the manual labour and offers resistance to the spatial variations, in contrast to the earlier approaches of manual feature extraction and numerous deep neural networks with various parameters.

CNN, Capsule Neural Networks, Pose, Traffic sign, Dataset, GTSRB

"Traffic Sign Detection Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 3, page no.c760-c765, March-2023, Available :http://www.jetir.org/papers/JETIR2303287.pdf

"Traffic Sign Detection Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 3, page no. ppc760-c765, March-2023, Available at : http://www.jetir.org/papers/JETIR2303287.pdf