Recognizing buses and other public transport vehicles can be a difficult task, especially in crowded and noisy environments. The primary objective of this research is to develop a robust and efficient system that can accurately detect bus routes and assist people in navigating public transportation. Our proposed system integrates a convolutional neural network-based deep learning model with optical character recognition technologies to detect bus routes efficiently in real-world scenarios. We employed YOLOv5 for object detection, which provides enhanced efficiency and accuracy in identifying buses and their routes. Additionally, we used PaddleOCR for precise character recognition to extract textual information from images, such as route numbers and destination names. By combining YOLOv5 and PaddleOCR, we have created a system that significantly improves the detection and recognition of bus routes compared to other competitive models. Our results demonstrate that the integrated approach not only enhances detection accuracy but also proves the efficacy of our model in practical applications. This research contributes to the development of intelligent transportation systems, making public transit more accessible and user-friendly for everyone.