Road safety is a critical global concern, with manual enforcement of helmet laws and vehicle safety standards (e.g., rear-view mirror presence) being resource-intensive and inconsistent. This paper presents an AI-powered system to automate traffic violation detection, significantly enhancing enforcement efficiency and road safety. The system leverages YOLOv8 for robust object detection and EasyOCR for license plate recognition. Trained on a custom dataset of annotated images (augmented for diversity), it identifies helmet non-compliance, the absence of rear-view mirrors on motorcycles, an innovative contribution to automated checks, and extracts vehicle registration numbers. A Streamlit-based interface facilitates real-time monitoring and violation logging. Advanced image preprocessing enhances license plate recognition, particularly under challenging conditions. Based on evaluation results, the model achieves an overall precision of 0.9147, a recall of 0.886, and a mean Average Precision (mAP@50) of 0.843. The mAP@50 95 of 0.503 further indicates strong detection capability under stricter IoU thresholds. This work demonstrates a practical and effective solution for automated traffic rule enforcement, with considerations for real-world deployment discussed.

Automatic License Plate Recognition (ALPR) involves extracting vehicle license plate information from image or a video capture. These systems have gained popularity due to the wide availability of low-cost surveillance cameras and advances in Deep Learning. Typically, video-based ALPR systems rely on multiple frames to detect the vehicle and recognize the license plates. Therefore, we propose a system capable of extracting exactly one frame per vehicle and recognizing its license plate characters from this singular image using an Optical Character Recognition (OCR) model. Early experiments show that this methodology is viable.

License plate recognition (LPR) involves automated systems that utilize cameras and computer vision to read vehicle license plates. Such plates collected through LPR can then be compared against databases to identify stolen vehicles, uninsured drivers, crime suspects, and more. The LPR system plays a significant role in saving time for institutions such as the police force. In the past, LPR relied heavily on Optical Character Recognition (OCR), which has been widely explored to recognize characters in images. Usually, collected plate images suffer from various limitations, including noise, blurring, weather conditions, and close characters, making the recognition complex. Existing LPR methods still require significant improvement, especially for distorted images. To fill this gap, we propose utilizing visual language models (VLMs) such as OpenAI GPT4o, Google Gemini 1.5, Google PaliGemma (Pathways Language and Image model + Gemma model), Meta Llama 3.2, Anthropic Claude 3.5 Sonnet, LLaVA, NVIDIA VILA, and moondream2 to recognize such unclear plates with close characters. This paper evaluates the VLM's capability to address the aforementioned problems. Additionally, we introduce ``VehiclePaliGemma'', a fine-tuned Open-sourced PaliGemma VLM designed to recognize plates under challenging conditions. We compared our proposed VehiclePaliGemma with state-of-the-art methods and other VLMs using a dataset of Malaysian license plates collected under complex conditions. The results indicate that VehiclePaliGemma achieved superior performance with an accuracy of 87.6\%. Moreover, it is able to predict the car's plate at a speed of 7 frames per second using A100-80GB GPU. Finally, we explored the multitasking capability of VehiclePaliGemma model to accurately identify plates containing multiple cars of various models and colors, with plates positioned and oriented in different directions.

With the robust development of technology, license plate recognition technology can now be properly applied in various scenarios, such as road monitoring, tracking of stolen vehicles, detection at parking lot entrances and exits, and so on. However, the precondition for these applications to function normally is that the license plate must be 'clear' enough to be recognized by the system with the correct license plate number. If the license plate becomes blurred due to some external factors, then the accuracy of recognition will be greatly reduced. Although there are many road surveillance cameras in Taiwan, the quality of most cameras is not good, often leading to the inability to recognize license plate numbers due to low photo resolution. Therefore, this study focuses on using super-resolution technology to process blurred license plates. This study will mainly fine-tune three super-resolution models: Real-ESRGAN, A-ESRGAN, and StarSRGAN, and compare their effectiveness in enhancing the resolution of license plate photos and enabling accurate license plate recognition. By comparing different super-resolution models, it is hoped to find the most suitable model for this task, providing valuable references for future researchers.

Artificial Intelligence is transforming the business world as a whole with all its applications and potential, with visual-based AI being capable of digital images and videos. Visual-based AI, which refers to computer vision, is an application of AI that is playing a significant role in enabling a digital transformation by enabling machines to detect and recognize not just images and videos, but also the various elements within them, such as people, objects, animals and even sentiments, emotional and other parameters-based capabilities to name a few. Artificial intelligence is now further evolving across various industries and sectors. Transport: Computer vision aids in a better experience for transport, as video analytics combined with Automatic number plate recognition can help in tracking and tracing violators of traffic safety laws (speed limits and lane violation etc.) and stolen or lost cars, as well as in toll management and traffic monitoring and controlling. Aviation: Visual AI can help in providing prompt assistance for elderly passengers and for those requiring assistance (physically challenged, pregnant women etc.); it can also be useful in creating a new "face-as-a-ticket" option for easy and fast boarding for passengers, in tracking down lost baggage around the airport as well as in security surveillance on passengers and suspicious objects (track and trace objects and passengers relevant to it).

Today we are accessible to a mountain of intelligent technologies. And no doubt that computer vision stores a vital space among all of them. When we talk about computer vision, the foremost application that we think of is Image Recognition. But indeed, a computer vision also encompasses OCR (Optical Character Recognition) algorithm, which allows seamless computer operations. In this article, we will discuss the origin, advancements, OCR tasks, and OCR industry applications that are enriching the OCR Pipeline.

Significant number of researches have been developed recently around intelligent system for traffic management, especially, OCR based license plate recognition, as it is considered as a main step for any automatic traffic management system. Good quality data sets are increasingly needed and produced by the research community to improve the performance of those algorithms. Furthermore, a special need of data is noted for countries having special characters on their licence plates, like Morocco, where Arabic Alphabet is used. In this work, we present a labeled open data set of circulation plates taken in Morocco, for different type of vehicles, namely cars, trucks and motorcycles. This data was collected manually and consists of 705 unique and different images. Furthermore this data was labeled for plate segmentation and for matriculation number OCR. Also, As we show in this paper, the data can be enriched using data augmentation techniques to create training sets with few thousands of images for different machine leaning and AI applications. We present and compare a set of models built on this data. Also, we publish this data as an open access data to encourage innovation and applications in the field of OCR and image processing for traffic control and other applications for transportation and heterogeneous vehicle management.

Benefiting from the rapid development of convolutional neural networks, the performance of car license plate detection and recognition has been largely improved. Nonetheless, challenges still exist especially for real-world applications. In this paper, we present an efficient and accurate framework to solve the license plate detection and recognition tasks simultaneously. It is a lightweight and unified deep neural network, that can be optimized end-to-end and work in real-time. Specifically, for unconstrained scenarios, an anchor-free method is adopted to efficiently detect the bounding box and four corners of a license plate, which are used to extract and rectify the target region features. Then, a novel convolutional neural network branch is designed to further extract features of characters without segmentation. Finally, recognition task is treated as sequence labelling problems, which are solved by Connectionist Temporal Classification (CTC) directly. Several public datasets including images collected from different scenarios under various conditions are chosen for evaluation. A large number of experiments indicate that the proposed method significantly outperforms the previous state-of-the-art methods in both speed and precision.

To actually detect and recognize number plates in an input image a network much like the above is applied to 128x64 windows at various positions and scales, as described in the windowing section. The network differs from the one used in training in that the last two layers are convolutional rather than fully connected, and the input image can be any size rather than 128x64. The idea is that the whole image at a particular scale can be fed into this network which yields an image with a presence / character probability values at each "pixel". The idea here is that adjacent windows will share many convolutional features, so rolling them into the same network avoids calculating the same features multiple times.