Abstract
The system called Automatic number plate recognition (ANPR) is used to read information from number plates on objects. The components of ANPR systems include image capture hardware, image processing software, and pattern recognition methods. However, the quality of the picture that is taken is extremely important for ANPR systems' accuracy. Images in real-world situations may be impacted by a variety of elements, including illumination, blur, noise, and occlusion, which can lower the image's quality and result in inaccurate recognition. Therefore, before the input picture is transferred to the ANPR system, image enhancement techniques are crucial for enhancing its quality. Numerous image improvement methods, including noise reduction, contrast enhancement, and picture restoration, have been suggested in recent years to increase the functionality of ANPR devices.This research offers a thorough analysis of the most recent image enhancement methods and how they affect the precision of ANPR systems. The testing findings show that the suggested strategies can greatly increase the ANPR systems' recognition rate.
For smart cities and the Internet of Things, more study into number plate recognition, also known as number plate identification, may be helpful. using image processing techniques. Due to the exponential growth in the number of automobiles, automated systems must be used to store vehicle data for a variety of reasons. A useful approach for detecting Indian licence plates has been developed, and it is recommended. Loud sounds, inadequate illumination, unevenness, and strangely shaped licence plates are all things we can put up with.The per-processing step of this study uses a variety of image processing techniques, including morphological transformation, Gaussian smoothing, Gaussian thresholding, and the Sobel edge detection approach.An enhanced lightweight detection technique for licence plate identification in real-world scenarios was offered as the prior method was inefficient and slow.