A SURVEY ON VARIOUS AVAILABLE OBJECT DETECTION MODELS AND APPLICATION IN AUTOMATIC LICENCE PLATE DETECTION Aditya Kulkarni 1 , Manali Munot 2 , Sai Salunkhe 3 Shubham Mhaske 4 Nilesh Korade 5 1 Student at Pimpri Chinchwad College of Engineering and Research, Ravet, Pune, India-412101 2 Student at Pimpri Chinchwad College of Engineering and Research, Ravet, Pune, India-412101 3 Student at Pimpri Chinchwad College of Engineering and Research, Ravet, Pune, India-412101 4 Student at Pimpri Chinchwad College of Engineering and Research, Ravet, Pune, India-412101 5 Asst. Professor at Pimpri Chinchwad College of Engineering and Research, Ravet, Pune, India-412101 Abstract: With the development in technologies right from serial to parallel computing, GPU, AI, and deep learning models a series of tools to process complex images have been developed. The main focus of this research is to compare various algorithms(pre-trained models) and their contributions to process complex images in terms of performance, accuracy, time, and their limitations. The pre-trained models we are using are CNN, R-CNN, R-FCN, and YOLO. These models are python language-based and use libraries like TensorFlow, OpenCV, and free image databases (Microsoft COCO and PAS-CAL VOC 2007/2012). These not only aim at object detection but also on building bounding boxes around appropriate locations. Thus, by this review, we get a better vision of these models and their performance and a good idea of which models are ideal for various situations. Keywords: Digital Image Processing, OpenCV, License Plate Detection, License Plate Recognition,YOLO,OCR. 1. INTRODUCTION Many systems use vehicle plate identification and recognition, including travel time calculation, highway car counting, traffic violation detection, and surveillance applications. As the population grows, so does the number of vehicles on the road.As a result, finding a parking spot for a large number of students and faculty at Educational Institutions has become increasingly difficult. The majority of parking lots are handled manually by security guards who may or may not keep track of the vehicles parked there.As a result, the vehicle driver must continue to walk the parking lot in search of a parking spot. In the absence of security guards, car robberies and quarrels between drivers over parking spaces can occur.Automated License Plate Recognition (ALPR) is another name for Automated Number Plate Recognition (ANPR).Automatic Number Plate Recognition, or ANPR, is a technology that 'reads' vehicle number plates using pattern recognition. Simply put, ANPR cameras 'photograph' the number plates of vehicles that violate the rules as they drive by.This 'photograph' is then fed into a computer system, which extracts information about the vehicle's driver and owner, as well as information about the vehicle itself. ANPR is made up of ccs that are regulated by a computer.When a car passes, ANPR 'reads' Vehicle Registration Marks – also known as number plates – from digital images captured by cameras mounted on a mobile unit or in traffic monitoring vehicles.In the identification of licence plates, computer vision and character recognition, as well as algorithms for licence plate recognition, play a critical role. As a result, they are the foundation of every ANPR scheme.A static camera, a framer, a monitor, and specially built applications for image processing, analysis, and recognition are all part of the framework for automatic car licence plate recognition. Journal of University of Shanghai for Science and Technology ISSN: 1007-6735 Volume 23, Issue 6, June - 2021 Page -47