Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 46 views

    ALPR

    Uploaded by

    Vamsi Reddy
    The document discusses experimental license plate recognition using deep learning models in Keras. It summarizes previous work on license plate detection and recognition using techniques like YOLO, SSD, and CNNs. It then outlines the goal of testing models like VGG19, EfficientNetB7, and ResNet152 on license plate datasets to evaluate their performance, finding prediction accuracies of around 92-95%.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    ALPR

    Uploaded by

    Vamsi Reddy
    46 views7 pages
    The document discusses experimental license plate recognition using deep learning models in Keras. It summarizes previous work on license plate detection and recognition using techniques like YOLO, SSD, and CNNs. It then outlines the goal of testing models like VGG19, EfficientNetB7, and ResNet152 on license plate datasets to evaluate their performance, finding prediction accuracies of around 92-95%.

    Original Title

    ALPR ppt

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses experimental license plate recognition using deep learning models in Keras. It summarizes previous work on license plate detection and recognition using techniques like YOLO, SSD, and CNNs. It then outlines the goal of testing models like VGG19, EfficientNetB7, and ResNet152 on license plate datasets to evaluate their performance, finding prediction accuracies of around 92-95%.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    46 views7 pages

    ALPR

    Uploaded by

    Vamsi Reddy
    The document discusses experimental license plate recognition using deep learning models in Keras. It summarizes previous work on license plate detection and recognition using techniques like YOLO, SSD, and CNNs. It then outlines the goal of testing models like VGG19, EfficientNetB7, and ResNet152 on license plate datasets to evaluate their performance, finding prediction accuracies of around 92-95%.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 7

    EXPERIMENTAL BASED LICENSE PLATE

    RECOGNITION USING KERAS APPLICATIONS

    Project Associates
    G. VAMSIDHAR REDDY (199F1A0418)
    R. MAHENDRA REDDY (199F1A0441)
    C. GOPAL ABHISHEK (199F1A0413)
    G. VIJAY KUMAR (199F1A0417)
    M. PURUSHOTTAMA REDDY (209F5A0411)
    B. SANTHOSH KUMAR (199F1A0406)

    PROJECT CO-ORDINATOR PROJECT GUIDE


    Smt. T. RANJITHA DEVI M.Tech, (Ph.D) Mr. J. E. SIVA M.Tech
    Assistant Professor, ECE Dept. Assistant Professor, ECE Dept.

    SRI VENKATESWARA INSTITUTE OF TECHNOLOGY


    (Affiliated to JNTU, Anantapuramu)
    Hampapuram(V), Raptadu (M)-515772, Anantapuramu (Dist.),A.P.
    ABSTRACT

     Automatic license plate recognition (ALPR) is generally considered a solved problem in the
    computer vision community.
     Due to recent developments in highway research and increased utilization of vehicles, there has
    been significant interest paid on latest, effective, and precise Intelligent Transportation System
    (ITS).
     Some experimental based model by using Deep learning Keras Applications like VGG19,
    EfficientNetB7, ResNet152 model with pre-trained weights and train this to our data.
     For this model we had use two types of license plate Image Datasets like “vehicle Number
    Plate Detection” and “Fifty States car License Plate dataset” for testing on this model.
     Finally, we had got predicted results are VGG19 with 92%, EfficientNetB7 with 90% and
    ResNet152 with 95% approximately for both datasets.
    LITERATURE SURVEY

    License Plate Detection Using Convolutional Neural Network–Back to the Basic with Design
    of Experiments (March 4, 2022)
    • Automatic License Plate Recognition (ALPR) is one of the applications that hugely benefited from
    Convolutional Neural Network (CNN) processing.
    • However, good performing models such as YOLOv3 and SSD (Single-Shot detector)
    • They focuses on the design of experiment (DOE) of training parameters in transferring YOLOv3 model
    design and optimising the training specifically for license plate detection tasks.
    • ALPR performance of YOLOv3 with the CNN model untouched, specifically on the LP detection task.
    • An AP of 99% is achieved for Malaysian vehicle LP detection by strategically tuning the YOLOv3 training
    parameters.

    AUTOMATIC NUMBER PLATE RECOGNITION USING TENSORFLOW AND


    EASYOCR(September -2022):
    • First, it is necessary to locate and extract the license plate region from a larger scene image.
    • Second, having a license plate region to work with, the alphanumeric characters in the plate need to be
    extracted from the background.
    • Third, deliver them to a character system (BOX APPROACH) for recognition.
    • Study and resolve algorithmic and mathematical aspects of the automatic number plate recognition systems,
    such as problematic of machine vision, pattern recognition, OCR and neural networks.
    Vehicle License Plate Recognition (June 05, 2021 ):
    • VLPR is used in various commercial applications, including electronic toll collecting, personal
    security, visitor management systems, parking management, and other corporate applications.
    • License plate detection using a You Only Look Once (YOLO)-PyTorch deep learning
    architecture.
    • YOLO version 5 to recognize a single class in an image dataset.

    Automatic License Plate Recognition with YOLOv5 and Easy-OCR method (June 2022):
    • The number of automobiles on the road has risen steadily during the last decade.
    • Obtaining real-time CCTV footage is an extremely time-consuming task.
    • You Only Look Once (YOLO), is used for object detection and Easy-OCR for character
    recognition.
    • Technologies such as object identification, OCR, character segmentation, and character
    recognition, among others.
    A Light CNN for End-to-End Car License Plates Detection and Recognition
    (December 13, 2019) :
    • The multi-task license plate detection algorithm of three-layer cascaded network, to complete
    the license plate detection, corner detection and colour recognition task using an entire network
    structure.
    • License plate recognition adopts CRNN and CTC model to realize end-to-end object recognition
    algorithm.
    • The experimental result shows that our method achieves up to 98% recognition precision and is
    superior to other methods in the precision and speed of detection and recognition.

    Multi-national and Multi-language License Plate Detection using Convolutional Neural


    Networks (August 2020):
    • They focused on LP detection and classification of multi-national and multi-language LPs with
    different layouts from BR, USA, EU, TR, KSA and UAE, proposing a method that can detect
    LPs regardless of their country of origin, language or layout.
    • In addition, a new multi-national, multi-language and multi-layout LP dataset was introduced
    in order to enable benchmarking and to close the gap in this field.
    • LP detection average precision was 99.57%, while the LP classification accuracy was 99.33%.
    A Real-Time Vehicle Number Plate Detection and Recognition System (2020):
    • Real-time vehicle number plate recognition (RVNPR)
    • It's not necessary to put in additional devices like GPS or radio frequency Identification (RFID)
    to implement the proposed system.
    • Using high-definition cameras, the system takes images of every passing vehicle and sends the
    image to the computer for processing by RVNPR software.
    • The advantage of our proposed method is its high accuracy in plate detection and recognition.

    You might also like