DELP-DAR system for license plate detection and recognition

Abstract

Automatic License Plate detection and Recognition (ALPR) is a quite popular and active research topic in the field of computer vision, image processing and intelligent transport systems. ALPR is used to make detection and recognition processes more robust and efficient in highly complicated environments and backgrounds. Several research investigations are still necessary due to some constraints such as: completeness of numbering systems of countries, different colors, various languages, multiple sizes and varied fonts. For this, we present in this paper an automatic framework for License Plate (LP) detection and recognition from complex scenes. Our framework is based on mask region convolutional neural networks used for LP detection, segmentation and recognition. Although some studies have focused on LP detection, LP recognition, LP segmentation or just two of them, our study uses the maskr-cnn in the three stages. The evaluation of our framework is enhanced by four datasets for different countries and consequently with various languages. In fact, it tested on four datasets including images captured from multiple scenes under numerous conditions such as varied orientation, poor quality images, blurred images and complex environmental backgrounds. Extensive experiments show the robustness and efficiency of our suggested framework in all datasets.

Research on Image Adaptive Enhancement Algorithm under Low Light in License Plate Recognition System

“…With the deepening of the network structure, these features become more and more abstract. With the complexity and difference of license plate images collected under different lighting conditions being taken into consideration, Lenet5 convolutional neural network is designed to classify the enhanced images in the paper [13]. The network schematic diagram is shown in Figure 2, and it is composed of two convolution pooling layers and three fully connected layers, where the loss function is defined as the cross-entropy loss function.…”

“…The final SSIM index is shown in the Equation (13). When it is set so that C 3 = C 2 /2, the equation can be reduced to Equation (14).…”

Нейромережева Система Розпізнавання Автономера

“…На першому етапі вхідне зображення довільним чином розбивається на множину регіонів зацікавлення, які поступають на входи згорткових мереж (CNN, Convolution Neural Networks), які вирішують завдання місцезнаходження автономера на вхідному зображенні та формує на виході багатовимірний вектор ознак (4096 у нашому випадку). Отримані вектори ознак поступають на вхід класифікатора SVM (support vector machine,), лінійних класифікаторів на базі методу опорних векторів [14][15][16]. На виході Mask R-CNN нейромережі отримуємо місцеположення пластини автономера на фотозображенні автомобіля (рис.…”

Indonesian Plate Number Identification Using YOLACT and Mobilenetv2 in the Parking Management System

“…Many factors affect ALPR recognition accuracies such as light ambient, image resolution, camera angles, etc. Previously in ALPR researches has been done, there were 2 methods Generally used such as morphological approach [2][3][4][5] and Deep Learning approach [6][7][8][9]. The deep learning approach is often used recently because has better accuracy than the edge detection approach, Despite the fact deep learning approach has poor performance speed.…”

“…The research [8] performed plate number detection, segmentation, and character recognition using Mask Region Convolutional Neural Network (Mask R-CNN). This study used GoogLeNet [12] without inception module as feature extraction, and swish activation function.…”