Deep‐learning‐based license plate detection method using vehicle region extraction

Abstract

A new license plate detection method for challenging environments is proposed. Background clutters are common in road scene images and the detection of license plates (occupying only a small part of an image) is considered as a difficult problem. In order to address this problem, a two‐step approach is developed: first vehicle regions are detected and the license plate in each vehicle region is localised. This vehicle region detection based approach provides scale information and limits search ranges in license plate detection, so that one can reliably detect license plate regions. To be precise, the faster region‐based convolutional neural network algorithm for the vehicle region detection is adopted and candidates for license plates in each detected region with the hierarchical sampling method are generated. Finally, non‐plate candidates are filtered out by training a deep convolutional neural network. The proposed method is evaluated on the Caltech dataset and the method showed a precision of 98.39% and a recall of 96.83%, which outperforms conventional methods.

A Novel Least Square and Image Rotation based Method for Solving the Inclination Problem of License Plate in Its Camera Captured Image

“…In this paper, since our proposed method highlights algorithm of optimizing inclination problem of license plates in their camera captured images, their segmentation and recognition methods are not the focus of this paper, but can be consulted in Ref. [19], Ref. [20] and Ref.…”

Temporal matching prior network for vehicle license plate detection and recognition in videos

“…The architecture consists of two major stages: license plate detection and license plate recognition. In the first stage, we exploit additional information in the previous ( t − 1) and subsequent ( t + 1) frames to detect license plates in the current ( t ) frame of the video, as a departure to existing algorithms . Our detection network has 22 layer structures and each layer structure is composed of three operations: convolution, batch normalization (BN), and max pooling (Maxpool).…”

“…Automatic vehicle license plate detection and recognition are increasingly important in intelligent transportation systems, and they play a key role in various areas such as unmanned parking and traffic control. Drawn by these increasing needs, state‐of‐the‐art algorithms based on convolutional neural networks (CNNs) have been proposed for license plate detection and recognition . Table provides details of the existing approaches including methods, objectives, datasets, target countries, accuracies, and processing times.…”

“…Although Korean license plates were handled in , their data are not available and, in all cases, the amount of data is not sufficient to validate the Korean license plate recognition performance. Meanwhile, despite promising results on several refined still image datasets, the algorithms in still suffer from significant limitations when applied to video data. The main issues are: (a) the vehicle motion blur and geometric distortion, (b) outlier objects such as signboards containing text quite similar to license plates, and (c) the lack of a public training dataset for plate detection and recognition in videos.…”

“…The main issues are: (a) the vehicle motion blur and geometric distortion, (b) outlier objects such as signboards containing text quite similar to license plates, and (c) the lack of a public training dataset for plate detection and recognition in videos. To address the issues in real‐world videos identified across the existing algorithms , in this study, we designed a CNN architecture with temporal matching priors between adjacent frames. The forward matching (FM) prior leads to an improvement in the accuracy of the detection of motion‐blurred or distorted plates by generating the missing bounding boxes that hold the plate position information.…”