A Hybrid KNN-SVM Model for Iranian License Plate Recognition

Raj

et al. 2020

Sensors

Automatic vehicle license plate recognition is an essential part of intelligent vehicle access control and monitoring systems. With the increasing number of vehicles, it is important that an effective real-time system for automated license plate recognition is developed. Computer vision techniques are typically used for this task. However, it remains a challenging problem, as both high accuracy and low processing time are required in such a system. Here, we propose a method for license plate recognition that seeks to find a balance between these two requirements. The proposed method consists of two stages: detection and recognition. In the detection stage, the image is processed so that a region of interest is identified. In the recognition stage, features are extracted from the region of interest using the histogram of oriented gradients method. These features are then used to train an artificial neural network to identify characters in the license plate. Experimental results show that the proposed method achieves a high level of accuracy as well as low processing time when compared to existing methods, indicating that it is suitable for real-time applications.

“…They achieved 95.40% character segmentation accuracy. A similar method was also introduced by Tabrizi et al [13], where they achieved 95.24% character segmentation accuracy.…”

Section: License Plate Character Segmentationmentioning

confidence: 96%

Section: Recognition or Classificationmentioning

confidence: 99%

A Vision-Based Machine Learning Method for Barrier Access Control Using Vehicle License Plate Authentication

Raj

et al. 2020

Sensors

“…Reduce the accumulated error, improve the generation ability and minimize the use of infrastructure with fuzzy decision tree (FDT) [95] KNN Improve accuracy, adaptation and provide continuous position information based on k-nearest neighbor algorithm (KNN) [100] SVM Increase the accuracy and decrease the costs, robust against noisy and large data set with a hybrid of the k-nearest neighbors algorithm and the Multi-Class Support Vector Machines (KNN-SVM) model [99] Coarse-grained turn estimation can be performed with very high accuracy [101] Clustering Offers a formalism for identifying with use of hierarchical effective reactive algorithms for navigating through the combinatorial space in concert with geometric realizations for a particular choice of the hierarchical clustering method [96] k-means K-Means clustering is proposed to automatically identify and discard transient high amplitude interferences and make noise covariances estimation [102] Classification A realistic indoor multi path environment classification based on practical RF measurements that is a compromise between accuracy and resources/complexity [97] Regression Improve robustness and accuracy, localization error and the computation complexity based on regression tree Improvement in the positional accuracy base on Artificial Neural Network (ANN) [98] Support Vector Machine Regression (SVR) and Partial Least Squares Regression (PLSR) [103] Bayesian networks…”

Section: Decision Treementioning

confidence: 99%

Indoor navigation systems based on data mining techniques in internet of things: a survey

et al. 2018

Internet of Things (IoT) is turning into an essential part of daily life, and numerous IoT-based scenarios will be seen in future of modern cities ranging from small indoor situations to huge outdoor environments. In this era, navigation continues to be a crucial element in both outdoor and indoor environments, and many solutions have been provided in both cases. On the other side, recent smart objects have produced a substantial amount of various data which demands sophisticated data mining solutions to cope with them. This paper presents a detailed review of previous studies on using data mining techniques in indoor navigation systems for the loT scenarios. We aim to understand what type of navigation problems exist in different IoT scenarios with a focus on indoor environments and later on we investigate how data mining solutions can provide solutions on those challenges.

“…This method is sensitive to the noise disturbance, and image orientation [1]. While the supervised-based method has common classifiers that have been used for character recognition, Mark net and Bayes net have been used as mention in [9,10] , which are Neural Network (NN) as mention in [11,12] ,and support vector machine (SVM) as mention in [13][14][15]. Because of the rapid development in digital signal processing and digital image processing, many systems implemented on an embedded digital system to process video stream, such as in [16].The system consist of modules to detect and recognize characters.…”

Section: Related Workmentioning

confidence: 99%

Plate Detection and Recognition of Iraqi License Plate Using KNN Algorithm

Alaidi¹,

Alsaidi²,

Yahya

2017

eduj

This paper presents an automated car license plate recognition system applied for Iraqi vehicle plate number that developed and applied to be used in control and law enforcement related applications. In this work, the proposed license plate recognition consists of three basic stages (preprocessing, license plate localization, license plate recognition). The license plate images are pre-processed through convert image to grayscale and apply morphological transformation filter not convert the result to binary image. Then, blurs the binary image using Gaussian filter and find all contour in image using OpenCV library. In the license plate localization KNN (k-Nearest Neighbors) algorithm are used to find all possible characters in the image. The last step is done by Crop the part of image with highest candidate license plate and apply the preprocessing and license plate localization again to find and recognize all part of license plate in the cropped image.