• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.12
• /
• pp.131-141
• /
• 2012

This paper proposes a method of analyzing unrecognizable numbers of license plate images, which are degraded by various factors such as low resolution, low light level, geometric distortion, and periodic noise, to name a few. With existing vehicle license plate recognition methods, it is difficult to recognize license plate if images are not recognizable in the pre-process of removing degradation factors. Although images of license plate have not been improved to be recognizable in the pre-process, the proposed method makes it possible to recognize numbers of license by distorting pre-saved reference images of license plate numbers same as sample plates, and by assuming likelihood ratio using statistical methods. The proposed method also makes it possible to identify suspect vehicle license plate under unstable light conditions and with low resolution images that are unrecognizable by the naked eye. This method has been used in real criminal investigation to recognize numbers of license plate of criminal vehicle, and has proved to be useful as criminal evidence through experiments under various conditions.

• 한국전기화학회:학술대회논문집
• /
• 2005.07a
• /
• pp.253-256
• /
• 2005

• Korean Journal of Computational Design and Engineering
• /
• v.20 no.3
• /
• pp.230-237
• /
• 2015

Soil deformation on the off-load ground is significantly affected by soil conditions, such as soil type, water content, and etc. Thus, the soil characteristics should be estimated for predicting vehicle movements on the off-load conditions. The plate-sinkage test, a widely-used experimental test for predicting the wheel-soil interaction, provides the soil characteristic parameters from the relationship between soil stress and plate sinkage. In this study, soil stress under the plate-sinkage situation is calculated by the DEM (Discrete Element Method) model. We developed a virtual soil bin with DEM to obtain the vertical reaction forces under the plate pressing the soil surface. Also parametric studies to investigate effects of DEM model parameters, such as, particle density, Young's modulus, dynamic friction, rolling friction, and adhesion, on the characteristic soil parameters were performed.

• Proceedings of the KIPE Conference
• /
• 1998.07a
• /
• pp.95-98
• /
• 1998

Applying the magnetically levitated transportation system, which is noncontact bearing system, to solve the problems such as transformation of original form or flaw of iron plate caused by transportation of thin iron plate which required high quality as body of motor vehicle, materials of electronic devices etc.. Magnetic saturation phenomena caused by thickness of iron plate and gap size between magnets. In case of iron plate, the vibration mode will be considered since vibration occurs during transportation. In order to solve the problems caused by vibration, choose the levitation system method using numbers of magnet, magnetic saturation for thickness and length of iron plate with parameters in location and gap of magnet. In this paper, we will suggest the whole design technique of magnetically levitated transportation system, namely method of magnetic attraction and transportation system

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.2
• /
• pp.299-306
• /
• 2020

Image recognition using neural networks is widely used in various fields. In this study, we investigated licensed / unlicensed vehicle recognition systems necessary for vehicle number recognition and control when entering and exiting a specific area. This system is equipped with the function of recognizing the image, so it checks all the information on the vehicle number and adds the function to accurately recognize the vehicle number plate. In addition, it is possible to check the vehicle number more quickly using a neural network.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.17 no.4
• /
• pp.85-94
• /
• 2021

The LPR system's trigger sensor makes problem occasionally due to the heave weight of vehicle or the obsolescence equipment. If we replace the hardware sensor to the deep-learning based software sensor in order to generate the trigger signal, LPR system maintenance would be a lot easier. In this paper we proposed the deep-learning sliding window based object detection and tracking algorithm for the LPR system's trigger signal generation. The gate passing vehicle's license plate recognition results are combined into the normal tracking algorithm to catch the position of the vehicle on the trigger line. The experimental results show that the deep learning sliding window based trigger signal generating performance was 100% for the gate passing vehicles including the 5.5% trigger signal position errors due to the minimum bounding box location errors in the vehicle detection process.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.16 no.4
• /
• pp.19-28
• /
• 2020

Vehicle license plate recognition system is not generalized in Malaysia due to the loose character layout rule and the varying number of characters as well as the mixed capital English characters and italic English words. Because the italic English word is hard to segmentation, a separate method is required to recognize in Malaysian license plate. In this paper, we propose a mixed character level and word level English license plate recognition algorithm using deep learning neural networks. The difference of Gaussian method is used to segment character and word by generating a black and white image with emphasized character strokes and separated touching characters. The proposed deep learning neural networks are implemented on the LPR system at the gate of a building in Kuala-Lumpur for the collection of database and the evaluation of algorithm performance. The evaluation results show that the proposed Malaysian English LPR can be used in commercial market with 98.01% accuracy.

• Journal of Auto-vehicle Safety Association
• /
• v.9 no.4
• /
• pp.48-54
• /
• 2017

This paper presents the motorcycle inspection standards development on the vehicle identification, engine and transmission, tyres and wheels, steering and suspension, and brake system. 187 real-world motorcycles are visually and mechanically inspected according to the developed inspection standards. The non-compliance rate of the vehicle identification is 20.3% and main causes are insecure, damaged, and not clearly visible number plate. The non-compliance rate of the brake system is 15.5% and main cause is failing to meet the brake performance requirements. The motorcycle inspections standards are improved reflecting 187 cases of real-world motorcycle inspection results.

• Proceedings of the KSR Conference
• /
• 2009.05b
• /
• pp.217-222
• /
• 2009

High-speed EMU under development vibrates more than a articulated high-speed train since power units are attached on each vehicle and railway vehicle. In this study, anisotropic equivalent stiffness of a aluminum extrusion plate were calculated to know and predict vibration characteristic of High-speed EMU under development. Eigen frequencies and modal shape of high speed train vehicle were calculated. And vibration generated was predicted at each position of vehicle when vehicle was operating.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.409-415
• /
• 2003

Recently, the modular learning are very popular and receive much attention for pattern classification. The modular learning method based on the "divide and conquer" strategy can not only solve the complex problems, but also reach a better result than a single classifier′s on the learning quality and speed. In the neural network area, some researches that take the modular learning approach also have been made to improve classification performance. In this paper, we propose a simple modular neural network for characters recognition of vehicle number plate and evaluate its performance on the clustering methods of feature vectors used in constructing subnetworks. We implement two clustering method, one is grouping similar feature vectors by K-means clustering algorithm, the other grouping unsimilar feature vectors by our proposed algorithm. The experiment result shows that our algorithm achieves much better performance.