• Journal of Advanced Navigation Technology
• /
• v.14 no.1
• /
• pp.27-32
• /
• 2010

In this paper, we research a virtual card generation system to secure e-commerce. Network security has increased the need to meet rapidly growing trend. And the amount and quality of e-commerce expansion due to the need for secure commerce transactions has increased even more. Instead of exposing the actual credit card number, we expose a virtual card number on the network. It can prevent the risk of hacking. We proved that through various experiments.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.287-290
• /
• 2017

키스트로크 다이나믹스 사용자 인증은 행위 기반 인증 방법 중의 하나로써, 사용자가 입력하는 비밀번호 혹은 PIN번호의 패턴을 분석하여 사용자를 인증한다. 비밀번호나 PIN번호가 다른 사용자에게 노출되어도 입력 패턴을 분석하여 사용자를 인증함으로써 지식기반(what you know) 인증의 단점을 보완할 수 있다. 하지만 사용자의 입력 패턴이 항상 일정하지 않고, 사용자별 터치하는 방법이 모두 다르기 때문에 모든 사용자에게서 동일한 특징을 추출하여 그 사용자의 패턴을 생성하고 인증 수단으로 사용하기에는 한계가 있다. 이에 본 논문에서는 사용자별 맞춤형 특징 집합과 전체 특징과의 사용자 인증 성능 변화를 실험을 통해 확인한다. 사용자별 맞춤형 특징이 전체 특징을 사용한 경우보다 평균적으로 EER 6% 이상의 성능 향상이 있었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.11
• /
• pp.2432-2438
• /
• 1997

This paper proposes recognition system using multi-backpropagation neural networks rather than single backpropagation neural network to enhance the rate of character recognition resultsing from extracting the region of velhicle number in that the image of vehicle number plate from CCD camera has a distinguish feature, that is, illumination of a pattern. The experiment in this paper shows an output that the method using multi-backpropagation neural networks rather than signal backpropagation neural network takes less training time for computation and also has higher recognition rage of vehicle number.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2001.06a
• /
• pp.281-284
• /
• 2001

In this paper, we present a car number retrieving system using speech recogntion and speech synthesis for PDA. This system consist of 4-digit numbers and command speech recognition as well its speech synthesis. Experiment results showed 4-digit numbers recognition rate 97% and commands recognition 99% through speaker-independent method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.568-570
• /
• 2002

최근, 분류기 쪽에서는 모듈라 학습을 이용한 방법들에 대해서 상당한 관심이 모아지고 있다. 모듈라 학습 방법은 divide and conquer 개념에 바탕을 두고 있기 때문에 복잡한 문제에 대해서 학습 질 측면이나 학습 속도 면에서 단일 분류기에 비해 좋은 결과들을 나타내고 있다. 인공신경망을 이용한 분류 방법 쪽에서도 이러한 연구들이 이루어지고 있다. 본 논문에서는 번호판 인식을 위한 간단한 형태의 모듈라 신경망을 제안하고 이의 성능을 평가하였다. 실험 결과, 일반적인 차량 번호판의 영상에서 성공적인 결과를 보였으며, 잡음에 의한 훼손된 번호판도 좋은 인식 결과를 보였다. 또한 인식률 측면 뿐만 아니라 학습 속도 면에서도 상당한 이득이 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10a
• /
• pp.238-240
• /
• 2004

경제 성장과 생활 수준의 향상으로 인한 자동차 수의 증가는 않은 문제를 발생시키고 있다 제한된 인력과 비용으로 효율적인 자동차 관리를 위한 연구 분야 중에서 자동차 번호판 인식 (Vehicle Plate Recognition) 기술은 법규위반의 식별, 통행료 징수, 납세, 도난.도주 차량 확인 및 주차 관리 등의 않은 분야에 응용되고 있다. 자동차 번호판 문자 인식 문제와 같이 훈련 예제 수집 비용이 많이 드는 경우에 제한된 수의 훈련 예제를 최대한 활용하여 분류 성능을 향상시키기 위한 방안 중 하나로, 수집된 훈련 예제들로부터 가상의 예제를 생성하고, 생성된 가상 예제를 훈련 예제로 추가하여 학습하는 절러 연구가 수행된 바 있다. 본 논문에서는 자동차 번호판 문자 인식의 성능 향상을 위친 수집된 예제들을 적절히 병합하여 가상의 예제를 생성하는 방안에 관해 기술하고, 문자 인식 분야에서 일반적으로 많이 사용되는 여러 알고리즘에 대하여 다양한 가상 예제 생성 방안 및 다양한 생성 비율 따른 실험을 통해 그 효용성을 확인하였다

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.4
• /
• pp.173-179
• /
• 2012

In this paper, we presents a new method for vehicle number plate detection. Our method is basically the method extracting a rectangles from a car image because the shape of a vehicle number plate is a rectangle. For detecting the vehicle number plate, firstly, the contrast of the input image is enhanced. Then, the lines in the image are obtained by using LSD(line segment detector), and rectangles in the image are detected from the line data. These rectangles are the candidates of the car plate, from which the car plate is selected. In this procedure, the method of detecting rectangles is our proposed method, which consists of three stages: (1) extracting corners from the line segments by LSD; (2) extracting diagonal lines from the corner data; and (3) detecting rectangles from diagonal line information. And finally the vehicle number plate is selected from these rectangles by using the feature of the vehicle number plate and the inside information of rectangles. In the experiments with the 100 images captured by our digital camera, we have achieved a detection rate of 94%.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.35T no.3
• /
• pp.46-52
• /
• 1998

In this paper, after inputting the computer with the attached number plate on the vehicle, using it, the color decomposition method and back propagation neural network proposed the extractable method of the vehicle number plate at high speed. This method separated R, G, B signal form input moving vehicle image to computer through video camera, then after transform this R, G, B signal into input image data of the computer by using color depth of vehicle number plate and store up binary value in the memory frame buffer. After adapting character's recognition algorithm, also improving this, by adapting back propagation neural network makes the vehicle number plate recognition system. Also minimalizing the similar color's confusion, adapting horizontal and vertical extracting algorithm by using the vehicle's rectangular architecture shows the extract and character's recognition of the vehicle number plate at high speed.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.705-711
• /
• 2011

This paper proposes an effective algorithm of license plate recognition for industrial applications. By applying Canny edge detection on a vehicle image, it is possible to find a connected rectangular, which is a strong candidate for license plate. The color information of license plate separates plates into white and green. Then, OTSU binary image processing and foreground neighbor pixel propagation algorithm CLNF will be applied to each license plates to reduce noise except numbers and letters. Finally, through labeling, numbers and letters will be extracted from the license plate. Letter and number regions, separated from the plate, pass through mesh method and thinning process for extracting feature vectors by X-Y projection method. The extracted feature vectors are compared with the pre-learned weighting values by backpropagation neural network to execute final recognition process. The experiment results show that the proposed license plate recognition algorithm works effectively.

• Journal of IKEEE
• /
• v.23 no.2
• /
• pp.642-651
• /
• 2019

One of the most important research topics on intelligent transportation systems in recent years is detecting and recognizing a license plate. The license plate has a unique identification data on vehicle information. The existing vehicle traffic control system is based on a stop and uses a loop coil as a method of vehicle entrance/exit recognition. The method has the disadvantage of causing traffic jams and rising maintenance costs. We propose to exploit differential image of camera background instead of loop coil as an entrance/exit recognition method of vehicles. After entrance/exit recognition, we detect the candidate images of license plate using the morphological characteristics. The license plate can finally be detected using SVM(Support Vector Machine). Letter and numbers of the detected license plate are recognized using CNN(Convolutional Neural Network). The experimental results show that the proposed algorithm has a higher recognition rate than the existing license plate recognition algorithm.