• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.6
• /
• pp.1-7
• /
• 2008

In this paper, we introduce a new technology to extract the unique features from an iris image, which uses scale-space filtering. Resulting iris code can be used to develop a system for rapid and automatic human identification with high reliability and confidence levels. First, an iris part is separated from the whole image and the radius and center of the iris are evaluated. Next, the regions that have a high possibility of being noise are discriminated and the features presented in the highly detailed pattern are then extracted. In order to conserve the original signal while minimizing the effect of noise, scale-space filtering is applied. Experiments are performed using a set of 272 iris images taken from 18 persons. Test results show that the iris feature patterns of different persons are clearly discriminated from those of the same person.

• The Journal of Korea Robotics Society
• /
• v.4 no.1
• /
• pp.1-9
• /
• 2009

Radio Frequency Identification (RFID) is an automatic identification method. Information such as identification, logistics history, and specification of products are written and stored into the memory of RFID tags (that is, transponders), and retrieved through RF communication between RFID reader device and RFID tags. RFID systems have been applied to many fields of transportation, industry, logistics, environment, etc in order to improve business efficiency and reduce maintenance cost as well. Recently, some research results are announced in which RFID devices are combined with other sensors for mobile robot localization. In this paper, design of multi-protocol baseband for RFID reader device is proposed, and the baseband modem is implemented into SoC (System On a Chip). The baseband modem SoC for multi-protocol RFID reader is composed of several IP (Intellectual Property) blocks such as multi-protocol blocks, CPU, UART(Universal Asynchronous Receiver and Transmitter), memory, etc. As a result, the SoC implemented with FPGA(Field Programmable Gate Array) is applied to real product. It is shown that the size of RFID Reader module designed with the FPGA becomes smaller, and the SoC chip price for the same function becomes cheap. In addition, operation performance could be the same or better than that of the product with no SoC applied.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.3C
• /
• pp.233-240
• /
• 2012

Unlike traditional factory environment, in an industrial factory network applied wireless sensor network technologies, all procedures of discovery, identification and verification of devices should be performed in an automatic fashion. To address these challenges, we design a management system using the device registry server that we propose in this paper. In the phase of device discovery, the proposed system utilizes properties of routing protocol running in factories. Also, in the phase of identification and verification, the system uses unique and general information of a device stored within the device registration server. Such a way allows management system to reduce implementation complexity and to easily manage devices in a factory applied with a wireless network consisting of heterogeneous devices.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.7
• /
• pp.313-318
• /
• 2006

An automatic sample centering system is underway at the protein crystallography beam line of the Pohang Light Source to improve the efficiency of the crystal screening process. A sample pin which contains a protein crystal is mounted on a goniometer head. Then the crystal should be moved to the center of X-ray beam by controlling the motorized goniometer to obtain diffraction data. Since the X-ray beam is located at the center of the image obtained from the CCD camera when the image of the sample pin is in focus, an auto-focusing algorithm is a very important part in the auto-sample-centering system. However the results of applying several well-known auto focusing algorithms directly to the images are not satisfactory owing to the following factors: misalignment of CCD camera, non-uniform cryo-stream in the background of the image and the supporter of the loop. The performance of an auto-focusing algorithm can be increased if the algorithm is applied to only the loop region identified. Non-uniform cryo-stream and a various illumination condition and a stain, which is shown in the image, are main obstacles to loop region identification. In this paper, a simple loop region identification algorithm, which can solve these problems, is proposed and the effective ness of the proposed scheme is shown by applying the auto-focusing algorithm to the loop region identified.

• Journal of Mechanical Science and Technology
• /
• v.15 no.7
• /
• pp.847-858
• /
• 2001

This paper considers the control model identification and H(sub)$\infty$ controller design for a tandem cold mill (TCM). In order to improve the performance of the existing automatic gauge control (AGC) system based on the Taylor linearized model of the TCM, a new mathematical model that can complement the Taylor linearized model is constructed by using the N4SID algorithm based on subspace method and the least squares algorithm based on ARX model. It is shown that the identified model had dynamic characteristics of the TCM than the existing Taylor linearized model. The H(sub)$\infty$ controller is designed to have robust stability to the system parameters variation, disturbance attenuation and robust tracking capability to the set-up value of strip thickness. The H(sub)$\infty$ servo problem is formulated and it is solved by using LMI (linear matrix inequality) techniques. Simulation results demonstrate the usefulness and applicability of the proposed H(sub)$\infty$ controller.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.9
• /
• pp.3701-3720
• /
• 2015

A system for the recognition of machine printed Arabic script is proposed. The Arabic script is shared by three languages i.e., Arabic, Urdu and Farsi. The three languages have a descent amount of vocabulary in common, thus compounding the problems for identification. Therefore, in an ideal scenario not only the script has to be differentiated from other scripts but also the language of the script has to be recognized. The recognition process involves the segregation of Arabic scripted documents from Latin, Han and other scripted documents using horizontal and vertical projection profiles, and the identification of the language. Identification mainly involves extracting connected components, which are subjected to Principle Component Analysis (PCA) transformation for extracting uncorrelated features. Later the traditional K-Nearest Neighbours (KNN) algorithm is used for recognition. Experiments were carried out by varying the number of principal components and connected components to be extracted per document to find a combination of both that would give the optimal accuracy. An accuracy of 100% is achieved for connected components >=18 and Principal components equals to 15. This proposed system would play a vital role in automatic archiving of multilingual documents and the selection of the appropriate Arabic script in multi lingual Optical Character Recognition (OCR) systems.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.21 no.2
• /
• pp.133-140
• /
• 2018

In electronic warfare(EW), low probability of intercept(LPI) radar signal is a survival technique. Accordingly, identification techniques of the LPI radar waveform have became significant recently. In this paper, classification and extracting parameters techniques for 7 intrapulse modulated radar signals are introduced. We propose a technique of classifying intrapulse modulated radar signals using Convolutional Neural Network(CNN). The time-frequency image(TFI) obtained from Choi-William Distribution(CWD) is used as the input of CNN without extracting the extra feature of each intrapulse modulated radar signals. In addition a method to extract the intrapulse radar modulation parameters using binary image processing is introduced. We demonstrate the performance of the proposed intrapulse radar waveform identification system. Simulation results show that the classification system achieves a overall correct classification success rate of 90 % or better at SNR = -6 dB and the parameter extraction system has an overall error of less than 10 % at SNR of less than -4 dB.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.11a
• /
• pp.203-207
• /
• 2006

Nowadays, Cars are continuing to grow at an alarming rate but they also cause many problems such as traffic accident, pollutions and so on. One of the most effective methods that prevent traffic accidents is the use of traffic monitoring systems, which are already widely used in many countries. The monitoring system is beginning to be used in domestic recently. An intelligent monitoring system generates photo images of cars as well as identifies cars by recognizing their plates. That is, the system automatically recognizes characters of vehicle plates. An automatic vehicle plate recognition consists of two main module: a vehicle plate locating module and a vehicle plate number identification module. We study for a vehicle plate number identification module in this paper. We use image preprocessing, feature extraction, multi-layer neural networks for recognizing characters of vehicle plates and we present a feature-comparison method for improving the performance of vehicle plate number identification module. In the experiment on identifying vehicle plate number, 300 images taken from various scenes were used. Of which, 8 images have been failed to identify vehicle plate number and the overall rate of success for our vehicle plate recognition algorithm is 98%.

• Korean Journal of Remote Sensing
• /
• v.35 no.1
• /
• pp.93-115
• /
• 2019

The availability of high-resolution laser scanning data and advanced machine learning algorithms has enabled an accurate potential rockfall source identification. However, the presence of other mass movements, such as landslides within the same region of interest, poses additional challenges to this task. Thus, this research presents a method based on an integration of Gaussian mixture model (GMM) and ensemble artificial neural network (bagging ANN [BANN]) for automatic detection of potential rockfall sources at Kinta Valley area, Malaysia. The GMM was utilised to determine slope angle thresholds of various geomorphological units. Different algorithms(ANN, support vector machine [SVM] and k nearest neighbour [kNN]) were individually tested with various ensemble models (bagging, voting and boosting). Grid search method was adopted to optimise the hyperparameters of the investigated base models. The proposed model achieves excellent results with success and prediction accuracies at 95% and 94%, respectively. In addition, this technique has achieved excellent accuracies (ROC = 95%) over other methods used. Moreover, the proposed model has achieved the optimal prediction accuracies (92%) on the basis of testing data, thereby indicating that the model can be generalised and replicated in different regions, and the proposed method can be applied to various landslide studies.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.635-640
• /
• 2021

In this paper, we describe a parking space identification system that can automatically identify empty parking lot spaces from a parking lot photo. This system is based on a deep learning technique, and the accuracy of the identification result is good by learning various existing parking lot images. It could be applied to the existing parking management system. This system was also developed as a smartphone application for easy testing. Therefore, if you take a picture of a parking lot through a smartphone camera, the captured image is automatically recognized and an empty parking space can be automatically identified.