• The KIPS Transactions:PartB
• /
• 제18B권6호
• /
• pp.405-414
• /
• 2011

Korean grammar checkers typically detect context-dependent errors by employing heuristic rules that are manually formulated by a language expert. These rules are appended each time a new error pattern is detected. However, such grammar checkers are not consistent. In order to resolve this shortcoming, we propose new method for generalizing error decision rules to detect the above errors. For this purpose, we use an existing thesaurus KorLex, which is the Korean version of Princeton WordNet. KorLex has hierarchical word senses for nouns, but does not contain any information about the relationships between cases in a sentence. Through the Tree Cut Model and the MDL(minimum description length) model based on information theory, we extract noun classes from KorLex and generalize error decision rules from these noun classes. In order to verify the accuracy of the new method in an experiment, we extracted nouns used as an object of the four predicates usually confused from a large corpus, and subsequently extracted noun classes from these nouns. We found that the number of error decision rules generalized from these noun classes has decreased to about 64.8%. In conclusion, the precision of our grammar checker exceeds that of conventional ones by 6.2%.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• 제43권3호
• /
• pp.30-38
• /
• 2006

In this paper, we improved to drops recognition rate according to distance using distance and depth information with 3D from stereo face images. A monocular face image has problem to drops recognition rate by uncertainty information such as distance of an object, size, moving, rotation, and depth. Also, if image information was not acquired such as rotation, illumination, and pose change for recognition, it has a very many fault. So, we wish to solve such problem. Proposed method consists of an eyes detection algorithm, analysis a pose of face, md principal component analysis (PCA). We also convert the YCbCr space from the RGB for detect with fast face in a limited region. We create multi-layered relative intensity map in face candidate region and decide whether it is face from facial geometry. It can acquire the depth information of distance, eyes, and mouth in stereo face images. Proposed method detects face according to scale, moving, and rotation by using distance and depth. We train by using PCA the detected left face and estimated direction difference. Simulation results with face recognition rate of 95.83% (100cm) in the front and 98.3% with the pose change were obtained successfully. Therefore, proposed method can be used to obtain high recognition rate with an appropriate scaling and pose change according to the distance.

• Journal of the Korea Society of Computer and Information
• /
• 제25권3호
• /
• pp.33-42
• /
• 2020

There has been difficulties in identifying objects by relying on the naked eye in various surveillance systems. There is a growing need for automated surveillance systems to replace soldiers in the field of military surveillance operations. Even though the object detection technology is developing rapidly in the civilian domain, but the research applied to the military is insufficient due to a lack of data and interest. Thus, in this paper, we applied one of deep learning algorithms, Convolutional Neural Network-based binary classification to develop an autonomous identification model of both friend and foe helicopters (AH-64, Mi-17) among the military weapon systems, and evaluated the model performance by considering accuracy, precision, recall and F-measure. As the result, the identification model demonstrates 97.8%, 97.3%, 98.5%, and 97.8 for accuracy, precision, recall and F-measure, respectively. In addition, we analyzed the feature map on convolution layers of the identification model in order to check which area of imagery is highly weighted. In general, rotary shaft of rotating wing, wheels, and air-intake on both of ally and foe helicopters played a major role in the performance of the identification model. This is the first study to attempt to classify images of helicopters among military weapons systems using CNN, and the model proposed in this study shows higher accuracy than the existing classification model for other weapons systems.

• Journal of the Korean Society for Nondestructive Testing
• /
• 제23권5호
• /
• pp.464-474
• /
• 2003

Ultrasonic imaging of 3-D structures for nondestructive evaluation must provide readily recognizable images with enough details to clearly show various flaws that may or may not be present. Typical flaws that need to be detected are miniature cracks, for instance, in metal pipes having aged over years of operation in nuclear power plants; and these sub-millimeter cracks or flaws must be depicted in the final 3-D image for a meaningful evaluation. As a step towards improving conspicuity and thus detection of flaws, we propose a pulse-echo ultrasonic imaging technique to generate various 3-D views of the 3-D object under evaluation through strategic scanning and processing of the pulse-echo data. We employ a 2-D Wiener filter that filters the pulse-echo data along the plane orthogonal to the beam propagation so that ultrasonic beams can be sharpened. This three-dimensional processing and display coupled with 3-D manipulation capabilities by which users are able to pan and rotate the 3-D structure improve conspicuity of flaws. Providing such manipulation operations allow a clear depiction of the size and the location of various flaws in 3-D.

• Journal of Korea Multimedia Society
• /
• 제14권1호
• /
• pp.121-132
• /
• 2011

A healthcare system is a type of medical information system that performs early detection and prevention in diseases by checking one's health condition periodically. Such a healthcare system is based on the signal obtained from the body. However, the developed existing system represents certain differences in the storage and description of vital signs according to medicare devices and the evaluation method of the system. It brings some disadvantages, such as lacks in the interoperability between systems, increases in the development cost of systems, and absence of a unified system. Thus, this study develops a healthcare system based on a meta model. For establishing this objective, this study describes and stores vital sign data based on the standard meta model of HL7 and applies OCL, which is a mathematical specification language, for defining wellness indexes and extracting data in order to evaluate health risk appraisals in health. In addition, this study implements components based on OSGi and assemble them in order to easily extend various devices and systems. By describing vital data based on the meta model, it represents some advantages that it makes possible to ensure the interoperability between systems and introduce the standardization of the evaluation method of health conditions through defining the wellness index using OCL. Also, it provides dear specifications.

• Journal of Astronomy and Space Sciences
• /
• 제24권3호
• /
• pp.209-218
• /
• 2007

In this paper, we have presented the observational result for the photometric quality of main telescopes in Gimhae Astronomical Observatory. Also we performed the observation of searching new minor planets as competitive work in public observatories. The observation was carried out using 60cm telescope of Gimhae Astronomical Observatory on 2007 January 13. And, $Sch\ddot{u}ler$ BVI filters and 1K CCD camera (AP8p) were used. To define the quality of CCD photometry, we observed the region of well-known standard stars in the open cluster M67. From observed data, The transformation coefficients and airmass coefficients were obtained, and the accuracy of CCD photometry was investigated. From PSF photometry, we obtained the color-magnitude diagram of M67, and considered the useful magnitude limit and the physical properties of M67. This method can be successfully used to confirm the photometric quality of main telescope in public observatories. To investigate the detection possibility of unknown object as astroid, we observed the near area of the opposition in the ecliptic plane. And we discussed the result. Our result show that it can be possible to detect minor planets in solar system brighter than $V{\sim}18.3mag$. and it can carry out photometric study brighter than V 16mag. in Gimhae Astronomical Observatory. These results imply that the public observatories can make the research work.

• Journal of the Korean Association of Geographic Information Studies
• /
• 제9권3호
• /
• pp.82-92
• /
• 2006

As beaches throughout Korea have suffered great losses of sand due to artificial developments and meteorological phenomena, particularly typhoons, it is necessary to monitor beaches that are prone to erosion continuously, establish and enforce a comprehensive plan to attack coastal erosion with the object of the long-term management. However, debates and temporary measures, not based on accurate coastal zone surveys and analyses, have been established up to now. Therefore, with Haeundae sand beach as a case study, we proposed methods to collect accurate spatial data of the coastline and the sand beach through GPS survey. And we detected and analyzed topographic changes resulting from Typhoon Nabi quantitatively and qualitatively, by using GIS technique. Results showed a mean elevation of 1.95 m, a total area of 53,441 $m^2$, and a total volume of 104,639 $m^3$ after Typhoon Nabi. Mean elevation rose 0.06 m between the pre- and the post-typhoon surveys by a protective shore wall. However, strong winds and north-northeast surges brought by the typhoon caused erosion of the area and the volume, by 3,096 $m^2$ and 2,320 $m^3$. Accurate spatial databases of coastal zones based on integrated GPS GIS techniques and quantitative and qualitative analyses of topographical changes will help Korea develop systematic and effective countermeasures against coastal erosion.

• Journal of the Korea Convergence Society
• /
• 제11권11호
• /
• pp.9-17
• /
• 2020

In this paper, we proposed an SNS review analysis method based on deep learning for user tendency. The existing SNS review analysis method has a problem that does not reflect a variety of opinions on various interests because most are processed based on the highest weight. To solve this problem, the proposed method is to extract the user's personal tendency from the SNS review for food. It performs classification using the YOLOv3 model, and after performing a sentiment analysis through the BiLSTM model, it extracts various personal tendencies through a set algorithm. Experiments showed that the performance of Top-1 accuracy 88.61% and Top-5 90.13% for the YOLOv3 model, and 90.99% accuracy for the BiLSTM model. Also, it was shown that diversity of the individual tendencies in the SNS review classification through the heat map. In the future, it is expected to extract personal tendencies from various fields and be used for customized service or marketing.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• 제49권3호
• /
• pp.53-61
• /
• 2012

This paper proposes a real-time distance measurement system of high temperature and high speed target using infrared stereo camera. We construct an infrared stereo camera system that measure the difference between target and background temperatures for automatic target measurement. First, the proposed method detects target region based on target motion and intensity variation of local region using difference between target and background temperatures. Second, stereo matching by left and right target information is used to estimate disparity about real-time distance of target. In the proposed method using infrared stereo camera system, we compare distances in three dimension trajectory measuring instrument and in infrared stereo camera measurement. In this experiment from three video data, the result shows an average 9.68% distance error rate. The proposed method is suitable for distance and position measurement of varied targets using infrared stereo system.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• 제39권2호
• /
• pp.35-44
• /
• 2002

The translation and the rotation of camera occur global motion which affects all over the frame in video sequence. With the video sequences containing global motion, it is practically impossible to extract exact video objects and to calculate genuine object motions. Therefore, high compression ratio cannot be achieved due to the large motion vectors. This problem can be solved when the global motion compensated frames are used. The existing camera motion estimation methods for global motion compensation have a large amount of computations in common. In this paper, we propose a simple global motion estimation algorithm that consists of linear equations without any repetition. The algorithm uses information .of symmetric points in the frame of the video sequence. The discriminant conditions to distinguish regions belonging to distant view from foreground in the frame are presented. Only for the distant view satisfying the discriminant conditions, the linear equations for the panning, tilting, and zooming parameters are applied. From the experimental results using the MPEG test sequences, we can confirm that the proposed algorithm estimates correct global motion parameters. Moreover the real-time capability of the proposed technique can be applicable to many MPEG-4 and MPEG-7 related areas.