• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.4
• /
• pp.82-92
• /
• 2006

In the field of image recognition, research on face recognition has recently attracted a lot of attention. The most important step in face recognition is automatic eye detection researched as a prerequisite stage. Existing eye detection methods for focusing on the frontal face can be mainly classified into two categories: active infrared(IR)-based approaches and image-based approaches. This paper proposes an eye region detection method in non-frontal faces. The proposed method is based on the edge--based method that shows the fastest computation time. To extract eye region in non-frontal faces, the method uses edge orientationhistogram of the global region of faces. The problem caused by some noise and unfavorable ambient light is solved by using proportion of width and height for local information and relationship between components for global information in approximately extracted region. In experimental results, the proposed method improved precision rates, as solving 3 problems caused by edge information and achieves a detection accuracy of 83.5% and a computational time of 0.5sec per face image using 300 face images provided by The Weizmann Institute of Science.

• Science of Emotion and Sensibility
• /
• v.13 no.3
• /
• pp.475-484
• /
• 2010

This study examined the influence of the SOA(stimulus onset asynchrony) between visual and auditory stimuli on the integration phenomenon of audio-visual senses. Within the stimulus integration phenomenon, the redundant target effect (the faster and more accurate response to the target stimulus when the target stimulus is presented with more than two modalities) and the visual dominance effect (the faster and more accurate response to a visual stimulus compared to an auditory stimulus) were examined as we composed a visual and auditory unimodal target condition and a multimodal target condition and then observed the response time and accuracy. Consequently, despite the change between visual and auditory stimuli SOA, there was no redundant target effect present. The auditory dominance effect appeared when the SOA between the two stimuli was over 100ms. Theses results imply that the redundant target effect is continuously maintained even when the SOA between two modal stimuli is altered, and also suggests that the behavioral results of superior information processing can only be deducted when the time difference between the onset of the auditory stimuli and the visual stimuli is approximately over 100ms.

• Korean Journal of Remote Sensing
• /
• v.33 no.6_2
• /
• pp.1061-1073
• /
• 2017

In this study, images were classified using convolutional neural network (CNN) - a deep learning technique - to investigate the feasibility of information production through a combination of artificial intelligence and spatial data. CNN determines kernel attributes based on a classification criterion and extracts information from feature maps to classify each pixel. In this study, a CNN network was constructed to classify materials with similar spectral characteristics and attribute information; this is difficult to achieve by conventional image processing techniques. A Compact Airborne Spectrographic Imager(CASI) and an Airborne Imaging Spectrometer for Application (AISA) were used on the following three study sites to test this method: Site 1, Site 2, and Site 3. Site 1 and Site 2 were agricultural lands covered in various crops,such as potato, onion, and rice. Site 3 included different buildings,such as single and joint residential facilities. Results indicated that the classification of crop species at Site 1 and Site 2 using this method yielded accuracies of 96% and 99%, respectively. At Site 3, the designation of buildings according to their purpose yielded an accuracy of 96%. Using a combination of existing land cover maps and spatial data, we propose a thematic environmental map that provides seasonal crop types and facilitates the creation of a land cover map.

• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.107-116
• /
• 2004

This paper introduces ISAAC (An Interface for Sentence Analysis & Abstraction with Cogitation) which provides an integrated user interface for sentence analysis. Into ISAAC, the various linguistic tools and resources are integrated. They are necessary for sentence analysis. Most of the tools and resources for sentence analysis are developed and accumulated independently. In the sentence analyzing with these tools and resources, it is difficult for sentence analyst to manage and control information which is taken on each step. In this respect, we have integrated the usable tools and resources, and made ISAAC to provide the consistent user oriented interface to each function. We have been able to divide sentence analysis process Into 14 steps. In ISAAC, these steps are processed by four individual modules $\cicled1$syntactic analysis of sentence,$\cicled2$retrieval of a root word,$\cicled3$searching category information in Roget s Thesaurus, and $\cicled4$searching category information in OfN(Ontology for Narratives). Therefore, in case of sentence analysis with ISAAC, the process of total 14 steps falls into 4 steps. This means that it is able to improve the performance of sentence analyst to the extent 3.5 times or more. Furthermore, ISAAC undertaking tedious transcription needed to process each step, we expect that ISAAC can help the analyst to maintain the accuracy of sentence analysis.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.403-410
• /
• 2004

Recently, studies of image analysis, as the preprocessing stage for medical image analysis or image retrieval, are actively carried out. This paper intends to propose a way of utilizing color components for image retrieval. For image retrieval, it is based on color components, and for analysis of color, CLCM (Color Level Co-occurrence Matrix) and statistical techniques are used. CLCM proposed in this paper is to project color components on 3D space through geometric rotate transform and then, to interpret distribution that is made from the spatial relationship. CLCM is 2D histogram that is made in color model, which is created through geometric rotate transform of a color model. In order to analyze it, a statistical technique is used. Like CLCM, GLCM (Gray Level Co-occurrence Matrix)[1] and Invariant Moment [2,3] use 2D distribution chart, which use basic statistical techniques in order to interpret 2D data. However, even though GLCM and Invariant Moment are optimized in each domain, it is impossible to perfectly interpret irregular data available on the spatial coordinates. That is, GLCM and Invariant Moment use only the basic statistical techniques so reliability of the extracted features is low. In order to interpret the spatial relationship and weight of data, this study has used Principal Component Analysis [4,5] that is used in multivariate statistics. In order to increase accuracy of data, it has proposed a way to project color components on 3D space, to rotate it and then, to extract features of data from all angles.

• The KIPS Transactions:PartC
• /
• v.15C no.5
• /
• pp.351-358
• /
• 2008

Recently, as network flooding attacks such as DoS/DDoS and Internet Worm have posed devastating threats to network services, rapid detection and proper response mechanisms are the major concern for secure and reliable network services. However, most of the current Intrusion Detection Systems(IDSs) focus on detail analysis of packet data, which results in late detection and a high system burden to cope with high-speed network environment. In this paper we propose a lightweight and fast detection mechanism for traffic flooding attacks. Firstly, we use SNMP MIB statistical data gathered from SNMP agents, instead of raw packet data from network links. Secondly, we use a machine learning approach based on a Support Vector Machine(SVM) for attack classification. Using MIB and SVM, we achieved fast detection with high accuracy, the minimization of the system burden, and extendibility for system deployment. The proposed mechanism is constructed in a hierarchical structure, which first distinguishes attack traffic from normal traffic and then determines the type of attacks in detail. Using MIB data sets collected from real experiments involving a DDoS attack, we validate the possibility of our approaches. It is shown that network attacks are detected with high efficiency, and classified with low false alarms.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.12 no.2
• /
• pp.13-29
• /
• 2001

The study examined the current status and the use of electronic publishing files to produce a bibliographic database. In particular . it examined the problems faced in the production of KoreaMed, an abstract database of Korean medical journals. The methodology of KoreaMed to utilize the computer files which was produced in the process of publication of a print journal is found to be very effective. It assures the accuracy of data, accelerates the input speeds, and reduces the input costs. However, such a project can not be accomplished to a satisfactory level without the cooperation of the publishers involved. It turns out that many small publishers and academic societies hardly have saved the electronic publishing files of previous issues. Besides, it is hard to maintain the right channel to receive the files continuously. The input and processing of special characters are very delicate problems. In addition, the diversity of layout and formats of journals, of the electronic publishing software used, and of the storage media, makes the utilization of the electronic publishing files a very complex process. In order to operate the KoreaMed system more efficiently by requiring the publishers to submit XML files which meets the standard of the KoreaMed, it is necessary to educate and train personnels of journal publishers for the management of electronic publishing files.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.20 no.12
• /
• pp.1325-1332
• /
• 2009

In this paper, we design a 2.4 GHz bio-radar system that can detect human heartbeat and respiration signals with small size and improved noise performance using single circular-polarized antenna and phase-locked loop. The demonstrated bio-radar system consists of single circular-polarized antenna with $90^{\circ}$ hybrid, low-noise amplifier, power amplifier, voltage-controlled oscillator with phase-locked loop circuits, quadrature demodulator and analog circuits. To realize compact size, the printed annular ring stacked microstrip antenna is integrated on the transceiver circuits, so its dimension is just $40\times40mm^2$. Also, to improve signal-to-noise-ratio performance by phase noise due to transmitter leakage signal, the phase-locked loop circuit is used. The measured results show that the heart rate and respiration accuracy was found to be very high for the distance of 50 cm without the additional digital signal processing.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.3
• /
• pp.155-160
• /
• 2018

The unmanned aerial vehicle (UAV) is used in various fields, such as land surveying, facility management, and disaster monitoring and restoration because it has low operational costs, fast data acquisition, and can generate a digital surface model (DSM). Recently, the UAV has been applied to process management in construction projects. Construction projects are widely distributed not only in urban areas but also in mountainous areas and rural areas where people are rarely in traffic or in vehicles. Projects range from a few hundred meters to several kilometers long. In order to perform a reconnaissance survey, a surveying method using a global positioning system (GPS) or a total station has mainly been used. However, these methods have a disadvantage in that a lot of time is required for data acquisition. This study's purpose is to evaluate the usability of a UAV DSM for surveying a construction area. Data was acquired using the UAV and a three-dimensional (3D) laser scanner, and the DSM of the construction site was created through data processing. The UAV DSM showed accuracy to within 30 cm based on the 3D laser scanner data, and a process comparison between the two work methods was able to present the usability of the UAV DSM in the field of construction surveying. Future utilization of the UAV DSM is expected to greatly improve the efficiency of work in construction projects.

• The KIPS Transactions:PartB
• /
• v.18B no.2
• /
• pp.57-66
• /
• 2011

To prevent cardiac diseases, quantifying cardiac function is important in routine clinical practice by analyzing blood volume and ejection fraction. These works have been manually performed and hence it requires computational costs and varies depending on the operator. In this paper, an automatic left ventricle segmentation algorithm is presented to segment left ventricle on cardiac magnetic resonance images. After coil sensitivity of MRI images is compensated, a K-mean clustering scheme is applied to segment blood area. A graph searching scheme is employed to correct the segmentation error from coil distortions and noises. Using cardiac MRI images from 38 subjects, the presented algorithm is performed to calculate blood volume and ejection fraction and compared with those of manual contouring by experts and GE MASS software. Based on the results, the presented algorithm achieves the average accuracy of 6.2mL${\pm}$5.6, 2.9mL${\pm}$3.0 and 2.1%${\pm}$1.5 in diastolic phase, systolic phase and ejection fraction, respectively. Moreover, the presented algorithm minimizes user intervention rates which was critical to automatize algorithms in previous researches.