• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.9
• /
• pp.930-935
• /
• 2014

A Gabor filter is a linear filter used for edge detectionas frequency and orientation representations of Gabor filters are similar to those of the human visual system. In this thesis, we propose a pedestrian detection algorithm using a Gabor filter bank. In order to extract the features of the pedestrian, we use various image processing algorithms and data structure algorithms. First, color image segmentation is performed to consider the information of the RGB color space. Second, histogram equalization is performed to enhance the brightness of the input images. Third, convolution is performed between a Gabor filter bank and the enhanced images. Fourth, statistical values are calculated by using the integral image (summed area table) method. The calculated statistical values are used for the feature matrix of the pedestrian area. To evaluate the proposed algorithm, the INRIA pedestrian database and SVM (Support Vector Machine) are used, and we compare the proposed algorithm and the HOG (Histogram of Oriented Gradient) pedestrian detector, presentlyreferred to as the methodology of pedestrian detection algorithm. The experimental results show that the proposed algorithm is more accurate compared to the HOG pedestrian detector.

• ETRI Journal
• /
• v.34 no.4
• /
• pp.542-552
• /
• 2012

In this paper, a gaze estimation method is proposed for use with a large-sized display at a distance. Our research has the following four novelties: this is the first study on gaze-tracking for large-sized displays and large Z (viewing) distances; our gaze-tracking accuracy is not affected by head movements since the proposed method tracks the head by using a near infrared camera and an infrared light-emitting diode; the threshold for local binarization of the pupil area is adaptively determined by using a p-tile method based on circular edge detection irrespective of the eyelid or eyelash shadows; and accurate gaze position is calculated by using two support vector regressions without complicated calibrations for the camera, display, and user's eyes, in which the gaze positions and head movements are used as feature values. The root mean square error of gaze detection is calculated as $0.79^{\circ}$ for a 30-inch screen.

• The Bulletin of The Korean Astronomical Society
• /
• v.37 no.1
• /
• pp.40.1-40.1
• /
• 2012

In the hierarchical universe, galaxy merger is predicted to be frequent, and thus it is an important element for understanding galaxy evolution. In particular, star formation is greatly enhanced during the merger. The aim of this study is to understand the position and rate change of star formation caused by equal-mass edge-on mergers. We use the GADGET2- N-body/SPH code, and fully consider gas cooling, star formation, and supernova feedback. We show the star formation rate (SFR), and the magnitude and color evolution of the merger remnants for 18 different configurations varying orbit elements and inclinations of host galaxies against orbit planes. Then we construct the mock images of the remnants and investigate on how equal-mass galaxy merger affects the SFR and color/magnitude evolution while considering dust reddening. We conclude that over 90% mass of SF in equal-mass merger is in the central region. SF in tidal feature involves a small fraction of new stars and thus is difficult to detect unless deep imaging is performed. Around 55 ${\pm}$ 5 percent of gas turns into stars until the final coalescence which typically corresponds to 0.8, 1.2, and 2.5 Gyr for direct, parabolic, and elliptical orbit, respectively. This result is roughly consistent with Cox et al. 2000. We plan to implement this result into semi-analytic model of galaxy formation. Caveats and future work on merging conditions are discussed.

• Journal of the Korea Society of Computer and Information
• /
• v.9 no.4 s.32
• /
• pp.85-91
• /
• 2004

The use of gestures provides an attractive alternate to cumbersome interface devices for human-computer interaction. This has motivated a very active research area concerned with computer vision-based analysis and interpretation of hand gestures The most important issues in gesture recognition are the simplification of algorithm and the reduction of processing time. The mathematical morphology based on geometrical set theory is best used to perform the processing. The key idea of proposed algorithm is to track a trajectory of center points in primitive elements extracted by morphological shape decomposition. The trajectory of morphological center points includes the information on shape orientation. Based on this characteristic we proposed the morphological gesture sequence recognition algorithm using feature vectors calculated to the trajectory of morphological center points. Through the experiment, we demonstrated the efficiency of proposed algorithm.

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.95-99
• /
• 2014

본 논문에서는 최근 급속히 증가하여 사회적 이슈가 되고 있는 SMS 스팸 필터링을 위한 듀얼 SMS 스팸필터링 기법을 제안한다. 지속적으로 증가하고 새롭게 변형되는 SMS 문자 필터링을 위해서는 패턴 및 스팸 단어 사전을 통한 필터링은 많은 수작업을 요구하여 부적합하다. 그리하여 기계 학습을 이용한 자동화 시스템 구축이 요구되고 있으며, 효과적인 기계 학습을 위해서는 자질 선택과 자질의 가중치 책정 방법이 중요하다. 하지만 SMS 문자 특성상 문장들이 짧기 때문에 출현하는 자질의 수가 적어 분류의 어려움을 겪게 된다. 이 같은 문제를 개선하기 위하여 본 논문에서는 슬라이딩 윈도우 기반 N-gram 확장을 통해 자질을 확장하고, 확장된 자질로 그래프를 구축하여 얕은 구조적 특징을 표현한다. 학습 데이터에 출현한 N-gram 자질을 정점(Vertex)으로, 자질의 출현 빈도를 그래프의 간선(Edge)의 가중치로 설정하여 햄(HAM)과 스팸(SPAM) 그래프를 각각 구성한다. 이렇게 구성된 그래프를 바탕으로 노드의 중요도와 간선의 가중치를 활용하여 최종적인 자질의 가중치를 결정한다. 입력 문자가 도착하면 스팸과 햄의 그래프를 각각 이용하여 입력 문자의 2개의 자질 벡터(Vector)를 생성한다. 생성된 자질 벡터를 지지 벡터 기계(Support Vector Machine)를 이용하여 각 SVM 확률 값(Probability Score)을 얻어 스팸 여부를 결정한다. 3가지의 실험환경에서 바이그램 자질과 이진 가중치를 사용한 기본 시스템보다 F1-Score의 약 최대 2.7%, 최소 0.5%까지 향상되었으며, 결과적으로 평균 약 1.35%의 성능 향상을 얻을 수 있었다.

• Proceedings of the KIEE Conference
• /
• 1995.11a
• /
• pp.502-504
• /
• 1995

In video image compression, it is important to extract the exact notion information from image sequence in order to perform the data compression, the field rate conversion, and the motion compensated interpolation effectively. It is well known that the location of the smallest sum of absolute difference(SAD) does not always give the true motion vector(MV) since the MV obtained via full block search is often corrupted by noise. In this paper, we first classifies the input blocks into 3 categories : the background, the shade-motion, and the edge-motion. According to the characteristics of the classified blocks, multiple locations of relatively small SAD are searched with an adaptive search window by using the proposed method. The proposed method picks MVs among those candidates by using temporal correlation. Since temporal correlation reveals the noise level in a particular region of the video image sequence, we are able to reduce the search are very effectively.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.3
• /
• pp.1174-1180
• /
• 2015

We investigate in this paper the radiated electromagnetic waves together with the discharge characteristics of Trichel pulse of negative DC corona discharge in air in pin-to-plate and wire-to-plate configurations. The feature of the current pulse and the frequency spectrum of the electromagnetic radiations were measured under various pressures and gas gaps. The results show that the repetition frequency and the amplitude of Trichel pulse current depend on the discharge conditions, but the rising time of the pulse relates only to the radius of needle or wire and keeps constant even if the other conditions (including the discharge current, the gas gap and the gas pressure) change. There exists the characterized spectrum of electromagnetic waves from negative corona discharge in Trichel pulse regime. These characterized radiations do not change their frequency at a given cathode geometry even if the averaged current, the gas gap or the air pressure changes, but the amplitude of radiations changes accordingly. The characterized electromagnetic radiations from Trichel pulse corona relate to the formation or the rising edge of current pulse. It confirms that the characterized radiations from Trichel pulse supply information of discharge system and provide a potential method for detecting charged targets.

• Journal of Korea Multimedia Society
• /
• v.16 no.5
• /
• pp.601-609
• /
• 2013

One of the most serious factors constraining the next generation cellular mobile consumer communication systems will be the severe co-channel interference experienced at the cell edge. Such a capacity-degrading impairment combined with the limited available spectrum resource makes it essential to develop more spectrally efficient solutions to enhance the system performance and enrich the mobile user's application services. This paper proposes a unique hybrid method of frequency hopping (FH) and subcarrier-reuse-partitioning that can maximize the system capacity by efficiently utilizing the available spectrum while at the same time reduce the co-channel interference effect. The main feature of the proposed method is that it applies an optimal combination of different frequency reuse factors (FRF) and FH-subcarrier allocation patterns into the partitioned cell regions. From the simulation results, it is shown that the proposed method can achieve the optimum number of subcarrier subsets according to the frequency-reuse distance and results in better performance than the fixed FRF methods, for a given partitioning arrangement. The results are presented in the context of both blocking probability and BER performances. It will also be shown how the proposed scheme is well suited to FH-OFDMA based cellular systems aiming at low co-channel interference performance and optimized number of subcarriers.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.6
• /
• pp.464-468
• /
• 2009

In this paper we propose an image-based approach, which is different from the traditional flow cytometric method to detect shape of apoptosis cells. This method can overcome the defects of cytometry and give precise recognition of apoptosis cells. In this work K-means clustering was used to do the rough segmentation and an active contour model, called 'snake' was used to do the precise edge detection. And then some features were extracted including physical feature, shape descriptor and texture features of the apoptosis cells. Finally a Mahalanobis distance classifier classifies the segmentation images as apoptosis and non-apoptosis cell.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.7
• /
• pp.813-816
• /
• 2005

Ear detection is an important part of an non-invasive ear recognition system. In this paper we propose human ear detection from side face images. The proposed method is made by imitating the human recognition process using feature information and color information. First, we search face candidate area in an input image by using 'skin-color model' and try to find an ear area based on edge information. Then, to verify whether it is the ear area or not, we use the SVM (Support Vector Machine) based on a statistical theory. The method shows high detection ratio in indoors environment with stable illumination.