• Journal of Internet Computing and Services
• /
• v.15 no.4
• /
• pp.9-20
• /
• 2014

Making good predictions about the outcome of one's actions would seem to be essential in the context of social interaction and decision-making. This paper proposes a computational model for learning articulated motion patterns for action recognition, which mimics biological-inspired visual perception processing of human brain. Developed model of cortical architecture for the unsupervised learning of motion sequence, builds upon neurophysiological knowledge about the cortical sites such as IT, MT, STS and specific neuronal representation which contribute to articulated motion perception. Experiments show how the model automatically selects significant motion patterns as well as meaningful static snapshot categories from continuous video input. Such key poses correspond to articulated postures which are utilized in probing the trained network to impose implied motion perception from static views. We also present how sequence selective representations are learned in STS by fusing snapshot and motion input and how learned feedback connections enable making predictions about future input sequence. Network simulations demonstrate the computational capacity of the proposed model for motion recognition.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.71-77
• /
• 2014

In this paper, we propose an improved numeric character recognition method which can recognize numeric characters well under low-illuminated and shade-illuminated environment. The LN(Local Normalization) preprocessing method is used in order to enhance low-illuminated and shade-illuminated image quality. The reading area is detected using line segment information extracted from the illumination-normalized meter images, and then the three-phase procedures are performed for segmentation of numeric characters in the reading area. Finally, an efficient hybrid classifier is used to classify the segmented numeric characters. The proposed numeric character classifier is a combination of multi-layered feedforward neural network and template matching module. Robust heuristic rules are applied to classify the numeric characters. Experiments using meter image database were conducted. Meter image database was made using various kinds of meters under low-illuminated and shade-illuminated environment. The experimental results indicates the superiority of the proposed numeric character recognition method.

• Journal of KIISE:Computer Systems and Theory
• /
• v.26 no.10
• /
• pp.1185-1193
• /
• 1999

최적 스택 필터는 시그널 또는 영상의 임의의 특성 정보를 보존하고자 하는 요구조건에 의해 강제된 구조적 제약 하에서 최대의 잡음제거 효과를 얻을 수 있다. 그리고 임계치 분할 특성과 양의 부울 함수에 기반한 이진 영역에서의 처리 특성은 이 필터가 높은 병렬성을 갖고 있음을 보여준다. 본 논문에서는 두 개의 병렬 계산 모델 MCC(Mesh-Connected Computer)와 CCC(Cube-Connected Computer)에서 최적 스택 필터를 위한 1차원 병렬 알고리즘을 개발한다. 최적 스택 필터의 실행 시간은 주로 이진 median 연산에 의해 결정되고 본 논문에서 제안된 알고리즘은 선형 분리성에 의해 이 연산을 구현한다. 이를 바탕으로, M 레벨의 1-D 시그널의 길이가 L이고 윈도우 폭이 N이라고 가정할 때, 제안된 알고리즘은 {{{{root M times root M`` MCC에서 O(L sqrt{M}`) 시간에 그리고 M 개의 PE를 갖는 CCC에서 O(L log M)시간에 수행될 수 있다. 또한 잡음을 더욱 효과적으로 제거하기 위해 윈도우 폭 N을 증가시킬 때, 제안된 병렬 알고리즘의 계산 시간은 일정하게 유지됨을 보인다.Abstract An optimal stack filter achieves the maximum noise attenuation under the structural constraints imposed by the requirement of preserving certain signal or image features. And the filter provides a high parallelism due to the principles of threshold decomposition and binary processing based on positive Boolean functions(PBFs). In this paper, we develop an one-dimensional parallel algorithm for the optimal stack filter on two parallel computation models, MCC(Mesh-Connected Computer) and CCC(Cube-Connected Computer). The running time of the optimal stack filter depends mainly on the binary median operation and our algorithm realizes this operation by the linear separability. Based on this scheme, our parallel algorithm can be performed in {{{{O(L sqrt{M}`) MCC and inO(L log M) time on CCC with M PEs, when the length of M``-valued 1-D signal is L`` and window width is N`` Also, we show that the computation time of our parallel algorithm keeps constant when the window width N increases in order to achieve the best noise attenuation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05c
• /
• pp.1651-1654
• /
• 2003

이동 단말의 보급이 보편화됨에 따라 이동 객체의 위치 정보를 기반으로 사용자에게 사람이나 사물, 차량 등과 같은 이동 객체의 위치를 파악하여 그에 대한 정보를 제공해 주는 시스템이 필요로 하게 되었나 이러만 이동 객체관리 시스템에서는 계속적으로 위치 정보가 변화하는 이동 객체의 특성상 데이터의 빈번한 갱신이 일어나게 되고 DBMS에 명시적으로 저장되지 않은 위치 정보에 대해서도 보다 정확한 위치를 사용자에게 제공해 주어야 한다. 그러나 차량의 위치 추적과 같이 적용 개체가 차량에 한정된 경우 이동 경로가 도로상으로 제한되어 있으므로 이동 경로를 예측하기 힘든 사람과 같은 객체와는 특성이 나르나 따라서 차량 객체에 대해 보다 효과적인 서비스를 제공해 주기 위해서는 사람에 대한 위치 추적과는 다른 갱신 정책과 불확실한 위치의 추정 기법이 필요하다. 본 논문에서는 공간 데이터에 저장된 도로의 위상 정보와 차량의 속도 속성을 이용한 갱신 정책을 정하여 갱신 빈도수로 줄이고 도로 레이어의 위상 정보를 통해 불확실한 과거 및 미래의 위치로 추정하는 기법을 제안한다. 제안한 갱신 정책은 차량의 속도를 고려하여 현재의 위치에서 도로상의 교차점에 도착하는 시점의 위치를 예측하여 데이터의 갱신 시점으로 결정한다. 또한 불확실한 위치에 대한 추정은 이동하는 도회와 대응되는 위상 정보를 기반으로 차량의 이동 방향을 예측하 여 불확실한 미래의 위치를 결정할 수 있으며 명시적으로 저장되지 않은 과거 위치 정보의 검색에 대한 요청이 발생했을 경우 위상 정보를 이용하여 위치를 보정하고 사용자에게 보나 높은 정확성을 지닌 정보를 제공해 줄 수 있다.다. SQL Server 2000 그리고 LSF를 이용하였다. 그리고 구현 환경과 구성요소에 대한 수행 화면을 보였다.ool)을 사용하더라도 단순 다중 쓰레드 모델보다 더 많은 수의 클라이언트를 수용할 수 있는 장점이 있다. 이러한 결과를 바탕으로 본 연구팀에서 수행중인 MoIM-Messge서버의 네트워크 모듈로 다중 쓰레드 소켓폴링 모델을 적용하였다.n rate compared with conventional face recognition algorithms. 아니라 실내에서도 발생하고 있었다. 정량한 8개 화합물 각각과 총 휘발성 유기화합물의 스피어만 상관계수는 벤젠을 제외하고는 모두 유의하였다. 이중 톨루엔과 크실렌은 총 휘발성 유기화합물과 좋은 상관성 (톨루엔 0.76, 크실렌, 0.87)을 나타내었다. 이 연구는 톨루엔과 크실렌이 총 휘발성 유기화합물의 좋은 지표를 사용될 있고, 톨루엔, 에틸벤젠, 크실렌 등 많은 휘발성 유기화합물의 발생원은 실외뿐 아니라 실내에도 있음을 나타내고 있다.>10)의 $[^{18}F]F_2$를 얻었다. 결론: $^{18}O(p,n)^{18}F$ 핵반응을 이용하여 친전자성 방사성동위원소 $[^{18}F]F_2$를 생산하였다. 표적 챔버는 알루미늄으로 제작하였으며 본 연구에서 연구된 $[^{18}F]F_2$가스는 친핵성 치환반응으로 방사성동위원소를 도입하기 어려운 다양한 방사성의 약품개발에 유용하게 이용될 수 있을 것이다.었으나 움직임 보정 후 영상을 이용하여 비교한 경우, 결합능 변화가 선조체 영역에서 국한되어 나타나며

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.311-320
• /
• 2007

This paper presents vision-based 3D facial expression animation technique and system which provide the robust 3D head pose estimation and real-time facial expression control. Many researches of 3D face animation have been done for the facial expression control itself rather than focusing on 3D head motion tracking. However, the head motion tracking is one of critical issues to be solved for developing realistic facial animation. In this research, we developed an integrated animation system that includes 3D head motion tracking and facial expression control at the same time. The proposed system consists of three major phases: face detection, 3D head motion tracking, and facial expression control. For face detection, with the non-parametric HT skin color model and template matching, we can detect the facial region efficiently from video frame. For 3D head motion tracking, we exploit the cylindrical head model that is projected to the initial head motion template. Given an initial reference template of the face image and the corresponding head motion, the cylindrical head model is created and the foil head motion is traced based on the optical flow method. For the facial expression cloning we utilize the feature-based method, The major facial feature points are detected by the geometry of information of the face with template matching and traced by optical flow. Since the locations of varying feature points are composed of head motion and facial expression information, the animation parameters which describe the variation of the facial features are acquired from geometrically transformed frontal head pose image. Finally, the facial expression cloning is done by two fitting process. The control points of the 3D model are varied applying the animation parameters to the face model, and the non-feature points around the control points are changed by use of Radial Basis Function(RBF). From the experiment, we can prove that the developed vision-based animation system can create realistic facial animation with robust head pose estimation and facial variation from input video image.

• Journal of the Korea Society for Simulation
• /
• v.18 no.3
• /
• pp.73-82
• /
• 2009

Due to the many advantages including low price, low power consumption, and miniaturization, the CMOS camera has been utilized in many applications, including mobile phones, the automotive industry, medical sciences and sensoring, robotic controls, and research in the security field. In particular, the 360 degree omni-directional camera when utilized in multi-camera applications has displayed issues of software nature, interface communication management, delays, and a complicated image display control. Other issues include energy management problems, and miniaturization of a multi-camera in the hardware field. Traditional CMOS camera systems are comprised of an embedded system that consists of a high-performance MCU enabling a camera to send and receive images and a multi-layer system similar to an individual control system that consists of the camera's high performance Micro Controller Unit. We proposed the SL-AVS (Small Size/Low power Around-View System) to be able to control a camera while collecting image data using a high speed synchronization technique on the foundation of a single layer low performance MCU. It is an initial model of the omni-directional camera that takes images from a 360 view drawing from several CMOS camera utilizing a 110 degree view. We then connected a single MCU with four low-power CMOS cameras and implemented controls that include synchronization, controlling, and transmit/receive functions of individual camera compared with the traditional system. The synchronization of the respective cameras were controlled and then memorized by handling each interrupt through the MCU. We were able to improve the efficiency of data transmission that minimizes re-synchronization amongst a target, the CMOS camera, and the MCU. Further, depending on the choice of users, respective or groups of images divided into 4 domains were then provided with a target. We finally analyzed and compared the performance of the developed camera system including the synchronization and time of data transfer and image data loss, etc.

• Journal of the Korea Computer Graphics Society
• /
• v.17 no.3
• /
• pp.1-7
• /
• 2011

Recently, various researches have been proposed to accelerate GPU-based volume ray-casting. However, those researches may cause several problems such as bottleneck of data transmission between CPU and GPU, requirement of additional video memory for hierarchical structure and increase of processing time whenever opacity transfer function changes. In this paper, we propose an efficient GPU-based empty space skipping technique to solve these problems. We store maximum density in a brick of volume dataset on a vertex element. Then we delete vertices regarded as transparent one by opacity transfer function in geometry shader. Remaining vertices are used to generate bounding boxes of non-transparent area that helps the ray to traverse efficiently. Although these vertices are independent on viewing condition they need to be reproduced when opacity transfer function changes. Our technique provides fast generation of opaque vertices for interactive processing since the generation stage of the opaque vertices is running in GPU pipeline. The rendering results of our algorithm are identical to the that of general GPU ray-casting, but the performance can be up to more than 10 times faster.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.2
• /
• pp.40-46
• /
• 2011

This paper proposes a real-time face detection and tracking system that uses neural oscillators which can be applied to access regulation system or control systems of user authentication as well as a new algorithm. We study a way to track faces using the neural oscillatory network which imitates the artificial neural net of information handing ability of human and animals, and biological movement characteristic of a singular neuron. The system that is suggested in this paper can broadly be broken into two stages of process. The first stage is the process of face extraction, which involves the acquisition of real-time RGB24bit color video delivering with the use of a cheap webcam. LEGION(Locally Excitatory Globally Inhibitory)algorithm is suggested as the face extraction method to be preceded for face tracking. The second stage is a method for face tracking by discovering the leader neuron that has the greatest connection strength amongst neighbor neuron of extracted face area. Along with the suggested method, the necessary element of face track such as stability as well as scale problem can be resolved.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.3C
• /
• pp.374-386
• /
• 2004

The mammogram provides the way to observe detailed internal organization of breasts to radiologists for the early detection. This paper is mainly focused on efficiently detecting the Microcalcification's Region Of Interest(ROI)s. Breast cancers can be caused from either microcalcifications or masses. Microcalcifications are appeared in a digital mammogram as tiny dots that have a little higher gray levels than their surrounding pixels. We can roughly determine the area which possibly contain microcalifications. In general, it is very challenging to find all the microcalcifications in a digital mammogram, because they are similar to some tissue parts of a breast. To efficiently detect microcalcifications ROI, we used four sequential processes; preprocessing for breast area detection, modified multilevel thresholding, ROI selection using simple thresholding filters and final ROI selection with two stages of neural networks. The filtering process with boundary conditions removes easily-distinguishable tissues while keeping all microcalcifications so that it cleans the thresholded mammogram images and speeds up the later processing by the average of 86％. The first neural network shows the average of 96.66％ recognition rate. The second neural network performs better by showing the average recognition rate 98.26％. By removing all tissues while keeping microcalcifications as much as possible, the next parts of a CAD system for detecting breast cancers can become much simpler.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.46 no.6
• /
• pp.28-37
• /
• 2009

In this paper, we propose an obstacle localization method using a road feature based on a V-disparity map binarized by a maximum frequency value. In a conventional method, the detection performance is severely affected by the size, number and type of obstacles. It's especially difficult to extract a large obstacle or a continuous obstacle like a median strip. So we use a road feature as a new decision standard to localize obstacles irrespective of external environments. A road feature is proper to be a new decision standard because it keeps its rough feature very well in V-disparity under environments where many obstacles exist. And first of all, we create a binary V-disparity map using a maximum frequency value to extract a road feature easily. And then we compare the binary V-disparity map with a median value to remove noises. Finally, we use a linear interpolation for rows which have no value. Comparing this road feature with each column value in disparity map, we can localize obstacles robustly. We also propose a post-processing technique to remove noises made in obstacle localization stage. The results in real road tests show that the proposed algorithm has a better performance than a conventional method.