• 대한원격탐사학회지
• /
• 제22권5호
• /
• pp.445-449
• /
• 2006

Diffuse pollution has been considering as a major source of the quality deterioration of water resources. The establishment of riparian vegetation strips or buffers along those areas of water bodies is used to reduce the threat of diffuse pollution. Remote sensing offers a means by which critical areas could be identified, so that subsequent action toward the establishment of riparian zones can be taken. On the behalf of KOMPSAT-2 satellite imagery as a high resolution spatial data, Landsat TM satellite data are used to aquire the land cover for the riparian buffers studied. This investigation aims to assess the riparian buffers established on the upper Geum river as a pollution mitigation. Through comparing the delineation of riparian buffer zones developed with the existing zones established by the government, we can find the critical distortion points of the existing riparian buffer zone.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권9호
• /
• pp.3243-3257
• /
• 2021

Deep neural networks provide excellent performance in pattern recognition, audio classification, and image recognition. It is important that they accurately recognize input data, particularly when they are used in autonomous vehicles or for medical services. In this study, we propose a data correction method for increasing the accuracy of an unknown classifier by modifying the input data without changing the classifier. This method modifies the input data slightly so that the unknown classifier will correctly recognize the input data. It is an ensemble method that has the characteristic of transferability to an unknown classifier by generating corrected data that are correctly recognized by several classifiers that are known in advance. We tested our method using MNIST and CIFAR-10 as experimental data. The experimental results exhibit that the accuracy of the unknown classifier is a 100% correct recognition rate owing to the data correction generated by the proposed method, which minimizes data distortion to maintain the data's recognizability by humans.

• 전자통신동향분석
• /
• 제37권5호
• /
• pp.22-32
• /
• 2022

Optical character recognition is a primary technology required in different fields, including digitizing archival documents, industrial automation, automatic driving, video analytics, medicine, and financial institution, among others. It was created in 1928 using pattern matching, but with the advent of artificial intelligence, it has since evolved into a high-performance character recognition technology. Recently, methods for detecting curved text and characters existing in a complicated background are being studied. Additionally, deep learning models are being developed in a way to recognize texts in various orientations and resolutions, perspective distortion, illumination reflection and partially occluded text, complex font characters, and special characters and artistic text among others. This report reviews the recent deep learning-based text detection and recognition methods and their various applications.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 추계학술발표대회
• /
• pp.1166-1169
• /
• 2011

In this paper, we design a Circle dot Code, In our scheme, we design a dot patterns for increasing maximum capacity and also for increasing robustness to Affine Transformation. Our code Can be extended according number of data circle. We use three data circle vision code. In this type code, after acquiring camera images for the Circle dot Codes, and perform error correction decoding using four position symbols and six CRC symbols. We perform graph based dot code analysis which determines the topological distance between dot pixels. Our code can be bridged the real world and ubiquitous computing environment.

• 한국재료학회지
• /
• 제22권2호
• /
• pp.82-85
• /
• 2012

The effect of the alloy systems Al-Mg alloy and Al-Si alloy in this study on the characteristics of die-casting were investigated using solidification simulation software (MAGMAsoft). Generally, it is well known that the casting characteristics of Al-Mg based alloys, such as the fluidity, feedability and die soldering behaviors, are inferior to those of Al-Si based alloys. However, the simulation results of this study showed that the filling pattern behaviors of both the Al-Mg and Al-Si alloys were found to be very similar, whereas the Al-Mg alloy had higher residual stress and greater distortion as generated due to solidification with a larger amount of volumetric shrinkage compared to the Al-Si alloy. The Al-Mg alloy exhibited very high relative numbers of stress-concentrated regions, especially near the rib areas. Owing to the residual stress and distortion, defects were evident in the Al-Mg alloy in the areas predicted by the simulation. However, there were no visible defects observed in the Al-Si alloy. This suggests that an adequate die temperature and casting process optimization are necessary to control and minimize defects when die casting the Al-Mg alloy. A Tatur test was conducted to observe the shrinkage characteristics of the aluminum alloys. The result showed that hot tearing or hot cracking occurred during the solidification of the Al-Mg alloy due to the large amount of shrinkage.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• 제28권3호
• /
• pp.222-228
• /
• 2006

Various methods have been used in the past to indirectly analyze the craniofacial region. Among these, the lateral and posterior-anterior cephalometircs are used for the evaluation of the dentofacial deformities. However, cephalometircs create inaccuracies because of the inherent enlargement and distortion of the image. The interpretation of cephalometric films is also problematic: the number of anatomic landmarks that can be identified accurately is limited, and the overlap of structures on a radiograph making locating these landmarks difficult. To overcome these problems, computed tomography(CT) has been recommended as an useful modality in the diagnosis, surgical planning, and follow-up of craniofacial anomalies. There is no significant enlargement or distortion of the image, overlap of structure, or tracing error. And the number of anatomic landmarks is vast. The purpose of this study was to examine the orbit and midfacial region using Occlusal Maxillary CT, consisted of slices parallel to the occlusal plane. Based on these CT scan, we provide the data that could be applied to monitor an individual patient's skeletal pattern and the guide to the maxillary osteotomy.

• 방송공학회논문지
• /
• 제17권2호
• /
• pp.223-236
• /
• 2012

본 논문에서는 인간 인지 기반 비디오 코딩을 위한 비디오 처리 방법을 개발한다. 제안하는 방법은 율-왜곡(rate-distortion) 최적화의 영향뿐만 아니라 제한적인 시, 공간 해상도, 지역적인 움직임 이력(history), visual saliency에 의한 인간 시각 인지를 고려한다. 이러한 인간의 인지적인 효과들을 고려하기 위하여 본 논문에서는 움직임 패턴을 모델링하고 Hedge 알고리듬을 사용하여 움직임 패턴을 결정하는 기법을 개발한다. 그 다음, 제안한 움직임 패턴과 기존의 visual saliency와의 결합을 통하여 인간 시각 인지 모델을 수립한다. 제안된 인간 시각 인지 모델을 구현하기 위하여 기존의 foveation filtering 방법을 확장한다. 시각적 자극이 덜한 지역만을 부드럽게(smoothing)하는 기존의 foveation filtering 기법과 비교하여 제안하는 foveation filtering 기법은 인간 시각 인지 모델에 따라 지역적으로 부드럽게 또는 지역적 특성을 향상시킴으로써, 시각적 자극이 덜한 지역에서 줄여진 대역폭을 효과적으로 시각적 자극이 큰 지역에서 사용하도록 이동 시킬 수 있는 장점이 있다. 제안된 방법의 성능은 전반적인 비디오 화질을 만족할 뿐만 아니라 인간이 인지하는 화질의 품질을 12%~44% 향상시킨다.

• 한국위성정보통신학회논문지
• /
• 제1권2호
• /
• pp.32-37
• /
• 2006

한국전자통신연구원은 2008년 말에 발사될 예정인 통신해양위성에 탑재될 Ka대역 안테나서브시스템을 개발하고 있다. Ka대역 통신용 안테나 서브시스템은 위성체의 동,서 판넬에 각각 하나씩 구성되어 있다. 이를 추진하기 위하여 한국전자통신연구원은 현제 대한항공(주)과 공동으로 통신위성 안테나 서브시스템을 설계하고 있다. 본 논문은 이득 변화 등과 같은 안테나 서브시스템 성능 규격을 검증하기 위하여 Ka 대역 반사판 포인팅 에러분석에 대하여 기술한다. 수행된 분석은 열변형에 의한 반사판 표면 변형 데이터 이며 이를 Ticra로 빔패턴의 변화를 확인하였다.

• 대한의용생체공학회:의공학회지
• /
• 제28권5호
• /
• pp.601-608
• /
• 2007

2 Dimensional Gel Electrophoresis(2DGE) is an essentialmethodology for analysis on the expression of various proteins. For example, information for the location, mass, expression, size and shape of the proteins obtained by 2DGE can be used for diagnosis, prognosis and biological progress by comparison of patients with the normal persons. Protein spot matching for this purpose is comparative analysis of protein expression pattern for the 2DGE images generated under different conditions. However, visual analysis of protein spots which are more than several hundreds included in a 2DGE image requires long time and heavy effort. Furthermore, geometrical distortion makes the spot matching for the same protein harder. In this paper, an iterative algorithm is introduced for more efficient spot matching. Proposed method is first performing global matching step, which reduces the geometrical difference between the landmarks and the spot to be matched. Thus, movement for a spot is defined by a weighted sum of the movement of the landmark spots. Weight for the summation is defined by the inverse of the distance from the spots to the landmarks. This movement is iteratively performed until the total sum of the difference between the corresponding landmarks is larger than a pre-selected value. Due to local distortion generally occurred in 2DGE images, there are many regions in whichmany spot pairs are miss-matched. In the second stage, the same spot matching algorithm is applied to such local regions with the additional landmarks for those regions. In other words, the same method is applied with the expanded landmark set to which additional landmarks are added. Our proposed algorithm for spot matching empirically proved reliable analysis of protein separation image by producing higher accuracy.

• 한국운동역학회지
• /
• 제23권4호
• /
• pp.369-376
• /
• 2013

The purposes of this study were to assess dynamic stability toward pelvis-spine column distortion during running and to compare the typical three-dimensional angular kinematics of the trunk motion; cervical, thoracic, lumbar segment spine and the pelvis from the multi-segmental spine model between exercise group and non-exercise group. Subjects were recruited as exercise healthy women on regular basis (group A, n=10) and non-exercise idiopathic scoliosis women (group B, n=10). Data was collected by using a vicon motion capture system (MX-T40, UK). The pelvis, spine segments column and lower limbs analysiaed through the 3D kinematic angular ROM pattern. There were significant differences in the time-space variables, the rotation motion of knee joint in lower limbs and the pelvis variables; obliquity in side bending, inter/outer rotation in twisting during running leg movement. There were significant differences in the spinal column that is lower-lumbar, upper-lumbar, upper-thoracic, mid-upper thoracic, mid-lower thoracic, lower thoracic and cervical spine at inclination, lateral bending and twist rotation between group A and group B (<.05, <.01 and <.001). As a results, group B had more restrictive motion than group A in the spinal column and leg movement behaved like a 'shock absorber". And the number of asymmetry index (AI) showed that group B was much lager unbalance than group A. In conclusion, non-exercise group was known to much more influence the dynamic stability of equilibrium for bilateral balance. These finding suggested that dynamic stability aimed at increasing balance of the trunk ROM must involve methods and strategies intended to reduce left/right asymmetry and the exercise injury.