• Proceedings of the Korean Nuclear Society Conference
• /
• 2001.05a
• /
• pp.352.1-352
• /
• 2001

• Journal of the Korean Society of Radiology
• /
• v.81 no.1
• /
• pp.176-189
• /
• 2020

Purpose To evaluate the clinical efficacy of real-time sonoelastography (RTS) for the follow-up of congenital muscular torticollis, based on measurements of muscle elasticity. Materials and Methods Thirty-four infants (23 male, 11 female) with congenital sternocleidomastoid (SCM) muscle torticollis underwent ultrasonography and elastography between November 2012 and December 2014. We evaluated the thickness, morphology (mass-like, fusiform, or overall thickened shape), and echogenicity of the SCM muscle on grayscale images and color patterns (homogeneous blue, mixed green < 50% and ≥ 50%, and green to red) on elastography. Strain ratios were measured using Q-lab software. A clinician classified the degree of neck rotation and side flexion deficits using a 5-point grade system based on angles of neck rotation and side flexion. Correlations between the ultrasonography and clinical findings were evaluated by statistical analysis. Results Twenty-two infants had right and 12 had left SCM torticollis, respectively. Linear regression analysis showed that involved/contralateral SCM thickness differences, morphology, elasticity color scores, and strain ratios of the affected SCM muscles were significantly correlated with neck rotation and side flexion deficit scores (p < 0.05). The elasticity color score of the affected SCM muscle was the most significant factor. Conclusion RTS might provide a reliable means for evaluating and monitoring congenital muscular torticollis.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.12
• /
• pp.107-119
• /
• 1999

There is no authentic solution in a face detection problem though it is an important part of pattern recognition and has many diverse application fields. The reason is that there are many unpredictable deformations due to facial expressions, view point, rotation, scale, gender, age, etc. To overcome these problems, we propose an algorithm based on feature-based method, which is well known to be robust to these deformations. We detect a face by calculating a similarity between the formation of real face feature and candidate feature formation which consists of eyebrow, eye, nose, and mouth. In this paper, we use a steerable filter instead of general derivative edge detector in order to get more accurate feature components. We applied deformable template to verify the detected face, which overcome the weak point of feature-based method. Considering the low detection rate because of face detection method using whole input images, we design an adaptive skin-color filter which can be applicable to a diverse skin color, minimizing target area and processing time.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.195-197
• /
• 2010

본 논문은 기존 평행좌표를 이용하는 얼굴 영상 대신 극좌표계 변환을 이용한 얼굴 영상을 이용하여 회전에 강인한 얼굴인식 방법을 제안한다. 극좌표계 변환 방법은 얼굴의 중심부분의 한 점을 극으로 삼아 이 점을 기준으로 360도 각 방향으로 일정 길이만큼 얼굴 영상을 샘플링 하여 새로운 얼굴 영상을 제작하는 방법이다. 이 극좌표계 변환 방법을 이용해 재구성된 영상에 대해 회귀( regression )문제 해결을 위해 변형된 LDA인 LDAr(LDA for regression)을 이용하여 얼굴의 중심부분의한 점인 극을 중심으로 임의의 각도로 회전된 영상의 회전 정도를 추정하여 이를 정규화 시키는 방법을 통해 얼굴 인식의 인식률을 향상시키고자 한다. LDAr은 LDA의 기본개념인 각 클래스 간 떨어진 정도를 최대화하는 것이 목적으로 클래스간 분산과 클래스내 분산의 비율을 최대화 하는 방법을 응용하여 이를 회귀문제에 적용할 수 있게 변형을 한 것이다. 즉, LDAr은 목표값(target)의 차이가 큰 샘플들과 목표값의 차이가 작은 샘플들 간의 거리의 비율을 최대화 하는 것을 목적으로 하게 된다. 제안된 방법을 Yale데이터에 적용하여 임의의 각도로 회전시킨 영상에 대해 회전 각도를 정확히 찾아내는 것을 확인할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.749-752
• /
• 2018

깊은 신경망 모델을 이용한 차량 번호판 검출과 번호판 문자 인식 시스템을 제안한다. 차량 번호판 인식 시스템은 세 가지 종류의 깊은 신경망 모델로 구성된다. 기존의 영상처리 기반의 차량 번호판 검출과 문자 인식을 전부 신경망으로 대체함으로써 영상의 밝기, 회전, 왜곡 등의 변형에 강인한 성능을 얻을 수 있다. 차량 번호판 검출률은 99.3%, 문자 영역 검출률은 99%, 문자 인식률을 98.5%를 얻었다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.3
• /
• pp.188-194
• /
• 2008

We propose the new method for the traffic signs recognition that is one of the DAS(Driving assistance system) in the intelligent vehicle. Our approach estimates a varied degree by using a geometric method from the varied traffic signs in noise, rotation and size, and extracts the recognition symbol from the compensated traffic sign for a recognition by using the sequential color-based clustering. This proposed clustering method classify the traffic sign into the attention, regulation, indication, and auxiliary class. Also, The circular tracing method is used for the final traffic sign recognition. To evaluate the effectiveness of the proposed method, varied traffic signs were built. As a result, The proposed method show that the 95 % recognition rate for a single variation, and 93 % recognition rate for a mixed variation.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.23 no.1
• /
• pp.9-17
• /
• 2005

The objective of the study is to extract information about the road surfaces to be studied by analyzing asphalt concrete-paved road surface images photographed with a digital video camera. To analyze the accuracy of road surface information gained using a digital imagery processing method, it was compared and analyzed with the outcomes of control surveying. As a result, an average error of 0.0427 m in the X-axis direction, that of 0.0527 m in the Y-axis direction, and that of 0.1539 m in the Z-axis direction were found, good enough for mapping at a scale of 1:1,000 or less and GIS data. Besides, information on road surface assessment factors such as crack ratio, the amount of rutting and profile index was gained by analyzing processed digital imagery. This information made it possible to conduct road surface assessment by generating PSI and MCI. As quality digital image information has been gathered from roads and stored, important fundamental data on PMS (Pavement Management System) will become available in the future.

• Journal of the Korea Convergence Society
• /
• v.10 no.3
• /
• pp.39-47
• /
• 2019

In this paper, we proposed extracting modified Histogram of Oriented Gradients (HOG) features using background removal when tracking pedestrians in real time. HOG feature extraction has a problem of slow processing speed due to large computation amount. Background removal has been studied to improve computation reductions and tracking rate. Area removal was carried out using S and V channels in HSV color space to reduce feature extraction in unnecessary areas. The average S and V channels of the video were removed and the input video was totally dark, so that the object tracking may fail. Histogram equalization was performed to prevent this case. HOG features extracted from the removed region are reduced, and processing speed and tracking rates were improved by extracting clear HOG features. In this experiment, we experimented with videos with a large number of pedestrians or one pedestrian, complicated videos with backgrounds, and videos with severe tremors. Compared with the existing HOG-SVM method, the proposed method improved the processing speed by 41.84% and the error rate was reduced by 52.29%.

• Journal of the Korea Concrete Institute
• /
• v.14 no.6
• /
• pp.892-899
• /
• 2002

Among the methods for enhancement of load-carrying capacity on flexural concrete member, recently, a concept is being investigated which replaces the steel in a conventional reinforced concrete member with a fiber reinforced polymer(FRP) shell. This study focuses on modeling of the structural behavior of concrete surrounded with FRP shells in flexural bending members. A numerical model of fiber cross-sectional analysis is proposed to predict the stress and deformation state of the FRP shell and concrete. The stress-strain relationship of concrete confined by a FRP shell is formulated to be based on the constitutive law of concrete in multi-axial compressive stress state, in assuming that the compression response is dependent on the radial expansion of the concrete. To describe the FRP shell behavior, equivalent orthotropic properties of in-plane behavior from classical lamination theory are used. The present model is validated to compare with the experiments of 4-point bending tests of FRP shell concrete beam, and has well predicted the moment-curvature relationships of the members, axial and hoop strains in the section, and the enhancement of confinement effect in concrete surrounded by FRP shell.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.6 no.4
• /
• pp.291-295
• /
• 2005

In this paper, we propose a face recognition method using modified 2-D PCA. While the previous PCA method computes the covariance matrix by using one dimensional vectors, the 2-D PCA method computes the covariance matrix by directly using direct two dimensional image, and extracts the feature vectors by solving eigenvalue problem. The proposed method recognizes the faces by applying the modified 2-D PCA to face images and it gets linear transformation matrix using two covariance matrices. The experimental results indicates that the proposed method improved about $1\%$ and achieved more stability in recognition rate than conventional 2-D PCA.