• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.67-75
• /
• 2011

This paper presents a scale and rotation-invariant gait recognition method using R-transform, which is computed by projecting squared coefficients of Radon transform. Since R-transform is invariant to translation, rotation, and scaling, it particularly suitable for extracting object poses without camera calibration. Coefficients of R-transform are used to compute correlation, and the maximum correlation value determines the similarity between two gait images. The proposed method requires neither camera calibration nor geometric compensation, and as a result, it makes robust gait recognition possible without additional compensation for translation, rotation, and scaling.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.9 no.2
• /
• pp.93-102
• /
• 1991

This study aims to develop techniques for generating Digital Elevation Model(DEM) from SPOT Computer Compatible Tape(CCT) data, so as to present an effective way of generation of DEM for large area. As the first phase of extracting ground heights from SPOT stereo digital data, the bundle adjustment technique was used to determine the satellite exterior orientation parameters. Because SPOT data has the characteristics of multiple perspective projection, exterior orientation Parameters were modelled as a function of scan lines. In the second phase, a normalized cross correlation matching technique was applied to search for the conjugate pixels ill stereo pairs. The preliminary study showed that the matching window size of 13$\times$13 was adequate. After image coordinates of the conjugate pixels were determined by the matching technique, the ground coordinates of the corresponding pixels were calculated by the space intersection method. Then DEM was generated by interpolations. In addtion an algorithm for the elimination of abnormal elevation was developed and applied. The algorithm was very effective to improve the accuracy of the generated DEM.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.12
• /
• pp.49-60
• /
• 2012

In this paper, we propose a hardware design for correction of barrel distortion using the nearest coordinates in the corrected image. Because it applies the nearest distance on corrected image rather than adjacent distance on distorted image, the picture quality is improved by the image whole area, solve the staircase phenomenon in the exterior area. But, because of additional arithmetic operation using design of bilinear interpolation, required arithmetic operation is increased. Look up table(LUT) structure is proposed in order to solve this, coordinate rotation digital computer(CORDIC) algorithm is applied. The results of the synthesis using Design compiler, the design of implementing all processes of the interpolation method with the hardware is higher than the previous design about the throughput, In case of the rear camera, the design of using LUT and hardware together can reduce the size than the design of implementing all processes with the hardware.

• Journal of the Korea Society of Computer and Information
• /
• v.9 no.3
• /
• pp.79-85
• /
• 2004

In this paper, an iterative algorithm for stereo registration is proposed. The proposed algorithm is used for reconstructing virtual environment in a virtual studio. The second order error function is employed for stereo registration. The disparity information is obtained by minimizing the error function in an iterative manner. The variable window sizes are used to cope with the projection error and occlusion problem in the stereo vision. The depth information obtained from two pairs of stereo images is used for creating virtual environment by Z-Mixing. The experiment results proves the possibility of applying the proposed algorithm to virtual studio.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.280-281
• /
• 2008

본 논문은 큰 구조물의 3파인 영상 재구성을 위해서 획득한 2차원 영상에서 특징점을 찾아 선으로 조합한 후 선 길이 정보를 추출하는 방법을 제안한다. 거대한 구조물의 외곽선 길이 정보 추출을 위해서는 광각 카메라에 의한 영상을 획득한다. 영상에서의 외곽선들은 모델의 기울어진 정보와 형태, 모델의 크기 등을 결정하게 되는데 광각카메라 사용에 의하여 배럴왜곡, 원근투영왜곡 등이 발생한다. 외곽선 정보 추출의 순서는 먼저모델의 2차원영상을 획득하고 이로부터 왜곡이 보정된 그레이영상을 획득한다. 이 그레이영상에서 잡음을 제거하고 특징점을 찾기 위하여 SUSAN 알고리즘을 사용한다. SUSAN알고리즘 기법은 적은 계산량과 잡음에 매우 강한 장점이 있어서 영상에서의 특징점을 얻기 위한 효과적인 기법이다. 특징점을 3차원 벡터공간에서 맵핑시킨 후 X, Y, Z 좌표축으로 점과 선으로 나타내고 시작점과 끝점의 좌표를 이용하여 벡터 길이를 얻는다. 이러한 벡터 데이터와 3차원 영상 재구성을 위한 라이브러리인 OpenGL을 사용하여 3차원 공간에 거대한 구조물들을 재구성하는 소프트웨어를 개발하였다.

• Journal of Korea Multimedia Society
• /
• v.16 no.6
• /
• pp.782-794
• /
• 2013

This paper proposes the wafer position recognition algorithm using camera. First, for eliminating the image distortions caused by the illumination and the irregular camera position, the wafer image is restored as a circle through projective transformation. Next, we use edge detection algorithm to extract the wafer's edge and then apply Generalized Symmetry Transform(GST) to extract a circle. The GST evaluates symmetry between two points by combining a distance weight function, a phase weight function, and a logarithmic mapping of the points' intensities and detecting interest regions. Trough several experiments, we found out the proposed method is able to prevent the cleaning system and the wafer from damaging.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.10
• /
• pp.2102-2111
• /
• 1997

Hand written numeral is projected on the 3D space after pre-processing of inputs and it makes a index by tracking of numerals. It computes the distance between extracted every features. It is used by input part of recognition process from the statistical historgram of the normalization of data in order to adaptation from variation. One hundred unmeral patterns have used for making a standard feature map and 100 pattern for the recogintion experiment. The result of it, we have the recoginition rete is 93.5% based on thresholding is 0.20 and 97.5% based on 0.25.

• Journal of the Korean Society of Radiology
• /
• v.9 no.5
• /
• pp.301-306
• /
• 2015

X-ray can be applied to obtain a projection image of an object. It is not easy to obtain an high quality image for the object composed of low and high density materials. For the object with large difference in density, it is possible to realize high contrast image using images of low and high tube voltages and image processing. The plastic and metalic parts of the electronic components can be imaged by the dual energy technique which use low and high tube voltages and by processing pixel-by-pixel using visual C++. The contrast-enhanced image can be used to detect and observe defects within the electronic components.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.2
• /
• pp.469-478
• /
• 2010

This paper proposes the effective shape descriptor for 3D foot pose estimation. To reduce processing time, silhouette-based foot image database is built and meta information which involves the 3D pose of the foot is appended to the database. And we proposed a modified Centroid Contour Distance whose size of the feature space is small and performance of pose estimation is better than the others. In order to analyze performance of the descriptor, we evaluate time and spatial complexity with retrieval accuracy, and then compare with the previous methods. Experimental results show that the proposed descriptor is more effective than the previous methods on feature extraction time and pose estimation accuracy.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.5
• /
• pp.43-51
• /
• 2009

In this paper, we propose an efficient method of face retrieval by using PCA(principal component analysis) based features. The coarse-to-fine strategy is adopted to sort the retrieval results in the lower dimensional eigenface space and to rearrange candidates at high ranks in higher dimensional eigenface space. To evaluate similarity between a query face image and class reference image, we utilize the PD (projection distance), MQDF(modified quadratic distance function) and MED(minimum Euclidean distance). The experimental results show that the proposed method which rearrange the retrieval results incrementally by using projection distance is efficient for face image retrieval.