• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.12
• /
• pp.8649-8653
• /
• 2015

A number of video indexing and retrieval algorithms have been proposed to manage large video databases efficiently. The video similarity measure is one of most important technical factor for video content management system. In this paper, we propose the luminance characteristics model to measure the video similarity efficiently. Most algorithms for video indexing have been commonly used histograms, edges, or motion features, whereas in this paper, the proposed algorithm is employed an efficient similarity measure using the luminance projection. To index the video sequences effectively and to reduce the computational complexity, we calculate video similarity using the key frames extracted by the cumulative measure, and compare the set of key frames using the modified Hausdorff distance. Experimental results show that the proposed luminance projection model yields the remarkable improved accuracy and performance than the conventional algorithm such as the histogram comparison method, with the low computational complexity.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.29 no.4
• /
• pp.30-36
• /
• 2015

The principle of an illumination and projection system including LED light sources for a spot type stage lighting system was presented, and its optical system was designed with optimizing parameters by the analytical methods. A dichroic mirror incorporated with an illumination system to optimizing LED source positions and to obtain the compact system. The projection system was optimized with specific constraints such as a chromatic aberration, distortion aberration and angle of incidence angles. Optimized design system has a beam angle from $10^{\circ}$ to $45^{\circ}$, and its illuminance was 4,500lux at distance of 6m on the work plane.

• Journal of Korea Multimedia Society
• /
• v.8 no.12
• /
• pp.1572-1580
• /
• 2005

The common requirements for watermarking are usually invisibility, robustness, and capacity. We proposed the watermarking for 3D mesh model based on projection onto convex sets for invisibility and robustness among requirements. As such, a 3D mesh model is projected alternatively onto two convex sets until it converge a point. The robustness convex set is designed to be able to embed watermark into the distance distribution of vertices. The invisibility convex set is designed for the watermark to be invisible based on the limit range of vertex movement. The watermark can be extracted using the decision values and index that the watermark was embedded with. Experimental results verify that the watermarked mesh model has both robustness against mesh simplification, cropping, affine transformations, and vertex randomization and invisibility.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.715-717
• /
• 2004

This paper proposes a new reconstruction method of high-resolution facial image from a low-resolution facial image based on a recursive error back-projection of top-down machine learning. A face is represented by a linear combination of prototypes of shape and texture. With the shape and texture information about the pixels in a given low-resolution facial image, we can estimate optimal coefficients for a linear combination of prototypes of shape and those of texture by solving least square minimization. Then high-resolution facial image can be obtained by using the optimal coefficients for linear combination of the high-resolution prototypes, In addition to, a recursive error back-projection is applied to improve the accuracy of synthesized high-resolution facial image. The encouraging results of the proposed method show that our method can be used to improve the performance of the face recognition by applying our method to reconstruct high-resolution facial images from low-resolution one captured at a distance.

• Kyungpook Mathematical Journal
• /
• v.64 no.1
• /
• pp.69-94
• /
• 2024

In this paper, we introduce an inertial self-adaptive projection method using Bregman distance techniques for solving pseudomonotone equilibrium problems in reflexive Banach spaces. The algorithm requires only one projection onto the feasible set without any Lipschitz-like condition on the bifunction. Using this method, a strong convergence theorem is proved under some mild conditions. Furthermore, we include numerical experiments to illustrate the behaviour of the new algorithm with respect to the Bregman function and other algorithms in the literature.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1411-1414
• /
• 1997

It is essential to obtain a distane informaion in order to completely execute assembly tasks such as a grasping and an insertion. In this paper, we propose a method estimating a measurement distance from a sensor to an object through using the omni-directional image sensing system for assembly(OISSA) and show its features and feasibility by a computer simulation. The method, utilizing a forwarded motion stereo technique, is simple to search the corresponding points and possible to immediatiely obtain a three-dimensional 2.pi.-shape information.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11a
• /
• pp.718-720
• /
• 2005

반짝이는 물체를 촬영하면 이미지에 하이라이트(highlight)와 반짝거림(specularity)이 발생한다. 하이라이트가 발생한 이미지에서 하이라이트를 제거하고 원색으로 복원하는 방법 중에 하나가 하이라이트 색 복원(inpainting)이다. 하이라이트 색을 복원하는 과정은 다음 두 단계로 구성된다. 첫 단계로 하이라이트의 위치를 알고 있다고 가정하aus 하이라이트의 주변 영역을 찾고 CL-projection을 이용해 주변 영역의 색에서 하이라이트나 반짝거림의 영향을 제거한다. 두 번째 단계로 하이라이트 주변 영역의 색을 기반으로 upper mean을 이용하여 distance transform을 수행한다. Upper mean을 이용한 distance transform의 가장 큰 장점은 하이라이트 주변을 보정하고 그 정보를 이용하기 때문에 하이라이트 색을 복원할 뿐만 아니라 반짝거림에 대한 보정도 된다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05b
• /
• pp.591-594
• /
• 2004

In this paper, The identity distinction of the moving objects using distance among hue normalization levels was proposed. Moving objects are detected by using difference image method and integral projection method to background image and objects image only with hue area. Hue information of the detected moving area are normalized by 24 levels from 0$^{\circ}$ to 360$^{\circ}$. A distance in between normalized levels with a hue distribution chart of the normalized moving objects is used for the identity distinction feature parameters of the moving objects. To examine proposed method in this paper, image of moving cars are obtained by setting up three cameras at different places every 1 km on outer motorway. The simulation results of identity distinction show that it is possible to distinct the identity a distance in between normalization levels of a hue distribution chart without background.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2599-2613
• /
• 2015

Multi-index hashing (MIH) is the state-of-the-art method for indexing binary codes, as it di-vides long codes into substrings and builds multiple hash tables. However, MIH is based on the dataset codes uniform distribution assumption, and will lose efficiency in dealing with non-uniformly distributed codes. Besides, there are lots of results sharing the same Hamming distance to a query, which makes the distance measure ambiguous. In this paper, we propose a data-oriented multi-index hashing method (DOMIH). We first compute the covariance ma-trix of bits and learn adaptive projection vector for each binary substring. Instead of using substrings as direct indices into hash tables, we project them with corresponding projection vectors to generate new indices. With adaptive projection, the indices in each hash table are near uniformly distributed. Then with covariance matrix, we propose a ranking method for the binary codes. By assigning different bit-level weights to different bits, the returned bina-ry codes are ranked at a finer-grained binary code level. Experiments conducted on reference large scale datasets show that compared to MIH the time performance of DOMIH can be improved by 36.9%-87.4%, and the search accuracy can be improved by 22.2%. To pinpoint the potential of DOMIH, we further use near-duplicate image retrieval as examples to show the applications and the good performance of our method.

• Korean Journal of Applied Biomechanics
• /
• v.24 no.3
• /
• pp.217-227
• /
• 2014

The purpose of this study was to investigate the relationship between distance and factors of javelin in korean male's javelin throwing. To accomplish this purpose, the analyzed trail selected total 29 trails (subjects 9) recorded more than 65 m in the 93rd National Sports Festival. The Kwon3D 3.1 version was used to obtain the three dimensional coordinates about the top, grip, end of javelin. And the kinematic data such as projection factors and direction angle of javelin calculated using Matlab2009a program. The statical analysis on the records (n=29) were used to Pearson's product moment correlation coefficient. There was a statistically positive relationship between the records and horizontal velocity (r=.866, ${\rho}$<.01), height (r=.541, ${\rho}$ <.001), height rate (r=.373, ${\rho}$ <.05) and horizontal displacement of javelin (r=.749, ${\rho}$ <.01), but the medial/lateral velocity showed a negative relationship to r=-.663 (${\rho}$ <.01). The attack and yaw angle showed not a significant relationship between the records, but the medial-lateral tilt (E1:r =-.557 [p<.01)] E2:r=-.629 [${\rho}$<.01], E3:r=-.528 [${\rho}$ <.01]) and attitude angle (E2:r=-.629 [[${\rho}$<.01], E3:r=-.619 [${\rho}$ <.01]) of javelin showed a negative relationship between the records, as well as the projection angle of javelin (r=-.419, ${\rho}$ <.05) showed a negative relationship between the records.