• Journal of Korea Multimedia Society
• /
• v.14 no.6
• /
• pp.742-751
• /
• 2011

This paper presents a robust 3D model hashing dependent on key and parameter by using heat kernel signature (HKS), which is special shape feature descriptor, In the proposed hashing, we calculate HKS coefficients of local and global time scales from eigenvalue and eigenvector of Mesh Laplace operator and cluster pairs of HKS coefficients to 2D square cells and calculate feature coefficients by the distance weights of pairs of HKS coefficients on each cell. Then we generate the binary hash through binarizing the intermediate hash that is the combination of the feature coefficients and the random coefficients. In our experiment, we evaluated the robustness against geometrical and topological attacks and the uniqueness of key and model and also evaluated the model space by estimating the attack intensity that can authenticate 3D model. Experimental results verified that the proposed scheme has more the improved performance than the conventional hashing on the robustness, uniqueness, model space.

• Journal of the Korean GEO-environmental Society
• /
• v.17 no.3
• /
• pp.21-26
• /
• 2016

Soil particle shape analysis was conducted with sands from Jumujun, Korea and Ras Al Khair, Saudi Arabia. Two hundred times enlarged digital images of the particles of those two sands were obtained with an optical microscope. The resolution of the digital images was $640{\times}320$. By conducting digital image processing, the coordinates of the soil particle boundary were extracted. After mapping those coordinates to the complex space, Fourier transformation was performed and the coefficients of each trigonometry term were computed. The coefficients reflect the shape characteristics of the sand grains and are invariant to translation. To evaluate the shape itself excluding the size of the soil particle, the coefficient was normalized by the equivalent radius of soil particle; this is called Fourier descriptor. After analyzing the Fourier descriptors, it was found that the major characteristics of Jumunjin and Ras Al Khair sands were elongation and asymmetry. Furthermore, it was found that the particle shapes reflect the self-similar, fractal nature of the textural features. The effects of resolution on soil particle shape analysis was also studied. Regarding this, it was found that the significant Fourier descriptors were not significantly affected by the image resolution investigated in this study, but the descriptors associated with textural features were affected.

• Journal of the KSME
• /
• v.44 no.6
• /
• pp.34-39
• /
• 2004

형상기억합금(SMA : Shape Memory Alloy)은 일반적인 금속이나 합금에서는 찾아볼 수 없는 형상기억효과(shape memory effect)와 초탄성 (superelasticity) 거동을 보이고 있다. 이러한 특성은 1951년에 금-카드뮴(Au-Cd) 합금에서 처음으로 발견되었으며, 1963년에 미국 해군병기연구소(Naval Ordnance Laboratory)에서 니켈-티타늄 (Ni-Ti) 합금에서 형상기억효과를 발견한 후로 널리 상용화되었다. 니티놀(nitinol)이라고 불려지는 니켈-티타늄 계열의 형상기억합금은 단위 부피당 많은 에너지를 낼 수 있고, 내 부식성(corrosion resistance)과 생화학적 적합성(bio-compatibility)이 뛰어나다. 또한 100,000사이클 이상의 긴 사용수명을 갖기 때문에 작동기(actuator)로서 우수한 특징을 갖는다. (중략)

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1325-1328
• /
• 2006

본 논문은 기계 가공시 형상의 인지 절차에 대해 기술한다. 주조와 단조 공정의 특성 중 한가지는 기계 가공시 원재료가 최종 형상에 매우 근접하다는 것이다. 이때 가공 형상 추출은 가공될 면을 인지하는 것과 가공면을 군집으로 그룹화 하는 두 단계로 수행될 수 있다. 이중 가공될 면을 인지하기 위한 기존의 방법은 3D Boolean difference operation을 수행하는 것이다. 그러나 3D Boolean difference operation의 계산적 난점 때문에 복잡한 형상에는 실용적이지 못하다. 본 논문의 목적은 가공 면을 인지하는 효율적인 알로리즘을 개발하는 것이다.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1998.04a
• /
• pp.151-154
• /
• 1998

본 논문에서는 스테레오 정합기법을 이용하여 2차원 물체의 형상정보로부터 3차원 형상정보를 자동 추출하는 시스템을 제안한다. 본 논문에서는 정확한 3차원 형상추출을 위해서 밝기값기반 방법과 특징기반 방법의 장점을 살려 두 방법을 통합 사용하였다. 또한, 오정합을 최소화하고 처리속도를 향상시키기 위해서Coarst-to-fine 방법을 적용하였다. 제안한 방법에 의해 도출된 변이영상(Disparity map)은 3차원 그래픽을 이용하여 모델링에 적용함으로써 3차원 형상정보 추출의 타당성 및 가상공간에서의 적용 가능성을 보였다.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.3
• /
• pp.65-74
• /
• 2021

3D reconstruction means that reconstructing the 3D shape of the object in an image and a video. We proposed a progressive occupancy network architecture that can recover not only the overall shape of the object but also the local details. Unlike the original occupancy network, which uses a feature vector embedding information of the whole image, we extract and utilize the different levels of image features depending on the receptive field size. We also propose a novel network architecture that applies the image features sequentially to the decoder blocks in the decoder and improves the quality of the reconstructed 3D shape progressively. In addition, we design a novel decoder block structure that combines the different levels of image features properly and uses them for updating the input point feature. We trained our progressive occupancy network with ShapeNet. We compare its representation power with two prior methods, including prior occupancy network(ONet) and the recent work(DISN) that used different levels of image features like ours. From the perspective of evaluation metrics, our network shows better performance than ONet for all the metrics, and it achieved a little better or a compatible score with DISN. For visualization results, we found that our method successfully reconstructs the local details that ONet misses. Also, compare with DISN that fails to reconstruct the thin parts or occluded parts of the object, our progressive occupancy network successfully catches the parts. These results validate the usefulness of the proposed network architecture.

• Journal of KIISE:Software and Applications
• /
• v.32 no.8
• /
• pp.759-768
• /
• 2005

This paper describes an algorithm that can recognize gestures constructing subspace gesture symbols with hybrid feature information. The previous popular methods based on geometric feature and appearance have resulted in ambiguous output in case of recognizing between similar gesture because they use just the Position information of the hands, feet or bodily shape features. However, our proposed method can classify not only recognition of motion but also similar gestures by the partial feature information presenting which parts of body move and the global feature information including 2-dimensional bodily motion. And this method which is a simple and robust recognition algorithm can be applied in various application such surveillance system and intelligent interface systems.

• Proceedings of the KSEEG Conference
• /
• 2007.04a
• /
• pp.319-321
• /
• 2007

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.681-684
• /
• 2006

본 논문은 능동형상모델(Active Shape Model: ASM)을 사용하여 손바닥의 형상을 추출하고 경계형상을 추적하기 위한 방법을 제안한다. 먼저, 경계추적을 위한 초기위치를 입력하기 위해 컬러영상에서 피부색영역의 위치 정보를 통해 중심점을 찾고 그 값을 통해 ASM을 이용하여 손바닥의 영역을 찾는다. ASM은 다양한 경계형상의 학습을 통해 평균값과 형상의 지배적 변형을 나타내는 형상벡터를 추출하기 위한 방법론이며 생체조직과 같은 형상이 일정하지 않고 평균형상을 기준으로 변화하는 형상의 외형을 추출, 추적하기에 적합한 기술이다. 본 논문에서는 피부색 특징을 이용하여 초기 손바닥의 위치를 찾고 이러한 위치정보를 이용하여 손 경계형상의 변화를 추적하는 방법을 실험을 통해 검증하였다

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.10
• /
• pp.113-122
• /
• 1999

When we want to retrieve the most similar image from the image database, the color histogram intersection, shape feature and texture feature comparing method are used as a metric to measure the similarity. In order to increase the accuracy of retrievals, we need to integrate two different features. In this paper, the histogram intersection and shape based block histogram intersection method are used. This method results in a high efficient algorithm that meets a similar accuracy and a relatively fast retrieval speed compared to the method of integration of two different features. The Proposed algorithm is tested on retrievals of image database consisting of various 600 images and we implemented that the proposed algorithm gives fast, high efficiency and reliability compared to others.