• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.385-388
• /
• 2000

본 논문에서는 영상처리 기법 중 하나인 이진 영상에 대한 골격화를 이용한 새로운 형상 기술자를 제안한다. 내용기반 영상 검색에서 형상을 이용하는 것은 가장 우세하고 인간이 가장 쉽게 인지할수 있는 방법 중의 하나이다. 형상을 이용한 검색을 위해 서는 인간이 인지하는 형상에 대한 정보를 간략화시킬 수 있는 기술자가 필요하다. 본 논문에서 제안하는 골격을 이용한 형상 기술자는 물체의 중요한 정보 중 하나인 골격을 영상 검색에 이용함으로써 기존의 물체가 갖고 있는 복잡한 형상 정보들을 여러개의 직선의 조합으로 간략하게 표현하고 이를 검색에 사용하는 것이다. 이를 위해서 단순한 골격화 외의 다른 형태학적 영상 처리를 이용하여 효과적인 직선 추출을 위한 여건을 마련한다. 그리고 근사화된 직선들이 추출되면 스케일에 대해 정규화 하여 골격을 이루는 직선들의 양 끝점을 형상 기술자로 얻을 수 있다. 각 특징벡터에 대한 정합은 각각의 회전에 대해 유클리디안 거리를 이용한다. 실험 결과, 제안된 방법이 자세한 부분보다는 대략적인 형상 검색과 동일한 카테고리의 데이타 집합에서 부분적인 변화에 대해 우수한 성능을 나타낸다는 것을 알 수 있다.

• 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 Broadcast Engineering
• /
• v.13 no.6
• /
• pp.962-965
• /
• 2008

2-D shape descriptors, which are vectors representing characteristics of shapes, enable comparison and classification of shapes and are mainly applied to image and 3-D model retrieval. Existing descriptors have limitations that they only describe shapes of single closed contours or lack in precision, making it difficult to be applied to shapes with multiple contours. Therefore, in this paper, we propose a new shape descriptor called Multi-Curvature-Scale Space that can be applied to shapes with multiple contours. Specifically, we represent the topology of the sub-contours in the multi-contour along with Curvature-Scale Space descriptors to represent the shapes of each sub-contours. Also, by allowing the weight of each component to be controlled when computing the distance between descriptors the weight, we deal with ambiguities in measuring similarity between shapes. Results of various experiments that prove the effectiveness of proposed descriptor are presented.

• Journal of the Korean GEO-environmental Society
• /
• v.18 no.3
• /
• pp.25-30
• /
• 2017

This paper introduces a novel method to quantify the morphological evolution of the strain response envelope. The strain response envelope is defined as an image in strain increment space corresponding to the unit stress input in stress space. Based on the shape of strain response envelopes, the deformation characteristics of soils can be described using the framework of elastic-plastic theory. Fourier descriptor analysis was used to investigate the morphological characteristics of strain response envelopes. The numerical results show that when the stress input remains in the initial yield surface the Fourier descriptors remain constant. Once the stress input crosses the initial yield surface, every descriptors deals in this study change. Numerical and experimental results of this study show that clear yielding response is only found in natural block samples. Among the Fourier descriptors, the descriptor called as asymmetry is the best for detecting the yield and is minimally sensitive to the number of input stress paths.

• 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 Korea Society of Computer and Information
• /
• v.16 no.11
• /
• pp.103-111
• /
• 2011

In this paper, we propose a Geometrical Centroid Contour Distance(GCCD) which is described by shape signature based on contour sequence. The proposed method uses geomertrical relation features instead of the absolute angle based features after it was normalized and aligned with dominant feature of the shape. Experimental result with MPEG-7 CE-Shape-1 Data Set reveals that our method has low time/spatial complexity and scale/rotation robustness than the other methods, showing that the precision of our method is more accurate than the conventional desctiptors. However, performance of the GCCD is limited with concave and complex shaped objects.

• Journal of the Korea Computer Graphics Society
• /
• v.16 no.2
• /
• pp.29-37
• /
• 2010

In this paper, we present a novel deformation method for alleviating the asymmetry of a scanned 3D face considering facial features. To handle detailed areas of the face, we developed a new local 3D shape descriptor based on facial features and surface curvatures. Our shape descriptor can improve the accuracy when deforming a 3D face toward a symmetric configuration, because it provides accurate point pairing with respect to the plane of symmetry. In addition, we use point-based representation over all stages of symmetrization, which makes it much easier to support discrete processes. Finally, we performed a statistical analysis to assess subjects' preference for the symmetrized faces by our approach.

• Journal of the Korean Society for Advanced Composite Structures
• /
• v.1 no.2
• /
• pp.59-65
• /
• 2010

The simple supported reinforced concrete slab bridges are analyzed by the specially orthotropic laminates theory. This method, however, may be too difficult for some practising engineers. In this paper, the result of analysis for such plate by means of the beam theory with unit width is reported. By using the "correction factor", the accurate solution for the plate can be obtained by the beam theory. By using the "correction factor", the accurate solution for the plate can be obtained by the beam theory. The plate aspect ratio considered is from 1 : 1 to 1 : 6. The result of this paper can be used for simply supported slab bridges analysis.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.10a
• /
• pp.231-231
• /
• 2003

사출성형에서의 지금까지의 에어트랩 문제의 해결법은 사출금형 내에 유동적 관계와 사출성형 기술자의 경험으로 해결했었다. 본 연구에서는 에어트랩 문제를 해결하기 위하여 금형을 설계할 때 미리 에어트랩의 위치를 알고 금형 디자인을 수정하여 사출 시간의 단축과 사출성형의 경제적 효과를 얻고자 한다. 사출성형을 할 때 에어트랩의 불량이 많이 발생하는 특징 형상들을 선정하여 각각의 특징형상들을 다시 해석하여 각각의 특징형상들의 에어트랩의 발생위치와 발생률을 알아내고, 사출금형설계에서 에어트랩불량이 일어날 형상들을 특징형상 변수에 대응시켜 최적의 형상으로 수정절차를 개발하였다. 여기서, 사출속도의 조절, 금형 온도의 조절, 수지온도 조절, 금형내의 압력 조절, 벤트의 설치 등은 최적의 상태로 고정시키고 형상수정 요소로 형상의 두께, 각도, 깊이, 필렛, 모 따기를 선정하여 특징형상 상관관계 모델을 구성하였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.1
• /
• pp.33-42
• /
• 2001

Recently, the interests in the 3D image, generated from the range data and CAD, have exceedingly increased, accordingly a various 3D image database is being constructed. The efficient and fast scheme to access the desired image data is the important issue in the application area of the Internet and digital library. However, it is difficult to manage the 3D image database because of its huge size. Therefore, a proper descriptor is necessary to manage the data efficiently, including the content-based search. In this paper, the proposed shape descriptor is based on the voxelization of the 3D image. The medial axis transform, stemming from the mathematical morphology, is performed on the voxelized 3D image and the graph, which is composed of node and edge, is generated from skeletons. The generated graph is adequate to the novel shape descriptor due to no loss of geometric information and the similarity of the insight of the human. Therefore the proposed shape descriptor would be useful for the recognition of 3D object, compression, and content-based search.