• 제목/요약/키워드: Shape-Based Matching

검색결과 220건 처리시간 0.027초

A New Shape Adaptation Scheme to Affine Invariant Detector

  • Liu, Congxin;Yang, Jie;Zhou, Yue;Feng, Deying
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제4권6호
    • /
    • pp.1253-1272
    • /
    • 2010
  • In this paper, we propose a new affine shape adaptation scheme for the affine invariant feature detector, in which the convergence stability is still an opening problem. This paper examines the relation between the integration scale matrix of next iteration and the current second moment matrix and finds that the convergence stability of the method can be improved by adjusting the relation between the two matrices instead of keeping them always proportional as proposed by previous methods. By estimating and updating the shape of the integration kernel and differentiation kernel in each iteration based on the anisotropy of the current second moment matrix, we propose a coarse-to-fine affine shape adaptation scheme which is able to adjust the pace of convergence and enable the process to converge smoothly. The feature matching experiments demonstrate that the proposed approach obtains an improvement in convergence ratio and repeatability compared with the current schemes with relatively fixed integration kernel.

MEASUREMENT OF THREE-DIMENSIONAL TRAJECTORIES OF BUBBLES AROUND A SWIMMER USING STEREO HIGH-SPEED CAMERA

  • Nomura, Tsuyoshi;Ikeda, Sei;Imura, Masataka;Manabe, Yoshitsugu;Chihara, Kunihiro
    • 한국방송∙미디어공학회:학술대회논문집
    • /
    • 한국방송공학회 2009년도 IWAIT
    • /
    • pp.768-772
    • /
    • 2009
  • This paper proposes a method for measurement three-dimensional trajectories of bubbles generated around a swimmer's arms from stereo high-speed camera videos. This method is based on two techniques: two-dimensional trajectory estimation in single-camera images and trajectory pair matching in stereo-camera images. The two-dimensional trajectory is estimated by block matching using similarity of bubble shape and probability of bubble displacement. The trajectory matching is achieved by a consistensy test using epipolar constraint in multiple frames. The experimental results in two-dimensional trajectory estimation showed the estimation accuracy of 47% solely by the general optical flow estimation, whereas 71% taking the bubble displacement into consideration. This concludes bubble displacement is an efficient aspect in this estimation. In three-dimensional trajectory estimation, bubbles were visually captured moving along the flow generated by an arm; which means an efficient material for swimmers to swim faster.

  • PDF

동적 변형의 회전 성분을 효율적으로 추출하기 위한 실용적 방법 (A Practical Method for Efficient Extraction of the Rotational Part of Dynamic Deformation)

  • 최민규
    • 한국게임학회 논문지
    • /
    • 제18권1호
    • /
    • pp.125-134
    • /
    • 2018
  • 본 논문에서는 시간에 따라 연속적으로 변하는 $3{\times}3$ 행렬의 회전 성분을 효율적으로 추출하는 실용적인 방법을 제안한다. 이는 물리기반 동적 변형을 위하여 널리 사용되는 공회전 유한 요소법이나 형상 맞춤 변형에서 매우 중요한 기술이다. 최근 극분해를 사용하는 시간 독립적인 기존 방법들과 달리 회전행렬 추출을 물리적으로 공식화한 후, 점진적 회전 표현법을 이용하는 반복법이 제안되었다. 본 논문에서는 점진적 회전 벡터의 최대 회전각을 ${\pi}/2$ 이내로 제한함으로써 반복 횟수를 줄이는 최적화 기법을 개발한다. 사실적인 동적 변형 시뮬레이션에서는 충분히 작은 시간 간격을 사용하기 때문에 이러한 제한은 실용적으로 문제가 되지 않는다. 다양한 실험을 통해 제안된 방법의 효율성 및 실용성을 보인다.

스테레오 정합을 이용한 3차원 형상정보 복원 (3D Shape Recovery based on Stereo Matching)

  • 구본기
    • 한국감성과학회:학술대회논문집
    • /
    • 한국감성과학회 1998년도 춘계학술발표 논문집
    • /
    • 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.

  • PDF

시계열 데이터베이스에서의 모양 기반 서브시퀀스 매칭 (Shape-Based Subsequence Matching in Time-Series Databases)

  • 김태훈;윤지희;김상욱;박상현
    • 한국정보과학회:학술대회논문집
    • /
    • 한국정보과학회 2001년도 가을 학술발표논문집 Vol.28 No.2 (1)
    • /
    • pp.178-180
    • /
    • 2001
  • 모양 기반 검색은 주어진 질의 시퀸스의 요소 값에 상관없이, 모양이 유사한 시퀸스 혹은 부분시퀸스를 찾는 연산이다. 본 논문에서는 시프트, 스케일링, 타임 워핑 등 동일 모양 변환의 다양한 조합을 지원할 수 있는 새로운 모양 기반유사 검색 모델을 제안하고, 효과적인 유사 부분 시퀸스 검색을 위한 인덱싱과 질의 처리 방법을 제안한다. 또한 실세계의 증권데이터를 이용한 다양한 실험 결과에 의하여, 본 방식이 질의 시퀸스와 유사한 모양의 모든 서브시퀸스를 성공적으로 찾는 것은 물론 순차검색 방법과 비교하여 매우 빠른 검색 효율을 가짐을 보인다.

  • PDF

A Novel Approach to Mugshot Based Arbitrary View Face Recognition

  • Zeng, Dan;Long, Shuqin;Li, Jing;Zhao, Qijun
    • Journal of the Optical Society of Korea
    • /
    • 제20권2호
    • /
    • pp.239-244
    • /
    • 2016
  • Mugshot face images, routinely collected by police, usually contain both frontal and profile views. Existing automated face recognition methods exploited mugshot databases by enlarging the gallery with synthetic multi-view face images generated from the mugshot face images. This paper, instead, proposes to match the query arbitrary view face image directly to the enrolled frontal and profile face images. During matching, the 3D face shape model reconstructed from the mugshot face images is used to establish corresponding semantic parts between query and gallery face images, based on which comparison is done. The final recognition result is obtained by fusing the matching results with frontal and profile face images. Compared with previous methods, the proposed method better utilizes mugshot databases without using synthetic face images that may have artifacts. Its effectiveness has been demonstrated on the Color FERET and CMU PIE databases.

Accuracy of the Point-Based Image Registration Method in Integrating Radiographic and Optical Scan Images: A Pilot Study

  • Mai, Hai Yen;Lee, Du-Hyeong
    • Journal of Korean Dental Science
    • /
    • 제13권1호
    • /
    • pp.28-34
    • /
    • 2020
  • Purpose: The purpose of this study was to investigate the influence of different implant computer software on the accuracy of image registration between radiographic and optical scan data. Materials and Methods: Cone-beam computed tomography and optical scan data of a partially edentulous jaw were collected and transferred to three different computer softwares: Blue Sky Plan (Blue Sky Bio), Implant Studio (3M Shape), and Geomagic DesignX (3D systems). In each software, the two image sets were aligned using a point-based automatic image registration algorithm. Image matching error was evaluated by measuring the linear discrepancies between the two images at the anterior and posterior area in the direction of the x-, y-, and z-axes. Kruskal-Wallis test and a post hoc Mann-Whitney U-test with Bonferroni correction were used for statistical analyses. The significance level was set at 0.05. Result: Overall discrepancy values ranged from 0.08 to 0.30 ㎛. The image registration accuracy among the software was significantly different in the x- and z-axes (P=0.009 and <0.001, respectively), but not different in the y-axis (P=0.064). Conclusion: The image registration accuracy performed by a point-based automatic image matching could be different depending on the computer software used.

선박 외판 성형에서 목적 형상과 전개 평판의 최적 정합을 위한 ICP(Iterative Closest Point) 알고리즘 적용 (Application of ICP(Iterative Closest Point) Algorithm for Optimized Registration of Object Surface and Unfolding Surface in Ship-Hull Plate Forming)

  • 이장현;윤종성;류철호;이황범
    • 한국CDE학회논문집
    • /
    • 제14권2호
    • /
    • pp.129-136
    • /
    • 2009
  • Generally, curved surfaces of ship hull are deformed by flame bending (line heating), multi-press forming, and die-less forming method. The forming methods generate the required in-plane/bending strain or displacement on the flat plate to make the curved surface. Multi-press forming imposes the forced displacements on the flat plate by controlling the position of each pressing points based upon the shape difference between the unfolded flat plate and the curved object shape. The flat plate has been obtained from the unfolding system that is independent of the ship CAD. Apparently, the curved surface and the unfolded-flat surface are expressed by different coordinate systems. Therefore, one of the issues is to find a registration of the unfolded surface and the curved shape for the purpose of minimum amount of forming works by comparing the two surfaces. This paper presents an efficient algorithm to get an optimized registration of two different surfaces in the multi-press forming of ship hull plate forming. The algorithm is based upon the ICP (Iterative Closest Point) algorithm. The algorithm consists of two iterative procedures including a transformation matrix and the closest points to minimize the distance between the unfolded surface and curved surfaces. Thereby the algorithm allows the minimized forming works in ship-hull forming.

Image Registration Based On Statistical Descriptors In Frequency Domain

  • Chang, Min-hyuk;Ahmad, Muhammad-Bilal;Lee, Cheul-hee;Chun, Jong-hoon;Park, Seung-jin;Park, Jong-an
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2002년도 ITC-CSCC -3
    • /
    • pp.1531-1534
    • /
    • 2002
  • Shape description and its corresponding matching algorithm is one of the main concerns in MPEG-7. In this paper, a new method is proposed for shape registration of 2D objects for MPEG-7 Shapes are recognized using the Hu statistical moments in frequency domain. The Hu moments are moment-based descriptors of planar shapes, which are invariant under general translation, rotational, scaling, and reflection transformation. The image is transformed into frequency domain using Fourier Transform. Annular and radial wedge distributions fur the power spectra are extracted. Different statistical features (Hu moments) are found f3r the power spectrum of each selected transformed individual feature. The Euclidean distance of the extracted moment descriptors of the features are found with respect to the shapes in the database. The minimum Euclidean distance is the candidate for the matched shape. The simulation results are performed on the test shapes of MPEG-7.

  • PDF

Non-Lambertian면의 형상복원 (3D Shape Reconstruction of Non-Lambertian Surface)

  • 김태은;이말례
    • 한국멀티미디어학회논문지
    • /
    • 제1권1호
    • /
    • pp.26-36
    • /
    • 1998
  • 2차원 밝기 영상에서 3차원 정보를 얻는 문제는 컴퓨터 시각 연구에서 매우 중요한 분야를 차지하고 있다. 이러한 목적을 위해 먼저 2차원 영상을 취득할 때 카메라의 위치, 광원의 방향, 영상내 물체의 반사특성 등 본질적인 정보를 이용한다. 이중에서 물체의 표면 반사특성은 매우 중요한 단서가 된다. 과거에는 물체의 반사특성을 Lambertian 반사만을 전제하여 연구를 진행했지만 실세계의 물체는 대부분 Non-Lambertian 반사특성을 갖는다. 본 논문에서는 2차원 밝기 영상에서 물체의 반사특성을 해석하고, 반사특성 파라미터를 추정하여 물체의 형상을 복구하는 새로운 방법과 반사특성을 모르는 상황에서 신경회로망 학습에 의해 형상을 복구하는 방법을 제안한다. 물체의 반사특성은 전반사 성분과 난반사 성분을 함께 갖는 Non-Lambertian 면을 그 대상으로 하며, 이러한 반사특성은 전반사(Torrance-Sparrow) 모델과 난반사(Lambertian) 모델의 선형적인 합으로 설명될 수 있다. 본 논문에서 제안한 Photometric Matching은 주변 화소의 밝기 분포를 고려하여 참조영상과의 매칭을 통한 형상복구 알고리듬으로써 기존의 Photometric Stereo에 근본을 두고 있지만, 잡음 및 오차의 누적 정도가 향상되었다. 또한 물체의 반사특성을 모르는 상황에서 신경회로망 학습에 의한 형상복구방법을 제안한다. 이 방법은 역전파 학습알고리듬을 이용해 광원 방향에 따른 밝기값에 대해 면법선을 교사하여 형상을 결정한다.

  • PDF