• Title, Summary, Keyword: bilinear rectangle

Search Result 2, Processing Time 0.231 seconds

Numerical Evaluation of Fundamental Finite Element Models in Bar and Beam Structures (Bar와 Beam 구조물의 기본적인 유한요소 모델의 수치해석)

  • Ryu, Yong-Hee;Ju, Bu-Seog;Jung, Woo-Young;Limkatanyu, Suchart
    • Journal of the Korean Society for Advanced Composite Structures
    • /
    • v.4 no.1
    • /
    • pp.1-8
    • /
    • 2013
  • The finite element analysis (FEA) is a numerical technique to find solutions of field problems. A field problem is approximated by differential equations or integral expressions. In a finite element, the field quantity is allowed to have a simple spatial variation in terms of linear or polynomial functions. This paper represents a review and an accuracy-study of the finite element method comparing the FEA results with the exact solution. The exact solutions were calculated by solid mechanics and FEA using matrix stiffness method. For this study, simple bar and cantilever models were considered to evaluate four types of basic elements - constant strain triangle (CST), linear strain triangle (LST), bi-linear-rectangle(Q4),and quadratic-rectangle(Q8). The bar model was subjected to uniaxial loading whereas in case of the cantilever model moment loading was used. In the uniaxial loading case, all basic element results of the displacement and stress in x-direction agreed well with the exact solutions. In the moment loading case, the displacement in y-direction using LST and Q8 elements were acceptable compared to the exact solution, but CST and Q4 elements had to be improved by the mesh refinement.

Recognition Performance Enhancement by License Plate Normalization (번호판 정규화에 의한 인식 성능 향상 기법)

  • Kim, Do-Hyeon;Kang, Min-Kyung;Cha, Eui-Young
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.12 no.7
    • /
    • pp.1278-1290
    • /
    • 2008
  • This paper proposes a preprocessing method and a neural network based character recognizer to enhance the overall performance of the license plate recognition system. First, plate outlines are extracted by virtual line matching, and then the 4 vertexes are obtained by calculating intersecting points of extracted lines. By these vertexes, plate image is reconstructed as rectangle-shaped image by bilinear transform. Finally, the license plate is recognized by the neural network based classifier which had been trained using delta-bar-delta algorithm. Various license plate images were used in the experiments, and the proposed plate normalization enhanced the recognition performance up to 16 percent.