Dissertation > Excellent graduate degree dissertation topics show
Shape Matching Based on Parabolic Fitting of Curvature Scale Space Maps
Author: WuFan
Tutor: ZhongBaoJiang
School: Nanjing University of Aeronautics and Astronautics
Course: Applied Mathematics
Keywords: Computer Vision Shape Matching Shape Description Curvature Scale Space Parabolic fitting
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 51
Quote: 0
Read: Download Dissertation
Abstract
|
Match between the shape of the object requires two basic steps in the field of computer vision , shape description and shape similarity calculation based on the description of the data . The curvature scale space (CSS) technology is a novel shape description method , because of a series of excellent properties of selected MPEG-7 standard . This technique on the CSS each arcuate lines to extract the maximum point value , thereby performing a matching between shapes . The disadvantage of this description is to retain only the data of the highest point of the arch lines , while ignoring the other information in the arched lines , which can not fully reflect the characteristics of object contours . To solve only consider the problems that exist in the highest point value CSS description method , this article proposed a new description of CSS-based map , called CSS Fig parabolic fitting . A new description of the shape characteristics of the method according to the arcuate lines , with the two-stage parabolic half arc fitting each period arcuate lines , thereby recording the next CSS FIG more important information , it is possible to more effectively describe the shape of the object . CSS-based map parabolic fitting description method , the shape similarity calculation problem , further study and put forward a new matching algorithm . First, horizontal cycle pan fitted CSS Figure the highest parabola is located in the extreme left of the map of the new CSS , matching of both parabolic curve . Subsequently , the similarity between the shape of the object calculated to establish the mathematical model , a numerical measure whether the shape matching . Simulation results show that the CSS diagram parabola fitting description method and the corresponding shape of the similarity calculating method can exhibit good results on the effect of shape matching .
|
Related Dissertations
- Research on Nondestructive Detection Technology for External Qualities of Papayas Based-on Vision,S667.9
- Study on Detection and Grading of ’Jiro’ Persimmon’s External Quality Based on Computer Vision,S665.2
- Prediction of Pork Processing Functionalities,TS251.1
- Research on Inspection Technology of Dehydrated Garlic Slice Based on Computer Vision,TP391.41
- Moving target trajectory analysis based Intelligent Traffic Monitoring System,TP277
- The Design and Implementation of On-line Strip Surface Defect Inspection System Based on Computer Vision,TP391.41
- Research on Key Technologies of Monocular Visual Odometry Based on DSP,TP391.41
- Research on Nitrogen Detective System Based on Image Processing,TP391.41
- Design and Implementation of Content Based Shape Search Platform,TP311.52
- Research and Application of Three-Dimensional of Human-Computer Interaction Technology Based on Computer Vision,TP391.41
- Research on Pose Estimation for UAV Based on Cooperative Object,TP391.41
- Research and Implementation of the Camera Calibration Methods,TP391.41
- Fragments Reassembly,TP391.41
- Computer Vision coal in thermal power plants plate Application,TM621.2
- Research on Molding Production Oriented Technology and Application of Visual Defects Recognition,TP391.41
- Research on Shoeprints Matching Algorithm on the Scene Based on Shape Context,TP391.41
- Corner and edge feature - based image registration method,TP391.41
- Robust Image Corner Detection Based on Curvature Product in Direct Curvature Scale Space,TP391.41
- Rectangularized CSS Images and a Matching Algorithm,TP391.41
- Research and Implementation of deformation modeling and rendering of key technologies,TP391.41
- Visual landing UAV cooperative target mid-infrared thermal blooming ambiguity removal method,V249.1
CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net Mobile
|