Dissertation > Excellent graduate degree dissertation topics show

Research on the Segmentation of Herb Cells Based on Curvelet and SVM

Author: WangZuo
Tutor: ZhouYu
School: Nanjing Forestry University
Course: Applied Computer Technology
Keywords: Miscanthus sacchariflorus cells Curvelet GLCM SVM
CLC: TP391.41
Type: Master's thesis
Year: 2013
Downloads: 0
Quote: 0
Read: Download Dissertation

Abstract


China has a large population and a great demand on paper supplies. And timber resourcehas no longer met the needs of people. so the cellulose content of herb cells directly concernswhether the herb is suitable for board making. Miscanthus sacchariflorus is a kind of herbs. Itcan be used as raw materials for paper-making instead of timber because of its rich cellulosecontent in the stem cells. So it is particularly important that how to extract cellulose fromMiscanthus sacchariflorus cell images.In the paper, applying image segmentation technology about China and aboard in timberspecies. And first edge detection has be used to segment the Miscanthus sacchariflorus cellimages. Several usual edge detection operators were compared and analyzed. To solve thisproblem, Curvelet transform theory was introduced to segment the Miscanthus saccharifloruscell images in the next chapter. The paper studied herbal cell image segmentation method basedon Curvelet and SVM and explored the feasibility of herbal cells feature extraction based ongray and texture features.In view of the multi-directional characteristics of Curvelet, the feature extraction methodbased on the Curvelet was studied. To solve the problem of insufficient information fromsub-band image just used Curvelet transform, method of feature extraction from Miscanthussacchariflorus cell images based on Curvelet and GLCM were proposed in this paper. Inaddition to extract mean and variance characteristics from sub-band image, further generateGLCM within the first layer of sub-band image through Curvelet transform. To get thecharacteristic parameters of Miscanthus sacchariflorus cell imaged, the paper analyzed GLCMcharacteristic parameters variation with three factors(grayscale, displacement and direction).Onthe basis, four usual characteristic parameters which include angle second order moment,contrast, correlation and entropy were calculated, which ultimately determine the characteristicparameters of Miscanthus sacchariflorus cell image with mean and variance characteristics.To illustrate the advantages of the proposed method, three other feature extraction methods:Curvelet characteristic parameters method, Curvelet mean and variance method and GLCMcharacteristic parameters method have been also discussed in the paper. And then, segmentationfor Miscanthus sacchariflorus cell images were implemented with a SVM classifier, includingthe selection of parameters,training samples and sliding window. Forthermore, to check theeffect on image segmentation, the original images were reconstructed according to image pixelposition and the category tags. Experiments show that the proposed method could betterdescribe the texture information of Miscanthus sacchariflorus cell images and result is betterthan the other three methods.

Related Dissertations

  1. Soft Sensor of Naphtha Dry Point on Support Vector Machines Regression,TE622.1
  2. The Research of the Fault Diagnoses Algorithm for the Liquid Rocket Engine Testing Bed Based on PCA-SVM,V433.9
  3. ISAR Imaging Simulation of Space Targets and Target Recognition Based on ISAR Images,TN957.52
  4. Research on Autamatic Music Structrue Analysis,TN912.3
  5. Research on Feature Extraction and Classification of Pulse Waveform for Cholecystitis and Nephrotic Syndrome Diagnosis,TP391.41
  6. Research on Sparse Image Representation and Coding Model,TP391.41
  7. Research on Classification Method of Tongue Substance Color and Tongue Coating Color Based on SVM,TP391.41
  8. The Research on Paper Currency Classification Method Based on Harr-Like Feature and Minimal Ball Including Samples,TP391.41
  9. Research on Focused Crawler Based on SVM Classification Algorithm,TP391.3
  10. Research on Predicting Intrinsic Disorder Protein Structure Based on Supervision Manifold Learning Algorithm,Q51
  11. The Application of Ant Colony Algorithm in Meteorological Satellite Cloud Pictures Segmentation,TP391.41
  12. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  13. Information Extraction of Marine Oil Spill with Collaborative Images of ASAR and MODIS,X87
  14. Research and Application of Gas Emission Prediction Based on LS-SVM,TD712.5
  15. Research of Support Vector Machine Based Fault Diagnosis System,TH165.3
  16. Image Fusion Algorithms Based on Multi-scale Analysis,TP391.41
  17. Research on Supplier-Selection Based on Strategic Sourcing,F426.31
  18. Research of License Plate Recognition Based on Rough Sets and Fuzzy SVM,TP391.41
  19. Vision-based Human Movement Analysis,TP391.41
  20. Research on Relevance Feedback Techniques Based on Long-term Log Learning and RW-Soft SVM in CBIR,TP391.3
  21. Expermential Study on Dynamic Characteristics of Aelian Soil in West Liaoning Province,TU411

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