Dissertation > Excellent graduate degree dissertation topics show

Research of Orange Quality Classification Technology Based on Computer Vision

Author: QianChunHua
Tutor: GongShengRong
School: Suzhou University
Course: Software Engineering
Keywords: Citrus grading Fourier descriptors BP neural network Gabor wavelet SVM
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 59
Quote: 0
Read: Download Dissertation


Citrus fruit quality grading is an important part of its premarket after picking . Most of our fruit grading manually , can not guarantee the citrus grading treatment effect . Therefore, the application of computer vision technology to achieve automatic detection and classification of quality of citrus is of great significance . In this paper , Suzhou Dongshan citrus , as the research object , on the basis of image pre-processing of citrus , focus on the application of computer vision technology to achieve the citrus quality grading technology process and specific implementation method , to include of citrus objects and eigenvalue extraction method , classification algorithms. Research reflected in this article : (1 ) differential operator in the analysis of the edge detection of several sub on the basis of the characteristics of citrus image , design citrus image segmentation method based on Canny operator . On this basis , combined with the human visual characteristics , design method based on Fourier descriptors citrus shape characterization method based on the color characteristics of the HIS model description . The experiments show that using Canny operator has a large signal-to-noise ratio , high detection accuracy and computational advantages ; HIS model more in line with the human visual system , based on Fourier descriptors citrus shape eigenvalue easy to shape classification and recognition . ( 2 ) for the analysis of the number of iterations of traditional BP neural network algorithm more calculated and complex problems , designed to optimize the parameters of BP neural network algorithm , the characteristic values ??of the color and shape as the input , the citrus is divided into superior , first-class , second-class and endures four grades. The experimental results show that the classification accuracy rate of 95 % . ( 3) design based on Gabor wavelet texture feature extraction and the PCA fusion of SVM citrus grading method . This method first used Gabor wavelet transform direction and scale factor generated basis functions , and extracted texture features described ; then adopt the PCA method of dimension reduction , the formation of texture features optimized value ; based on SVM algorithm citrus classification . Experimental proof : airspace based on the BP neural network algorithm citrus color, shape characteristics the classification results wavelet domain citrus the texture characteristics grading results based on SVM algorithm integrated conduct simple weight grading classification correct rate higher , reach 97.5%.

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 Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  7. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  8. Research on Classification Method of Tongue Substance Color and Tongue Coating Color Based on SVM,TP391.41
  9. The Research on Paper Currency Classification Method Based on Harr-Like Feature and Minimal Ball Including Samples,TP391.41
  10. Research on Visual Servo System of Mechanical ARM,TP242.6
  11. Municipal tourism land use planning environmental impact assessment,X820.3
  12. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  13. Research on Focused Crawler Based on SVM Classification Algorithm,TP391.3
  14. Research on Predicting Intrinsic Disorder Protein Structure Based on Supervision Manifold Learning Algorithm,Q51
  15. The Research on Evaluation of Living Status Systems of Expressway Relocated People,D523
  16. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  17. Mine Risk Information Integration and Intelligent Early Warning,X936
  18. Analysis on Synoptic Climatology Characteristics and Forecast Methods of Fog in Hainan,P457
  19. Research of License Plate Recognition Based on Rough Sets and Fuzzy SVM,TP391.41
  20. Optimization Study on Gating System and Molding Process Parameters of Injection Mold Based on Simulation,TQ320.662

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