14.2 United Way
About1. Introduction2. Overview3. GUI4. Image Signatures5. Unsupervised Filters6. Results & Analysis7. BioFilters8. NeuralFilters9. Duplicated Documents10. Face Recognition11. Auto Part Recognition12. Dynamic Library13. NeuralNet Filter14. Segment Variation15. TV Advertisements16. Counting & Tracking17. Image PreProcessing18. Image Processing19. Batch Job20. Parameters21. Input Option22. Application Developers23. Reference Manual24. Support Services25. Readme.txt

14.1 Parameters 
14.2 United Way 
14.3 Tabasco 
14.4 Mr. Potato 
14.5 Monopoly 
14.6 Stamp 

 

[Home][14. Segment Variation][14.2 United Way]

 

14.2   United Way - Rotation Symmetry

There are two ways to run this example:

  •    Batch
  •    Manual

The Batch Run takes only two clicks:

  • Click �Examples/Neural Net/United Way - R� ;
  • Click �Batch/Run�.

The Manual Run requires a few more clicks:

Input:

    Training: .\ex_trademark\image036.jpg

    Search: .\ex_trademark\

Parameters

    Edge Filter:           (Image Processing-----------1st box)

      None

    Threshold Filter:    (Image Processing-----------2nd box)   

      Light Background 192

    NeuralNet Filter:    (Neural Net Parameters)

      Symmetry: Rotation Symmetry

      Blurring = 25

      Sensitivity = 25

      Internal Cut = 40

      External Cut (Threshold) = 68000

Operation

  •    Click the �Key� button and select �.\ex_trademark\image036.jpg�;
  •    Click the �Source� button and select �.\ex_trademark\�;
  •    Set the Parameters as specified above;
  •    Click the �NeuralNet/Train� button to train the filter;
  •    Click the �NeuralNet/Matching/1:N (Key vs Source)� button to make a search.

Results

    ID  Name        Path        Score   X   Y   W   H   R

    I036_r10    I036_r10.jpg    C:\...\ex_trademark\    105088  36  36  160 124 350

    I036_r20    I036_r20.jpg    C:\...\ex_trademark\    84608   36  24  160 124 340

    I036_r30    I036_r30.jpg    C:\...\ex_trademark\    113408  24  12  160 124 330

    I036_r40    I036_r40.jpg    C:\...\ex_trademark\    76544   24  12  160 124 320

    I036_r50    I036_r50.jpg    C:\...\ex_trademark\    69248   36  36  160 124 310

    I036_r60    I036_r60.jpg    C:\...\ex_trademark\    96768   24  24  160 124 300

    I036_r70    I036_r70.jpg    C:\...\ex_trademark\    98176   48  48  160 124 290

    I036_r80    I036_r80.jpg    C:\...\ex_trademark\    107328  36  12  160 124 280

    I036_r90    I036_r90.jpg    C:\...\ex_trademark\    118592  24  12  160 124 270

          IMAGE036    IMAGE036.JPG    C:\...\ex_trademark\    128000000   30  18  160 124 0

Summary

    # Images        = 126

    # To be retrieved   = 10

    # Retrieved Correctly   = 10

    # Missed        = 0   

    Hit Ratio       = 100%    

Here, Hit Ratio is the number of correctly retrieved images divided by the number of retrieved images. In this particular case, Hit Ratio = 100% = 10/10.

 

[Home][About][1. Introduction][2. Overview][3. GUI][4. Image Signatures][5. Unsupervised Filters][6. Results & Analysis][7. BioFilters][8. NeuralFilters][9. Duplicated Documents][10. Face Recognition][11. Auto Part Recognition][12. Dynamic Library][13. NeuralNet Filter][14. Segment Variation][15. TV Advertisements][16. Counting & Tracking][17. Image PreProcessing][18. Image Processing][19. Batch Job][20. Parameters][21. Input Option][22. Application Developers][23. Reference Manual][24. Support Services][25. Readme.txt]

Copyright (c) 1998 - 2006 Attrasoft, Inc. All rights reserved.

gina@attrasoft.com