15.4 Run
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

15.1 Why? 
15.2 Data 
15.3 Parameters 
15.4 Run 
[Home][15. TV Advertisements][15.4 Run]

 

15.4   Run

To run this example,

  •    Click the “Key” button and select “.\sp_tv\ V-ITFD04-PART01-832.jpg”; ;
  •    Click the “Source” button and select “.\sp_tv\”;
  •    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.

The results are:

ID              Name            Path    Score        X     Y   W   H    R

V-...800    V-...800.jpg    ...         96384    60     0   409 24  0

V-...801    V-...801.jpg    ...         94656   12      0   409 24  0

V-...802    V-...802.jpg    ...         96640   66      0   409 24  0

V-...803    V-...803.jpg    ...         95104   78      0   409 24  0

V-...804    V-...804.jpg    ...         94976   90      0   409 24  0

V-...810    V-...810.jpg    ...         85824   108  360 409 24  0

V-...831    V-...831.jpg    ...         72448   48    228 409 24  0

V-...832    V-...832.jpg    ...         86336   48    228 409 24  0

V-...833    V-...833.jpg    ...         82048   48    228 409 24  0

V-...834    V-...834.jpg    ...         75072   48    228 409 24  0

V-...835    V-...835.jpg    ...         80512   48  2  28 409 24  0

V-...836    V-...836.jpg    ...         83456   48    228 409 24  0

V-...837    V-...837.jpg    ...         82240   48    228 409 24  0

V-...838    V-...838.jpg    ...         76928   48    228 409 24  0

V-...839    V-...839.jpg    ...         79808   48    228 409 24  0

V-...840    V-...840.jpg    ...         86016   48    228 409 24  0

V-...841    V-...841.jpg    ...         88192   48    228 409 24  0

V-...842    V-...842.jpg    ...         72960   48    228 409 24  0

V-...843    V-...843.jpg    ...         69568   48    228 409 24  0

V-...844    V-...844.jpg    ...         67840   48    228 409 24  0

V-...845    V-...845.jpg    ...         67584   48    228 409 24  0

V-...846    V-...846.jpg    ...         63232   48    228 409 24  0

V-...847    V-...847.jpg    ...         65536   48    228 409 24  0

V-...848    V-...848.jpg    ...         70080   48    228 409 24  0

V-...849    V-...849.jpg    ...         76416   48    228 409 24  0

V-...850    V-...850.jpg    ...         75776   48    228 409 24  0

V-...851    V-...851.jpg    ...         74624   48    228 409 24  0

V-...852    V-...852.jpg    ...         69568   48    228 409 24  0

V-...853    V-...853.jpg    ...         71296   48    228 409 24  0

V-...854    V-...854.jpg    ...         67904   48    228 409 24  0

V-...855    V-...855.jpg    ...         72960   48    228 409 24  0

V-...856    V-...856.jpg    ...         76160   48    228 409 24  0

V-...857    V-...857.jpg    ...         78656   48    228 409 24  0

V-...858    V-...858.jpg    ...         76608   48    228 409 24  0

V-...859    V-...859.jpg    ...         78656   48    228 409 24  0

V-...860    V-...860.jpg    ...         78144   48    228 409 24  0

V-...861    V-...861.jpg    ...         74432   48    228 409 24  0

V-...862    V-...862.jpg    ...         68480   48    228 409 24  0

V-...863    V-...863.jpg    ...         71808   48    228 409 24  0

V-...864    V-...864.jpg    ...          74176   48    228 409 24  0

V-...865    V-...865.jpg    ...         76096   48    228 409 24  0

V-...866    V-...866.jpg    ...         67520   48    228 409 24  0

V-...883    V-...883.jpg    ...         64000   72    300 409 24  0

V-...884    V-...884.jpg    ...         65152   72    300 409 24  0

V-...896    V-...896.jpg    ...         64384   72    300 409 24  0

V-...897    V-...897.jpg    ...         64896   72    300 409 24  0

V-...898    V-...898.jpg    ...         64704   72    300 409 24  0

V-...901    V-...901.jpg    ...         66624   84    300 409 24  0

V-...902    V-...902.jpg    ...         66048   72    300 409 24  0

V-...903    V-...903.jpg    ...         65664   72    300 409 24  0

V-...904    V-...904.jpg    ...         72064   72    300 409 24  0

There are 51 retrieved images. Images 831 to 866 represent 36 frames and 12 seconds of ads. All images in this group are identified.

Images 874 to 904 represent 29 frames and close to 10 seconds of ads.  The second group is a bit smaller, and needs a separate search. Some of the images in this group are identified. There are 6 errors; this error rate can be solved by customization.

 

[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