14.5 Monopoly - Scaling Symmetry
There are two ways to run this example:
-
Batch
-
Manual
The Batch Run takes only two clicks:
-
Click “Example/Neural Net/Manopoly -S” ;
-
Click “Batch/Run”.
The Manual Run requires a few more clicks:
Input:
Training: .\ex_trademark\image046.jpg
Search: .\ex_trademark\
Parameters
Edge Filter: (Image Processing---------------1st box)
None
Threshold Filter: (Image Processing---------------2nd box)
Default
Clean Up Filter: (Image Processing---------------3rd box)
None
NeuralNet Filter Parameter: (Neural Net Parameters)
Scaling Symmetry
Blurring = 3
Sensitivity = 25
Internal Cut = 40
External Cut = 3200
Image Type = 5
Operation
-
Click the "Key Segment" button and select ".\ex_trademark\image046.jpg";
-
Click the "Source" button and select ".\ex_trademark\";
-
Set the Parameters as specified above;
-
Click the "Neural Net\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
I46_S105 I46_S105.JPG C:\...\ex_trademark\ 3252 0 0 0 0 0
I46_S110 I46_S110.JPG C:\...\ex_trademark\ 3801 0 0 0 0 0
I46_S115 I46_S115.JPG C:\...\ex_trademark\ 3378 0 0 0 0 0
I46_S120 I46_S120.JPG C:\...\ex_trademark\ 3318 0 0 0 0 0
I46_S80 I46_S80.JPG C:\...\ex_trademark\ 4815 0 0 0 0 0
I46_S85 I46_S85.JPG C:\...\ex_trademark\ 4614 0 0 0 0 0
I46_S90 I46_S90.JPG C:\...\ex_trademark\ 4140 0 0 0 0 0
I46_S95 I46_S95.JPG C:\...\ex_trademark\ 5040 0 0 0 0 0
IMAGE046 IMAGE046.JPG C:\...\ex_trademark\ 2100000000 0 0 0 0 0
Summary
# Images = 126
# To be retrieved = 9
# Retrieved Correctly = 9
# Missed = 0
Hit Ratio = 100%
Copyright (c) 1998 - 2006 Attrasoft, Inc. All rights reserved.