7.2 Training
Training teaches the ImageFinder what to look for. Unsupervised Matching does not require training.
The BioFilter training requires two files, t1.txt and match.txt:
-
T1.txt is the signature file, which contains many signatures. Each image is converted into a signature.
-
Match.txt is a list of matching pairs. This file will teach the ImageFinder who will match with whom.
These two file names, t1.txt and match.txt, for training are fixed; you cannot change the names of these two files.
These two file names, t1.txt and match.txt, for training are fixed; you cannot change the names of these two files.
How to Prepare t1.txt
You obtain t1.txt through the signature computation process in chapter 4. First, you obtain signature file, a1.txt, then click “Signature/Copy a1.txt to t1.txt” to get t1.txt”.
How to Prepare match.txt
In all examples of this manual, the file, match.txt, are prepared for you. However, in your own applications, you have to prepare match.txt for each problem.
The match.txt looks like this:
152
1 L01008gi_r90 L01008gi-020501
2 L01008KEY_m L01008key-082301_m
3 L010103C L010103C-081502_m
4 L01010co_m L01010CODE_m
5 L010163C_m L010163C-083100_m
…
Line 1 is the number of matches in this file. This match file indicates images, L01008gi_r90, will match with image, L01008gi-020501. Each line has the following format:
Number, tab, filename, tab, filename.
Note:
You MUST have a tab between the three columns;
The file names do not contain “.jpg”.
There are two common errors:
(1) The Tab is replaced by a space;
(2) The number of rows is less than the first number in the file.
Once you get the two files prepared, click “BioFilter\Training\Training” to train the BioFilter. (Figure 7.1)
Copyright (c) 1998 - 2006 Attrasoft, Inc. All rights reserved.