[Home][25. Readme.txt][25.3 Image Recognition]
25.3 Image Recognition
Attrasoft ImageFinder matches whole images or image segments.
The ImageFinder can be used for:
-
Multiple Verification (1:1 Matching);
-
Identification or Search (1:N Matching); and
-
Multiple Identification (N:N and N:M Matching).
The image recognition process is to push images through a set of filters:
Preprocessing Filters
Edge Filters
Threshold Filters
Clean-Up Filters
Reduction Filters
Unsupervised Filters
BioFilters
NeuralFilters
NeuralNet Filters
You will need two inputs, key and source. Then you will match the key against the source. The key has one image. The source can be 1 image (1:1 matching), N images (1:N matching). You can also match the source against source (N:N matching).
The whole image matching will use image signatures.
The segment matching will NOT use image signatures.
[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.