2010 | OriginalPaper | Chapter
Similar - Dissimilar Victor Measure Analysis to Improve Image Knowledge Discovery Capacity of SOM
Authors : N. Chenthalir Indra, E. RamaRaj
Published in: Information and Communication Technologies
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Knowledge Discovery and Data Mining (KDD) is an interdisciplinary area focusing on methodologies for extracting useful knowledge from data. Patterns of relations of data and information have the capacity to signify knowledge. Image pattern collection and management is the hottest subject of the digital world. The demand for image recognition knowledge of various kinds of real world images becomes greater.
Kohenen’s Self Organizing Maps (SOM)
algorithm is one of the particular neural network algorithms, which is used for pattern learning and retrieval. The conventional SOM learning method represents poor knowledge and hence their applicable targets are restricted. In this paper SOM is scrutinizing with various standard distances and remarkable similar measures. Reliable image learning is achieved with City block, Lee, Maximum value distance, Jaccard and Dice coefficient. Image gallery can be mined well by using SOM with the above said measures. The composed knowledge is useful for various significant services.