Tsallis Mutual Information for Document Classification
Mutual information is one of the mostly used measures for evaluating image similarity. In this paper, we investigate the application of three different Tsallis-based generalizations of mutual information to analyze the similarity between scanned documents. These three generalizations derive from the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2011-09-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1099-4300/13/9/1694/ |
| _version_ | 1811262806690889728 |
|---|---|
| author | Màrius Vila Mateu Sbert Anton Bardera Miquel Feixas |
| author_facet | Màrius Vila Mateu Sbert Anton Bardera Miquel Feixas |
| author_sort | Màrius Vila |
| collection | DOAJ |
| description | Mutual information is one of the mostly used measures for evaluating image similarity. In this paper, we investigate the application of three different Tsallis-based generalizations of mutual information to analyze the similarity between scanned documents. These three generalizations derive from the Kullback–Leibler distance, the difference between entropy and conditional entropy, and the Jensen–Tsallis divergence, respectively. In addition, the ratio between these measures and the Tsallis joint entropy is analyzed. The performance of all these measures is studied for different entropic indexes in the context of document classification and registration. |
| first_indexed | 2024-04-12T19:33:15Z |
| format | Article |
| id | doaj.art-8c3bb841be674b3ab920c88834137fa4 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-04-12T19:33:15Z |
| publishDate | 2011-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-8c3bb841be674b3ab920c88834137fa42022-12-22T03:19:17ZengMDPI AGEntropy1099-43002011-09-011391694170710.3390/e13091694Tsallis Mutual Information for Document ClassificationMàrius VilaMateu SbertAnton BarderaMiquel FeixasMutual information is one of the mostly used measures for evaluating image similarity. In this paper, we investigate the application of three different Tsallis-based generalizations of mutual information to analyze the similarity between scanned documents. These three generalizations derive from the Kullback–Leibler distance, the difference between entropy and conditional entropy, and the Jensen–Tsallis divergence, respectively. In addition, the ratio between these measures and the Tsallis joint entropy is analyzed. The performance of all these measures is studied for different entropic indexes in the context of document classification and registration.http://www.mdpi.com/1099-4300/13/9/1694/Tsallis entropymutual informationimage similaritydocument classification |
| spellingShingle | Màrius Vila Mateu Sbert Anton Bardera Miquel Feixas Tsallis Mutual Information for Document Classification Entropy Tsallis entropy mutual information image similarity document classification |
| title | Tsallis Mutual Information for Document Classification |
| title_full | Tsallis Mutual Information for Document Classification |
| title_fullStr | Tsallis Mutual Information for Document Classification |
| title_full_unstemmed | Tsallis Mutual Information for Document Classification |
| title_short | Tsallis Mutual Information for Document Classification |
| title_sort | tsallis mutual information for document classification |
| topic | Tsallis entropy mutual information image similarity document classification |
| url | http://www.mdpi.com/1099-4300/13/9/1694/ |
| work_keys_str_mv | AT mariusvila tsallismutualinformationfordocumentclassification AT mateusbert tsallismutualinformationfordocumentclassification AT antonbardera tsallismutualinformationfordocumentclassification AT miquelfeixas tsallismutualinformationfordocumentclassification |