Sampling Fingerprints From Multimedia Content Resource Clusters
Nowadays, the growth of multimedia content over the web is exponential. The fingerprints are inconspicuously embedded in multimedia content. The fingerprints can be exploited to trace divergent information from multimedia resources. Sampling fingerprints, particularly from multimedia resources, is c...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10360132/ |
| _version_ | 1797365955907551232 |
|---|---|
| author | Umer Rashid Samra Naseer Abdur Rehman Khan Muazzam A. Khan Gauhar Ali Naveed Ahmad Yasir Javed |
| author_facet | Umer Rashid Samra Naseer Abdur Rehman Khan Muazzam A. Khan Gauhar Ali Naveed Ahmad Yasir Javed |
| author_sort | Umer Rashid |
| collection | DOAJ |
| description | Nowadays, the growth of multimedia content over the web is exponential. The fingerprints are inconspicuously embedded in multimedia content. The fingerprints can be exploited to trace divergent information from multimedia resources. Sampling fingerprints, particularly from multimedia resources, is challenging since they are complex, heterogeneous, and diverse. This research proposed an approach to sample fingerprints from multimedia resources. Our approach partitions the multimedia content space into converged clusters using variations of Canberra distance and identifies the most diverged samples using Kullback-Leibler (KL) divergence. The resultant clusters represent the information belonging to particular concepts and the diverged samples within the clusters represent multimedia fingerprints. The fingerprint sampling process is leveraged using unsupervised learning algorithms, instantiated across various multimedia descriptors, and tested over standard multimedia datasets. The average results obtained over various standard visual and acoustic datasets reveal 80%, 77%, and 78% accuracy, precision, and recall, respectively, surpassing most of the existing baseline clustering methods such as K-Means, Mean-Shift, and DBSCAN. Furthermore, the rigorousness of the proposed algorithm clustering is evaluated using the internal clustering stability silhouette coefficient and the fingerprint diversity scores. The results unveil a maximum of 94% diversity score. The proposed variation of Canberra distance and KL divergence provides the most stable performance (SD=0.02) and creates promising implications in future multimedia retrieval, summarization, and exploration activities. |
| first_indexed | 2024-03-08T16:57:20Z |
| format | Article |
| id | doaj.art-e6b8e9e2ccde4f5d924997c9f0e1a36e |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T16:57:20Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e6b8e9e2ccde4f5d924997c9f0e1a36e2024-01-05T00:02:42ZengIEEEIEEE Access2169-35362023-01-011114164014165610.1109/ACCESS.2023.334319010360132Sampling Fingerprints From Multimedia Content Resource ClustersUmer Rashid0https://orcid.org/0000-0002-3453-7979Samra Naseer1https://orcid.org/0009-0005-5859-8505Abdur Rehman Khan2Muazzam A. Khan3Gauhar Ali4https://orcid.org/0000-0001-9691-7347Naveed Ahmad5https://orcid.org/0000-0003-2941-9780Yasir Javed6https://orcid.org/0000-0002-6311-027XDepartment of Computer Sciences, Quaid-i-Azam University, Islamabad, PakistanDepartment of Computer Sciences, Quaid-i-Azam University, Islamabad, PakistanDepartment of Computer Science, National University of Modern Languages, Lahore, PakistanDepartment of Computer Sciences, Quaid-i-Azam University, Islamabad, PakistanCollege of Computer and Information Sciences, Prince Sultan University, Riyadh, Saudi ArabiaCollege of Computer and Information Sciences, Prince Sultan University, Riyadh, Saudi ArabiaCollege of Computer and Information Sciences, Prince Sultan University, Riyadh, Saudi ArabiaNowadays, the growth of multimedia content over the web is exponential. The fingerprints are inconspicuously embedded in multimedia content. The fingerprints can be exploited to trace divergent information from multimedia resources. Sampling fingerprints, particularly from multimedia resources, is challenging since they are complex, heterogeneous, and diverse. This research proposed an approach to sample fingerprints from multimedia resources. Our approach partitions the multimedia content space into converged clusters using variations of Canberra distance and identifies the most diverged samples using Kullback-Leibler (KL) divergence. The resultant clusters represent the information belonging to particular concepts and the diverged samples within the clusters represent multimedia fingerprints. The fingerprint sampling process is leveraged using unsupervised learning algorithms, instantiated across various multimedia descriptors, and tested over standard multimedia datasets. The average results obtained over various standard visual and acoustic datasets reveal 80%, 77%, and 78% accuracy, precision, and recall, respectively, surpassing most of the existing baseline clustering methods such as K-Means, Mean-Shift, and DBSCAN. Furthermore, the rigorousness of the proposed algorithm clustering is evaluated using the internal clustering stability silhouette coefficient and the fingerprint diversity scores. The results unveil a maximum of 94% diversity score. The proposed variation of Canberra distance and KL divergence provides the most stable performance (SD=0.02) and creates promising implications in future multimedia retrieval, summarization, and exploration activities.https://ieeexplore.ieee.org/document/10360132/Algorithmsconvergenceclusteringdivergencefingerprintsmultimedia |
| spellingShingle | Umer Rashid Samra Naseer Abdur Rehman Khan Muazzam A. Khan Gauhar Ali Naveed Ahmad Yasir Javed Sampling Fingerprints From Multimedia Content Resource Clusters IEEE Access Algorithms convergence clustering divergence fingerprints multimedia |
| title | Sampling Fingerprints From Multimedia Content Resource Clusters |
| title_full | Sampling Fingerprints From Multimedia Content Resource Clusters |
| title_fullStr | Sampling Fingerprints From Multimedia Content Resource Clusters |
| title_full_unstemmed | Sampling Fingerprints From Multimedia Content Resource Clusters |
| title_short | Sampling Fingerprints From Multimedia Content Resource Clusters |
| title_sort | sampling fingerprints from multimedia content resource clusters |
| topic | Algorithms convergence clustering divergence fingerprints multimedia |
| url | https://ieeexplore.ieee.org/document/10360132/ |
| work_keys_str_mv | AT umerrashid samplingfingerprintsfrommultimediacontentresourceclusters AT samranaseer samplingfingerprintsfrommultimediacontentresourceclusters AT abdurrehmankhan samplingfingerprintsfrommultimediacontentresourceclusters AT muazzamakhan samplingfingerprintsfrommultimediacontentresourceclusters AT gauharali samplingfingerprintsfrommultimediacontentresourceclusters AT naveedahmad samplingfingerprintsfrommultimediacontentresourceclusters AT yasirjaved samplingfingerprintsfrommultimediacontentresourceclusters |