Please use this identifier to cite or link to this item:
http://univ-bejaia.dz/dspace/123456789/20807
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Amrane, Abdesalam | - |
dc.contributor.author | Meziane, Abdelkrim;promoteur | - |
dc.date.accessioned | 2022-12-19T13:44:01Z | - |
dc.date.available | 2022-12-19T13:44:01Z | - |
dc.date.issued | 2022 | - |
dc.identifier.other | 004D/149 | - |
dc.identifier.uri | http://univ-bejaia.dz/dspace/123456789/20807 | - |
dc.description | Option :réseaux et systémes de distribués | en_US |
dc.description.abstract | Information extraction from multimedia content is a challenging task. In this thesis, we present an architecture of multimedia contents classification system that provides different phases to extract semantic information from broadcasted streams, starting with the segmentation process, news topics extraction, and advertisement detection and classification. Next, we give an extension to our framework and describes an audio-based hybrid model for content classification combining different deep neural networks with auto-encoder applied to advertisement detection in TV broadcast. Our models achieve high levels of precision. The last contribution consists of a distributed architecture based on the Kafka and Spark frameworks which offer parallel processing of TV streams, we demonstrate through this work the scalability and robustness of this architecture. | en_US |
dc.language.iso | en | en_US |
dc.publisher | université Abderahman Mira Bejaia | en_US |
dc.subject | Multimedia processing: Parallel processing:Deep learning:TV stream | en_US |
dc.title | Multimedia Content Classification in the Cloud | en_US |
dc.type | Thesis | en_US |
Appears in Collections: | Thèses de Doctorat |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
thesis_amrane.pdf | 2.53 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.