國立虎尾科技大學 |

Multimedia Data Extraction and Analysis Tool: Focus on Video and Image Processing /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Multimedia Data Extraction and Analysis Tool: Focus on Video and Image Processing // Joao Miguel Teixeira Braganca.
作者:	Braganca, Joao Miguel Teixeira,
面頁冊數:	1 electronic resource (86 pages)
附註:	Source: Masters Abstracts International, Volume: 86-08.
Contained By:	Masters Abstracts International86-08.
標題:	Computer engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31857646
ISBN:	9798304932370

Multimedia Data Extraction and Analysis Tool: Focus on Video and Image Processing /
Braganca, Joao Miguel Teixeira,

Multimedia Data Extraction and Analysis Tool: Focus on Video and Image Processing /Joao Miguel Teixeira Braganca. - 1 electronic resource (86 pages)

Source: Masters Abstracts International, Volume: 86-08.

In today's digital landscape, the rapid growth of multimedia content, particularly from influencers, has created a critical need for advanced monitoring tools. Building on previous research in multimedia data analysis, this dissertation proposes the development of a tool for extracting and analysing multimedia data to detect violations in influencer-produced content. The tool leverages pre-trained models such as Whisper.AI for speech recognition, YOLOv8 for object detection, and EasyOCR for Optical Character Recognition (OCR). Additionally, sentiment analysis models are employed and tested, with YOLOv8 further trained for specific tasks such as logo detection, ensuring adaptability to various use cases.The objective of this dissertation is to design a versatile and customizable tool capable of performing precise content analysis, including object detection, speech transcription, OCR, sentiment analysis, image classification and logo detection. The solution will be cloud-based, ensuring scalability and the ability to process large datasets.

English

ISBN: 9798304932370Subjects--Topical Terms:

569006
Computer engineering.
Subjects--Index Terms:

Multimedia data analysis

Multimedia Data Extraction and Analysis Tool: Focus on Video and Image Processing /
LDR:03647nam a22003973i 4500 001 1157895
005 20250603111437.5
006 m o d
007 cr|nu||||||||
008 250804s2024 miu||||||m |||||||eng d
020 $a 9798304932370
035 $a (MiAaPQD)AAI31857646
035 $a (MiAaPQD)104002226891
035 $a AAI31857646
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Braganca, Joao Miguel Teixeira, $e author. $3 1484185
245 1 0 $a Multimedia Data Extraction and Analysis Tool: Focus on Video and Image Processing / $c Joao Miguel Teixeira Braganca.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (86 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 86-08.
500 $a Advisors: Da Silva, Fabio Andre Souto.
502 $b Master's $c Instituto Politecnico do Porto (Portugal) $d 2024.
520 $a In today's digital landscape, the rapid growth of multimedia content, particularly from influencers, has created a critical need for advanced monitoring tools. Building on previous research in multimedia data analysis, this dissertation proposes the development of a tool for extracting and analysing multimedia data to detect violations in influencer-produced content. The tool leverages pre-trained models such as Whisper.AI for speech recognition, YOLOv8 for object detection, and EasyOCR for Optical Character Recognition (OCR). Additionally, sentiment analysis models are employed and tested, with YOLOv8 further trained for specific tasks such as logo detection, ensuring adaptability to various use cases.The objective of this dissertation is to design a versatile and customizable tool capable of performing precise content analysis, including object detection, speech transcription, OCR, sentiment analysis, image classification and logo detection. The solution will be cloud-based, ensuring scalability and the ability to process large datasets.
520 $a No panorama digital atual, o rapido crescimento de conteudos multimedia, particularmente de influencers, criou uma necessidade critica de ferramentas avancadas de mon-itorizacao. Com base em investigacoes anteriores na analise de dados multimedia, esta dissertacao propoe o desenvolvimento de uma ferramenta para extrair e analisar dados multimedia, com o objetivo de detetar violacoes em conteudos produzidos por influencers. A ferramenta utiliza modelos pre-treinados, como o Whisper.AI para reconhecimento de fala, o YOLOv8 para detecao de objetos e o EasyOCR para extracao de texto. Adicional-mente, sao utilizados e testados modelos de analise de sentimentos, sendo o YOLOv8 ainda treinado para tarefas especificas, como a detecao de logotipos, assegurando a adaptabili-dade a varios casos de uso. O objetivo principal desta dissertacao e conceber uma ferramenta versatil e personalizavel, capaz de realizar analises de conteudo precisas, incluindo detecao de objetos, transcricao de fala, reconhecimento otico de caracteres, analise de sentimentos, classificacao de ima-gens e detecao de logotipos. A solucao sera baseada na cloud, garantindo escalabilidade e a capacidade de processar grandes volumes de dados.
546 $a English
590 $a School code: 7013
650 4 $a Computer engineering. $3 569006
650 4 $a Information retrieval. $3 563691
650 4 $a Speech. $3 566021
650 4 $a Tagging. $3 1484186
650 4 $a User generated content. $3 1466903
650 4 $a Voice recognition. $3 1413635
650 4 $a Video recordings. $3 812709
650 4 $a Multimedia. $2 gtt $3 655239
650 4 $a Sentiment analysis. $3 1403973
650 4 $a Deep learning. $3 1127428
650 4 $a Violations. $3 1372548
653 $a Multimedia data analysis
653 $a Object detection
690 $a 0464
710 2 $a Instituto Politecnico do Porto (Portugal). $3 1466867
720 1 $a Da Silva, Fabio Andre Souto $e degree supervisor.
773 0 $t Masters Abstracts International $g 86-08.
790 $a 7013
791 $a Master's
792 $a 2024
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31857646