Navegando por Autor "Silva, Giani David"

Agora exibindo 1 - 3 de 3

SAPTE : a multimedia information system to support the discourse analysis and information retrieval of television programs.
(2015) Pereira, Moisés H. R.; Souza, Celso L. de; Pádua, Flávio Luis Cardeal; Silva, Giani David; Assis, Guilherme Tavares de; Pereira, Adriano César Machado
This paper presents a novel multimedia information system, called SAPTE, for supporting the discourse analysis and information retrieval of television programs from their corresponding video recordings. Unlike most common systems, SAPTE uses both content independent and dependent metadata, which are determined by the application of discourse analysis techniques as well as image and audio analysis methods. The proposed system was developed in partnership with the free-to-air Brazilian TV channel Rede Minas in an attempt to provide TV researchers with computational tools to assist their studies about this media universe. The system is based on the Matterhorn framework for managing video libraries, combining: (1) discourse analysis techniques for describing and indexing the videos, by considering aspects, such as, definitions of the subject of analysis, the nature of the speaker and the corpus of data resulting from the discourse; (2) a state of the art decoder software for large vocabulary continuous speech recognition, called Julius; (3) image and frequency domain techniques to compute visual signatures for the video recordings, containing color, shape and texture information; and (4) hashing and k-d tree methods for data indexing. The capabilities of SAPTE were successfully validated, as demonstrated by our experimental results, indicating that SAPTE is a promising computational tool for TV researchers.
Semiodiscursive analysis of TV newscasts based on data mining and image processing.
(2018) Conceição, Felipe Leandro Andrade; Pádua, Flávio Luis Cardeal; Pereira, Adriano César Machado; Assis, Guilherme Tavares de; Silva, Giani David; Andrade, Antonio Augusto Braighi
This work addresses the development of a novel computer-aided methodology for discourse analysis of TV newscasts. A TV newscast constitutes a particular type of discourse and has become a central part of the modern-day lives of millions of people. It is important to understand how this media content works and how it affects human life. To support the study of TV newscasts under the discourse analysis perspective, this work proposes a newscast structure to recover its main units and extract relevant data, named here as newscast discursive metadata (NDM). The NDM describes aspects, such as screen time and field size of newscasts’ participants and themes addressed. Data mining and image analysis methods are used to extract and analyze the NDM of a dataset containing 41 editions of two Brazilian newscasts. The experimental results are promising, demonstrating the effectiveness of the proposed methodology.
A unified approach to content-based indexing and retrieval of digital videos from television archives.
(2014) Souza, Celso L. de; Pádua, Flávio Luis Cardeal; Nunes, Cristiano Fraga Guimarães; Assis, Guilherme Tavares de; Silva, Giani David
This work addresses the development of a unified approach to content-based indexing and retrieval of digital videos from television archives. The proposed approach has been designed to deal with arbitrary television genres, making it suitable for various applications. To achieve this goal, the main steps of a content-based video retrieval system are addressed in this work, namely: video segmentation, key-frame extraction, content-based video indexing and the video retrieval operation itself. Video segmentation is addressed as a typical TV broadcast structuring problem, which consists in automatically determining the boundaries of each broadcasted program (like movies, news, among others) and inter-program (for instance, commercials). Specifically, to segment the videos, Electronic Program Guide (EPG) metadata is combined with the detection of two special cues, namely, audio cuts (silence) and dark monochrome frames. On the other hand, a color histogram-based approach performs key-frame extraction. Video indexing and retrieval are accomplished by using hashing and k-d tree methods, while visual signatures containing color, shape and texture information are estimated for the key-frames, by using image and frequency domain techniques. Experimental results with the dataset of a multimedia information system especially developed for managing television broadcast archives demonstrate that our approach works efficiently, retrieving videos in 0.16 seconds on average and achieving recall, precision and F1 measure values, as high as 0.76, 0.97 and 0.86 respectively.