Abstract
This paper presents news video retrieval using text query for Gujarati language news videos. Due to the fact that Broadcasted Video in India is lacking in metadata information such as closed captioning, transcriptions etc., retrieval of videos based on text data is trivial task for most of the Indian language video. To retrieve specific story based on text query in regional language is the key idea behind our approach. Broadcast video is segmented to get shots representing small news stories. To represent each shot efficiently, key frame extraction using singular value decomposition and rank of matrix is proposed. Text is extracted from keyframes for further indexing data. Next task is to process text using natural language processing steps like tokenization, punctuation and extra symbols removal as well as stemming of words to root words etc. Due to unavailability of stemming and other methods of preprocessing of text in Guajarati language, we have given basic stemming technique to reduce dictionary size for efficient indexing of text data. With proposed system 82.5 percent accuracy is achieved on Gujarati news video dataset ETV.
Highlights
In this era of Digital information, it is required to have intelligent analysis of digital information present in multimedia data
The approach of text query-based video retrieval is mainly divided in three submodules
We have proposed text query-based video retrieval from Guajarati language news video dataset
Summary
In this era of Digital information, it is required to have intelligent analysis of digital information present in multimedia data. Video clip or shots can be considered as a document for indexing and retrieval task. Features of images, objects of images or content of document are used for indexing the data. The time domain feature vectors of video are calculated generally by dividing video sequence into segments like shots, scenes, frames etc. Once shot boundary is decided, task is to extract features like texture, histograms, moments, motion vectors, text, etc. We have proposed text-based approach by providing query as text and searching through the dataset of videos based on textual content available as scene text or frame text. The approach of text query-based video retrieval is mainly divided in three submodules. Our key contributions are Key Frame Extraction method and Stemming of Gujarati Text and retrieval based on it.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
