Maven Video Repository: A Visually Classified and Tagged Video Repository
WEB 2.0’s accelerated growth has paved a way for the emergence of social video sharing platforms. These video sharing communities produce videos at an exponential rate. Unfortunately, these videos are incongruously tagged, leading to minimal amount of met
- PDF / 319,657 Bytes
- 11 Pages / 439.37 x 666.142 pts Page_size
- 67 Downloads / 180 Views
Abstract WEB 2.0’s accelerated growth has paved a way for the emergence of social video sharing platforms. These video sharing communities produce videos at an exponential rate. Unfortunately, these videos are incongruously tagged, leading to minimal amount of metadata to retrieve them. Categorizing and indexing these videos has become a pressing problem for these communities. Videos generated by these communities depend on users to tag them, thus they end up being loosely tagged. An innovative and novel application has been presented to classify and tag these large volumes of user-generated videos. The above proposed content-based automatic tagging application tags the videos, which further help in indexing and classifying them. This application first recognizes the person in the video and then discerns their emotions and then creating a MPEG-7 xml file to store the metadata. This application will drastically reduce human effort and radically increase the efficiency of video searching. Keywords Video classification videos Emotion recognition
⋅
⋅
Automatic video tagging
⋅
Face recognition in
P. Sahay (✉) ⋅ I. Chugh ⋅ R. Gupta ⋅ R. Kumar Computer Science Department, Amity University, Noida, Uttar Pradesh, India e-mail: [email protected] I. Chugh e-mail: [email protected] R. Gupta e-mail: [email protected] R. Kumar e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2018 S.C. Satapathy et al. (eds.), Data Engineering and Intelligent Computing, Advances in Intelligent Systems and Computing 542, DOI 10.1007/978-981-10-3223-3_37
385
386
P. Sahay et al.
1 Introduction Unprecedented growth of multimedia-sharing communities has led to exponential boom of videos. An analysis conducted by Google states that 300 h of videos are uploaded online every minute. Videos presently are being tagged by users. This process of tagging or adding meta-data (data about data) is cumbersome and time consuming. People are generally indolent to add desirable information about the video thus leading to poor information about the video. Video searches are dependent upon this information provided about the videos, to retrieve them when appropriate keywords are used to search them. Henceforth when this information provided is poor or less than adequate, classification or retrieval of videos becomes difficult [1]. ‘Folksonomy’ is a term coined for tagging or associating online documents with specific keywords to help finding and re-finding these documents later on. This keyword-document association is called tagging. It is a kind of media-knowledge extraction. These tags associated with the documents such as images and videos provide cumulative information about the document. Henceforth tagging videos with appropriate metadata has become need of hour to ease the process of video retrieval. Through this paper we combat this problem by use of automatic tag generating application. This application first detects the key-frames, followed by face recognition and emotion recognition. Resulting data from this process is compiled to f
Data Loading...
