Research on machine learning technologies to extract text from videos for the MYTV service search system | |
| Author | Giang Anh Duc |
| Call Number | AIT Project no.PMDS-22-05 |
| Subject(s) | Deep learning (Machine learning) Television broadcasting--Vietnam--Data processing Content analysis (Communication)--Data processing |
| Note | A project study submitted in partial fulfillment of the requirements for the degree of Professional Master in Data Science and Artificial Intelligence Applications, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Project ; no. PMDS-22-05 |
| Abstract | Metadata is an important data source in content management. It is extracted from the videos to enrich the data source for search and analysis to serve users better. However, in VNPT's MyTV service, the content management administrator manually enters the metadata data source, possibly creating erroneous content. This leads to a need for more rich data sources from automatic methods. The thesis topic will research and apply Deep learning techniques to automatically extract Text from existing video sources of MyTV. Text information appearing in videos and images will be filtered and added to VNPT's Bigdata data warehouse. And the text extract will be used for groups and categorized into Metadata in further work. The potential to increase the number of new customers and enrich and diversify the content repository to retain old customers is a difficult task for MyTV. The quality of services developed on the Bigdata platform, such as content recommendations, user personalization, and integrated advertising, depends on the thickness and accuracy of content data. Therefore, extracting the hidden data in the video content is necessary to help enrich the Bigdata data warehouse, quickly deploy service integration, increase customer experience, and reduce the churn rate. |
| Year | 2022 |
| Corresponding Series Added Entry | Asian Institute of Technology. Project ; no. PMDS-22-05 |
| Type | Project |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Professional Master in Data Science and Artificial Intelligence Applications (PMDS) |
| Chairperson(s) | Dailey, Matthew N.; |
| Examination Committee(s) | Chutiporn Anutariya;Chaklam Silpasuwanchai; |
| Degree | Professional Master in Data Science and Artificial Intelligence Applications - Asian Institute of Technology, 2022 |