Abstract
The growing amount of image data (produced in a multitude of different ways – for example, like photo albums from various events) and lack of a direct search method for image information frequently create a situation in which end users of the service that publishes such data want to find themselves but cannot do it faster than looking through all entries one by one. The objective of this study is to develop and implement an approach that would be able to process this kind of data source and extract images similar to those provided by end-users in an on-demand manner. To this end, the modern methods for extract and compressing faces are introduced and applied.
Highlights
In the modern world, the large amount of data generated in different domains frequently aids the development of new data-driven products and using them to extract valuable insights from the acquired data
This problem has occurred at Astrakhan State University (ASU) – since this university hosts a wide variety of events, it employs a full-fledged news agency, which is fittingly named ASU Media [3]
Since ASU Media covers all major university events and most minor events, it has accumulated a large photo archive in a form of photo albums in VK – a prime Russian social network – and a wide interest from people related to ASU
Summary
The large amount of data generated in different domains frequently aids the development of new data-driven products and (even more importantly) using them to extract valuable insights from the acquired data. One of the practical setups – which is the key object of study in this paper – is a photo search in a photo album of an event (or, if the hosting organization is large enough, from multiple photo albums) This problem has occurred at Astrakhan State University (ASU) – since this university hosts a wide variety of events, it employs a full-fledged news agency, which is fittingly named ASU Media [3]. The motivation behind this complaint has frequently been a need to find professional photography of oneself – the stories are normally accompanied by the photo album made by ASU Media photographers To tackle this problem, the following solution has been proposed: Collect the relevant data from the news stories
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.