PROJECT TITLE :
Massive-scale learning of image and video semantic concepts
Rapid growth in the capture and generation of images and videos is driving the requirement for more economical and effective systems for analyzing, searching, and retrieving this knowledge. Specific challenges embrace supporting automatic content indexing at a massive scale and accurately extracting a sufficiently giant range of relevant semantic ideas to enable effective search. In this paper, we tend to describe the event of a system for large-scale visual semantic concept extraction and learning for pictures and video. The system models the visual semantic space employing a hierarchical faceted classification theme across objects, scenes, individuals, activities, and events and utilizes a unique machine learning approach that creates ensemble classifiers from automatically extracted visual features. The ensemble learning and extraction processes are easily parallelizable for distributed processing using Hadoop® and IBM InfoSphere® Streams, which enable economical processing of enormous information sets. We report on varied applications and quantitative and qualitative results for different image and video information sets.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here