Indoor Scene Classification
Session: 2011-12-II Semester
Advisor: Prof. Amitabha Mukerjee
Anuja Ranjan Y9113
Manav Garg 10379
Proposal
Presentation
Report
Code implementing Espinace's approach
Codes & Results implementing our approach
ABSTRACT
Scene classication has now become an active area of research. A lot of work has been done
on classifying images into outdoor and indoor categories however, current approaches for scene
recognition show a signicant drop in performance for the case of indoor scenes. Classifying
indoor scenes is a challenging task due to the large variation across different examples within
each class and similarities between different classes.Besides spacial properties it requires us to
see the objects they contain. Exploiting this idea we
present a new procedure to classify real world indoor scenes.Here we learn object classifiers with
Gist features and use them to find objects in the scene and then classify them.