PROJECT TITLE :

Capturing Spatial Interdependence in Image Features: The Counting Grid, an Epitomic Representation for Bags of Features

ABSTRACT:

In recent scene recognition research pictures or giant image regions are usually represented as disorganized “bags” of features that will then be analyzed using models originally developed to capture co-variation of word counts in text. But, image feature counts are probably to be constrained in numerous ways than word counts in text. For instance, as a camera pans upwards from a building entrance over its 1st few floors and then any up into the sky Fig. one Fig. 1. Feature counts change slightly as the sphere of view moves. For example, the abundance of the “automobile” options is reduced, however the counts of the features found on building facades are increased. The counting grid model accounts for such changes naturally, and it will conjointly account for pictures of various scenes.