Identification of objects from image regions

Abstract

Over-segmentation could be relieved by adopting a divisive image segmentation model. This also requires the binary classification of whether a segmented region corresponds to a single semantic object. In this paper, we propose a model to address this classification problem, by detecting if a region contains both "background" and "foreground" regions. When "background" and "foreground" both present, the region is considered to have multiple objects, otherwise it corresponds to a single object. We implement the model based on certain image features of the region that effectively tell the difference between "background" and "foreground". Experiments show that our model can effectively perform the classification tasks.