Grant: Discovery Grants Program - Individual

Over the last four decades, the development of image segmentation algorithms has been an area of considerable research activity. The reason for such significant attention to this problem lies in its practical importance. Image segmentation is a key step towards high-level tasks such as image understanding and serves in a wide range of applications including object recognition, scene analysis or content-based image/video retrieval. Many image segmentation algorithms have been elaborated. However, strong segmentation, which corresponds to a partitioning of an image's pixels into regions that are semantically meaningful to people, remains a difficult and as yet largely unsolved problem. Most image segmentation algorithms extract regions satisfying some uniformity (homogeneity) criterion, which is based on low-level data-driven visual features (e.g., color, texture). Unfortunately, homogeneous regions do not necessarily (and usually do not) correspond to semantically meaningful objects. This is mainly caused by the disconnection between low-level visual features and high-level semantics, which is commonly referred to as the semantic gap. This has motivated researchers to develop image segmentation methods that, by introducing high-level knowledge into the segmentation process, can break through the performance ceiling imposed by the semantic gap. The main disadvantage of those methods is their lack of flexibility due to the assumption that such knowledge is provided in advance, which heavily restricts the application domain. The main objective of the proposed research is to develop image segmentation strategies which, through the use of machine learning, generate and incorporate high-level knowledge into the segmentation process.