| Summary: | This thesis is concerned with a novel local threshold segmentation algorithm for digital images incorporating
shape information. In image segmentation, most local threshold algorithms are based only on intensity analysis. In many applications where an image contains objects with a similar shape, in addition to the intensity information, some prior known shape attributes could be exploited
to improve the segmentation. The goal of this work is to design a local threshold algorithm that includes shape information to enhance the segmentation quality. The algorithm adaptively selects a local threshold. Shape attribute distributions are learned from typical objects in ground truth images. Local threshold for each object in an image to be segmented is chosen to maximize probabilities in
these shape attributes distributions. Then for the application of the oil sand image segmentation, a supervised classifier is introduced to further enhance the segmentation accuracy. The algorithm applies a supervised classifier trained by shape features to reject unwanted fragments. To meet different image segmentation intents in practical applications, we investigate a variety of combination of shape attributes and classifiers, and also look for the optimal one. Experiments on oil sand images
have shown that the proposed algorithm has superior performance to local threshold approaches based on intensity information in terms of segmentation quality.
|
|---|
