Comparison of Global Histogram Methods for 2D and 3D Entropy Based Image Segmentation

摘要

In this paper we explain two functional models for entropy based image segmentation: using global 2D and 3D image histograms of grayscale images. We compare results obtained by both methods for different type of images such as: biomedical and micro objects, digital video records and natural photographs. Short introduction of multistage gradient 3D entropy segmentation for texture analysis is also introduced. 2D and 3D entropy segmented images can be combined to achieve better results in applications such as digital video databases and multimedia information retrieval frameworks, micro object classification for material analysis and biomedical applications.