Image Segmentation, Compression and Reconstruction from Edge Distribution Estimation with Random Field and Random Cluster Theories
This work addresses image processing challenges for applications like compression and object detection, but appears incremental as it builds on existing theories with a custom deep belief network.
The paper tackled image segmentation and compression by estimating the smallest bounded region within an image using random field and random cluster theories, resulting in a compression method that requires slightly more than half of all pixels for worst-case reconstruction.
Random field and random cluster theory are used to describe certain mathematical results concerning the probability distribution of image pixel intensities characterized as generic $2D$ integer arrays. The size of the smallest bounded region within an image is estimated for segmenting an image, from which, the equilibrium distribution of intensities can be recovered. From the estimated bounded regions, properties of the sub-optimal and equilibrium distributions of intensities are derived, which leads to an image compression methodology whereby only slightly more than half of all pixels are required for a worst-case reconstruction of the original image. A custom deep belief network and heuristic allows for the unsupervised segmentation, detection and localization of objects in an image. An example illustrates the mathematical results.