Uniform Information Segmentation
This addresses the challenge of balancing detail preservation and simplification in image segmentation for computer vision applications, representing a novel approach rather than an incremental improvement.
The paper tackles the problem of image segmentation by proposing a criterion of information uniformity instead of size uniformity, leading to segments that adapt to image complexity and preserve details. The method proves superior to state-of-the-art on benchmarks and is computationally efficient, approaching real-time performance.
Size uniformity is one of the main criteria of superpixel methods. But size uniformity rarely conforms to the varying content of an image. The chosen size of the superpixels therefore represents a compromise - how to obtain the fewest superpixels without losing too much important detail. We propose that a more appropriate criterion for creating image segments is information uniformity. We introduce a novel method for segmenting an image based on this criterion. Since information is a natural way of measuring image complexity, our proposed algorithm leads to image segments that are smaller and denser in areas of high complexity and larger in homogeneous regions, thus simplifying the image while preserving its details. Our algorithm is simple and requires just one input parameter - a threshold on the information content. On segmentation comparison benchmarks it proves to be superior to the state-of-the-art. In addition, our method is computationally very efficient, approaching real-time performance, and is easily extensible to three-dimensional image stacks and video volumes.