A Locally Adapting Technique for Boundary Detection using Image Segmentation
This work addresses the need for precise boundary detection in quantitative digital image analysis, such as measuring material density or shockwave velocity, but appears incremental as it builds on existing segmentation techniques with added uncertainty quantification.
The paper tackles the problem of detecting object boundaries in images with overlapping intensity histograms by presenting a supervised image segmentation method that incorporates spatial information and uses maximum likelihood estimation to quantify uncertainty. It demonstrates success on radiograph and optical images, providing boundary locations with uncertainty bands.
Rapid growth in the field of quantitative digital image analysis is paving the way for researchers to make precise measurements about objects in an image. To compute quantities from the image such as the density of compressed materials or the velocity of a shockwave, we must determine object boundaries. Images containing regions that each have a spatial trend in intensity are of particular interest. We present a supervised image segmentation method that incorporates spatial information to locate boundaries between regions with overlapping intensity histograms. The segmentation of a pixel is determined by comparing its intensity to distributions from local, nearby pixel intensities. Because of the statistical nature of the algorithm, we use maximum likelihood estimation theory to quantify uncertainty about each boundary. We demonstrate the success of this algorithm on a radiograph of a multicomponent cylinder and on an optical image of a laser-induced shockwave, and we provide final boundary locations with associated bands of uncertainty.