Soil image segmentation and texture analysis: a computer vision approach

Automated processing of digitized soilsection images reveals elements of soil structure and draws primary estimates of bioecological importance, like ground fertility and changes in terrestrial ecosystems. We examine a sophisticated integration of some modern methods from computer vision for image feature extraction, texture analysis, and segmentation into homogeneous regions, relevant to soil micromorphology. First, we propose the use of a morphological partial differential equation-based segmentation scheme based on seeded region-growing and level curve evolution with speed depending on image contrast. Second, we analyze surface texture information by modeling image variations as local modulation components and using multifrequency filtering and instantaneous nonlinear energy-tracking operators to estimate spatial modulation energy. By separately exploiting contrast and texture information, through multiscale image smoothing, we propose a joint image segmentation method for further interpretation of soil images and feature measurements. Our experimental results in images digitized under different specifications and scales demonstrate the efficacy of our proposed computational methods for soil structure analysis. We also briefly demonstrate their applicability to remote sensing images.

I. Introduction

Image data in geosciences are common and require processing and measurement schemes that range from small microscopic scales to large remote sensing scales. In this work, we focus mainly to the first category and specifically in images of thin soilsections. The goal of soil micromorphology, as a branch of soil science, is the description, interpretation, and measurement of components, features, and fabrics in soils at a microscopic level. Basic soil components are the individual particles (e.g., quartz grains, clay minerals, plant fragments) that can be resolved with the optical microscope together with the fine material that is unresolved into discrete individuals. Soil structure is concerned with the size, shape, sharpness, contrast, frequency, and spatial arrangement of primary particles and voids. Many of these characteristics are a function of the orientation of components and the direction in which they are cut as well as of the magnification used. Soilsection images produced via a digitizing procedure, using conventional scanners, cameras, or microscopes under polarized light, exhibit a great variety of geometric features. Important image features that provide useful information for soil structure quality evaluation include cluster/particle shape, either one-dimensional (1-D), such as edges or curves, or two-dimensional (2-D), such as light or dark blobs (small homogeneous regions of random shape), spatial arrangement of soil components, and their texture.