Robust Image Segmentation Technique for Fragmentation Analysis
Fragmentation analysis of blast or crushed rock material is a time consuming and costly process. During the last two decades mining industries have been investigating image based analysis systems as an alternative to generate fragmentation results. Mining industries have recently begun using some commercially available software tools for real-time estimation of size distributions. Some existing systems require hours of manual editing of a partially segmented image for creating edges (or net) before executing the blob analysis routine. This paper describes a novel software application, which has the capability to capture images and analyze sequentially to generate the particle size distribution without any manual interventions. The system can process a batch of images captured during a fixed duration of time and produce the overall particle size distribution. The new method has different layers of segmentation modules, which allows the system to respond to a wide range of rock textures and lighting conditions. A new grey level slicing technique is developed which can perform under a range of illuminating conditions. The Canny based edge detection technique is used to segment rocks appearing in dark regions. The results are compared against a commercially available method and presented in this paper.
Mots Clés:
Fragmentation analysis, Size distribution, Grey-level slicing, image segmentation, automated image processing, Canny edge detector
