M
Matthew J. Thurley
Researcher at Luleå University of Technology
Publications - 39
Citations - 698
Matthew J. Thurley is an academic researcher from Luleå University of Technology. The author has contributed to research in topics: Mathematical morphology & Pellets. The author has an hindex of 13, co-authored 39 publications receiving 607 citations. Previous affiliations of Matthew J. Thurley include Monash University.
Papers
More filters
Journal ArticleDOI
Morphology-Based Crack Detection for Steel Slabs
TL;DR: The results provide proof-of-concept for a fully automated crack detection system based on the presented method, utilizing morphological image processing and statistical classification by logistic regression based on 3D profile data of steel slab surfaces.
Journal ArticleDOI
Automated online measurement of limestone particle size distributions using 3D range data
TL;DR: In this paper, the size distribution of piled limestone particles on conveyor belt is measured using 3D range data collected every minute during 13h of production, and 3D data from laser triangulation is used to provide high resolution data of the surface of the piled limestone particle.
Journal ArticleDOI
Identifying, visualizing, and comparing regions in irregularly spaced 3D surface data
Matthew J. Thurley,Kim Chew Ng +1 more
TL;DR: 3D coordinate surface data can now be morphologically processed directly in 3D, segmented, visualized, and directly compared to the actual surface fragmentation in order to quantify the results.
Journal ArticleDOI
An industrial 3D vision system for size measurement of iron ore green pellets using morphological image segmentation
TL;DR: In this paper, a 3D imaging and analysis system was developed that measured the pellet sieve size distribution into nine sieve sizes between 5 and 16+ mm, and determined the entirely visible (overlapped) particles based on their limited visible profile.
Journal ArticleDOI
Fast Morphological Image Processing Open-Source Extensions for GPU Processing With CUDA
Matthew J. Thurley,V. Danell +1 more
TL;DR: The vHGW algorithm for erosion and dilation independent of structuring element size has been implemented for horizontal, vertical, and 45 degree line structuring elements with significant performance improvements over NPP, however, memory handling limitations hinder performance in the vertical line case.