A histogram-based segmentation method for characterization of self-assembled hexagonal lattices

2013 IEEE International Conference on Image Processing

Choi

2013

Quantitative analysis of nanostructures from scanning electron microscope (SEM) images requires a clear segmentation of grains and their boundaries. This is not provided by active contour models, which also require user guidance. Our automatic technique creates a rough representation of grain boundaries by adaptive thresholding. It then performs raycasting from a rectangular grid of seed points to ensure that the grain shapes are convex, and selects the best result for each grain. The whole process can be repeated several times to improve the segmentation. We present results for images of titanium foil, which show that our approach compares favorably in terms of speed and segmentation quality with four competing techniques.

Section: Introductionmentioning

confidence: 96%

Grain-oriented segmentation of scanning electron microscope images

2013 IEEE International Conference on Image Processing

Choi

2013

2015 Chinese Automation Congress (CAC)

“…Common methods for image threshold segmentation are histogram segmentation [3], OTSU [4], fuzzy clustering [5], and neural network [6], [7]. Research on the maximum entropic segmentation method began in 1985 by Kapur [8].…”

Section: Introductionmentioning

confidence: 99%

Discrete Quantum-Behaved Particle Swarm Optimization for 2-D maximum entropic multilevel thresholding image segmentation

Xu¹,

Mu²,

Ma³

2015

This paper presents an improved discrete quantum particle swarm optimization (IDQPSO) for 2-D maximum entropic multi-threshold image segmentation algorithm. Firstly, particle swarm binary-encoded method based on 2-D threshold is proposed. Additionally, new particle evolution strategy is proposed to avoid converging on local optimum and accelerate searching progress. Additionally, experiments are conducted by comparing IDQPSO with other state-of-the-art methods such as QGA, NBPSO and BQPSO. The results show that IDPQSO outperforms other algorithms at precision, efficiency and stability.

“…In the past few years, many researchers have quantitatively analysed the porous structure images using simple segmentation methods such as fuzzy thresholding using entropy (Matefi-Tempfli et al, 2008) and adaptive thresholding based on histogram (Abdollahifard et al, 2011), which can identify each entity with ease. Matefi-Tempfli et al also suggested an order-characterized analysis of nanoporous aluminium oxide using triangles and symmetric regular hexagons.…”

Section: Introductionmentioning

confidence: 99%

Grain‐oriented segmentation of images of porous structures using ray casting and curvature energy minimization

Choi

2014

Journal of Microscopy

We segment an image of a porous structure by successively identifying individual grains, using a process that requires no manual initialization. Adaptive thresholding is used to extract an incomplete edge map from the image. Then, seed points are created on a rectangular grid. Rays are cast from each point to identify the local grain. The grain with the best shape is selected by energy minimization, and the grain is used to update the edge map. This is repeated until all the grains have been recognized. Tests on scanning electron microscope images of titanium oxide and aluminium oxide show that their process achieves better results than five other contour detection techniques.