Image processing for materials characterization: Issues, challenges and opportunities

Duval, Laurent; Moreaud, Maxime; Jeulin, Dominique; Talbot, Hugues; Angulo, Jesús

doi:10.1109/icip.2014.7025985

Cited by 18 publications

(12 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead of finding each maximin edge ( 2 ) times, we can calculate how many times each MST edge appears in the sum, which can be calculated with a modification of Kruskal's minimum spanning tree algorithm. In recent work we presented pseudo-code based on the disjoint set data-structures [25].…”

Section: Supervised Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Segmentation and learning in the quantitative analysis of microscopy images

2015

View full text Add to dashboard Cite

In material science and bio-medical domains the quantity and quality of microscopy images is rapidly increasing and there is a great need to automatically detect, delineate and quantify particles, grains, cells, neurons and other functional "objects" within these images. These are challenging problems for image processing because of the variability in object appearance that inevitably arises in real world image acquisition and analysis. One of the most promising (and practical) ways to address these challenges is interactive image segmentation. These algorithms are designed to incorporate input from a human operator to tailor the segmentation method to the image at hand. Interactive image segmentation is now a key tool in a wide range of applications in microscopy and elsewhere. Historically, interactive image segmentation algorithms have tailored segmentation on an image-by-image basis, and information derived from operator input is not transferred between images. But recently there has been increasing interest to use machine learning in segmentation to provide interactive tools that accumulate and learn from the operator input over longer periods of time. These new learning algorithms reduce the need for operator input over time, and can potentially provide a more dynamic balance between customization and automation for different applications. This paper reviews the state of the art in this area, provides a unified view of these algorithms, and compares the segmentation performance of various design choices.

show abstract

Section: Supervised Segmentationmentioning

confidence: 99%

“…Accurate segmentation of materials images introduces additional challenges to those encountered in other domains (e.g. bio-medical) and has been the topic of a recent special session [2] and recent references [3,4]. Some of these challenges include:…”

Section: Introductionmentioning

confidence: 98%

Segmentation and learning in the quantitative analysis of microscopy images

2015

View full text Add to dashboard Cite

show abstract

“…It uses modal convolution to describe the CNN and uses it to extract inter‐modal and modal information and fuse features at the pixel level. Couprie et al 20 proposed a multi‐scale CNN for RGB‐D scene markers based on hierarchical feature method. Liao et al designed a static gesture recognition system combining depth image and color image, 21 using depth image and color image acquired by Realsense, combined with generalized Hough transform to map depth image to color image.…”

Section: Related Workmentioning

confidence: 99%

Gesture recognition based on multi‐modal feature weight

Duan

Sun

Cheng

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Summary With the continuous development of sensor technology, the acquisition cost of RGB‐D images is getting lower and lower, and gesture recognition based on depth images and Red‐Green‐Blue (RGB) images has gradually become a research direction in the field of pattern recognition. However, most of the current processing methods for RGB‐D gesture images are relatively simple, ignoring the relationship and influence between its two modes, and unable to make full use of the correlation factors between different modes. In view of the above problems, this paper optimizes the effect of RGB‐D information processing by considering the independent features and related features of multi‐modal data to construct a weight adaptive algorithm to fuse different features. Simulation experiments show that the method proposed in this paper is better than the traditional RGB‐D gesture image processing method and the gesture recognition rate is higher. Comparing the current more advanced gesture recognition methods, the method proposed in this paper also achieves higher recognition accuracy, which verifies the feasibility and robustness of this method.

show abstract

“…The overlap of grayscale values between particle and matrix is displayed in the histogram in Figure 5c. The parameterization for all three segmentation methods for the René 104 image are as follows: the Otsu thresholding value was determined to be 0.498, the energy exchange parameter for EM/MPM ( β in reference Duval et al (2014)) was found to be 1.7, with 5 iteration/segmentation loops performed, and the graph-cutting procedure had values of λ = 6.0, β = 0, α γ = 1.0, ω γ = 1 e −2 , α γ = 1.0 and , respectively. The ground truth image was obtained through meticulous use of MS Paint.…”

Section: Image Segmentationmentioning

confidence: 99%

“…The analysis and post-processing of materials characterization datasets are often more challenging and time-consuming than the acquisition of the raw data (Duval et al, 2014). For example, image segmentation, or the problem of automatically separating and classifying features of interest from the background, is a common analysis task where it is trivial to complete by the human eye but often difficult for a computer to reliably and repeatably accomplish.…”

Section: Introductionmentioning

confidence: 99%

Application of the Maximum Flow–Minimum Cut Algorithm to Segmentation and Clustering of Materials Datasets

et al. 2019

View full text Add to dashboard Cite

Problems involving image segmentation, atomic cluster identification, segmentation of microstructure constituents in images and austenite reconstruction have seen various approaches attempt to solve them with mixed results. No single computational technique has been able to effectively tackle these problems due to the vast differences between them. We propose the application of graph cutting as a versatile technique that can provide solutions to numerous materials data analysis problems. This can be attributed to its configuration flexibility coupled with the ability to handle noisy experimental data. Implementation of a Bayesian statistical approach allows for the prior information, based on experimental results and already ingrained within nodes, to drive the expected solutions. This way, nodes within the graph can be grouped together with similar, neighboring nodes that are then assigned to a specific system with respect to calculated likelihoods. Associating probabilities with potential solutions and states of the system allows for quantitative, stochastic analysis. The promising, robust results for each problem indicate the potential usefulness of the technique so long as a network of nodes can be effectively established within the model system.

show abstract

Image processing for materials characterization: Issues, challenges and opportunities

Cited by 18 publications

References 51 publications

Segmentation and learning in the quantitative analysis of microscopy images

Segmentation and learning in the quantitative analysis of microscopy images

Gesture recognition based on multi‐modal feature weight

Application of the Maximum Flow–Minimum Cut Algorithm to Segmentation and Clustering of Materials Datasets

Contact Info

Product

Resources

About