Interactive max-tree visualization tool for image processing and analysis

Tavares, Luís Antônio; Souza, Roberto; Rittner, Letícia; Machado, Rubens; Lotufo, Roberto de Alencar

doi:10.1109/ipta.2015.7367110

Cited by 9 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Those relations are organised in graphs or trees containing large numbers of nodes (e.g. even in a relatively small image like Figure (A), threshold decomposition generates 27 622 dark and 28 648 bright regions with 39 378 and 40 363 boundaries, respectively) and this makes it difficult to represent and visualise in graph form or to be processed interactively (Tavares et al ., ). MSER has been used for extraction of regions (extremal regions), which are stable (in terms of intensity or size) over a range of threshold values (Matas et al ., ).…”

Section: Discussionmentioning

confidence: 97%

Automatic thresholding from the gradients of region boundaries

Landini

Randell

Fouad

et al. 2016

Journal of Microscopy

View full text Add to dashboard Cite

We present an approach for automatic threshold segmentation of greyscale images. The procedure is inspired by a reinterpretation of the strategy observed in human operators when adjusting thresholds manually and interactively by means of 'slider' controls. The approach translates into two methods. The first one is suitable for single or multiple global thresholds to be applied globally to images and consists of searching for a threshold value that generates a phase whose boundary coincides with the largest gradients in the original image. The second method is a variation, implemented to operate on the discrete connected components of the thresholded phase (i.e. the binary regions) independently. Consequently, this becomes an adaptive local threshold procedure, which operates relative to regions, rather than to local image subsets as is the case in most local thresholding methods previously published. Adding constraints for specifying certain classes of expected objects in the images can improve the output of the method over the traditional 'segmenting first, then classify' approach.

show abstract

Section: Discussionmentioning

confidence: 97%

Automatic thresholding from the gradients of region boundaries

Landini

Randell

Fouad

et al. 2016

Journal of Microscopy

View full text Add to dashboard Cite

show abstract

“…When the border intensity threshold has been found, the voxels around the local maximum are examined and successively included in the segmented object through the following algorithm: each 3D neighbour voxel is examined and included in the object if 1: their intensity is above the threshold 2: if their intensity is lower than the voxel previously added to the object 3: if the other neighbours would be added to the object as well. The third segmentation procedure is based on an iterative thresholding process, it is a simplified version of the algorithm published by Gul-Mohammed et al [17], and is based on the idea of max-trees and MSER technique [18] [19]. An interval of volumes is fixed and the image will undergo thresholding at each possible threshold and segmented objects having a volume in the defined range will be extracted from the image.…”

Section: Segmentationmentioning

confidence: 99%

DiAna, an ImageJ tool for object-based 3D co-localization and distance analysis

Gilles

Santos

Boudier

et al. 2017

Methods

157

130

View full text Add to dashboard Cite

an ImageJ tool for object-based 3D co-localization and distance analysis. Methods, Elsevier, 2016, 115, pp.55-64. 10.1016/j.ymeth.2016 1 DiAna, an ImageJ tool for object-based 3D co-localization and distance analysis AbstractWe present a new plugin for ImageJ called DiAna, for Distance Analysis, which comes with a userfriendly interface. DiAna proposes robust and accurate 3D segmentation for object extraction. The plugin performs automated object-based co-localization and distance analysis. DiAna offers an indepth analysis of co-localization between objects and retrieves 3D measurements including colocalizing volumes and surfaces of contact. It also computes the distribution of distances between objects in 3D. With DiAna, we furthermore introduce an original method, which allows for estimating the statistical significance of object co-localization. DiAna offers a complete and intuitive 3D image analysis tool for biologists.

show abstract

“…In these publications, our group was responsible for developing all the morphological aspects of the method and the collaborators were responsible for providing the datasets and performing classification of the profiles using the random forest classifier. In (Tavares et al, 2015, we developed an interactive max-tree tool. I am the second author in these two papers.…”

Section: Publications and Patentsmentioning

confidence: 99%

“…• Tavares, L., Souza, R., Rittner, L., Machado, R. and Lotufo, R. "Interactive Max-tree Visualization Tool for Image Processing and Analysis". IEEE International Conference on Image Processing Theory, Tools and Applications (IPTA), vol., pp 119-124, 2015 (Tavares et al, 2015).…”

Section: Conference Articlesmentioning

confidence: 99%

“…In the interactive methods previously cited, the interaction occurs by setting filtering parameters or by selecting regions in the input image. The work by (Tavares et al, 2015) was the first interactive method, where the interaction occurs in the max-tree domain. They provided a graphical representation of the max-tree, where the user is able to navigate and select nodes to perform interactive segmentation, filtering and collection of training samples.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Max-tree

Souza¹

View full text Add to dashboard Cite

The max-tree is a mathematical morphology tool that represents all connected components resulting of every possible upper threshold of an image. This work focus on advancing further the max-tree theory, algorithms and applications. In the theory domain, extinction filters (EFs) for increasing attributes are defined and a procedure for computing EFs for nonincreasing attributes, based on the space of shapes approach, is presented. In the algorithms domain, an array-based node-oriented data structure to store the max-tree and algorithms to process it are proposed. This structure gives direct access to the max-tree nodes, is more memory efficient and allows faster processing than other structures described in the literature. Using this proposed structure, EFs can be implemented efficiently as our experiments and complexity analysis indicate. EFs are experimentally compared to attribute filters and the results show that EFs are better in terms of simplification for recognition. We provide an open-source toolbox entitled iamxt that implements the data structure and the algorithms proposed using an array-based programming style. In the applications domain, we investigate two problems: classification of satellite images and magnetic resonance (MR) images brain segmentation. These applications are built upon EFs and the efficient max-tree algorithms. The satellite image classification approach we propose is called Extinction Profiles. It is currently the state-of-the-art for the classification of this kind of image. We validate this comparing to another state-of-the-art approach called Attribute Profile using two different datasets. For the brain segmentation application, we propose a public multi-vendor multi-field strength T 1-weighted brain MR dataset with 359 volumes and brain segmentation "silver standards" generated using supervised classification. We validate our method using this dataset and two other public datasets. The results show that our method has the highest sensitivity among the methods compared, i.e. preserves the brain, and it is robust to parameter initialization.

show abstract

Interactive max-tree visualization tool for image processing and analysis

Cited by 9 publications

References 21 publications

Automatic thresholding from the gradients of region boundaries

Automatic thresholding from the gradients of region boundaries

DiAna, an ImageJ tool for object-based 3D co-localization and distance analysis

Max-tree

Contact Info

Product

Resources

About