Image thresholding: Some new techniques

Pal, Nikhil R.; Bhandari, Dinabandhu

doi:10.1016/0165-1684(93)90107-l

Cited by 59 publications

(31 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later they incorporated another component, the object count agreement [37] together. Other evaluation studies using several measures can be found in references (23,25,36,43,44). Generally, for a complete evaluation and comparison of segmentation techniques, a set of performance measures should be necessary [9,18] .…”

Section: Discussionmentioning

confidence: 99%

“…[2] For example, the second-order local entropy that was maximized for selecting threshold values in the new algorithm proposed by Pal and Pal [24] and was also computed for comparing the performance of this algorithm with that of other algorithms by Pal and Bhandari. [25] It is expected that the new algorithm should produce quite high entropy values. In many applications, images are modeled as a mosaic of regions of uniform intensity corrupted by additive Gaussian white noise [e.g.…”

Section: Common Problems For Most Existing Methodsmentioning

confidence: 99%

“…This measure has been used in the evaluation of thresholding algorithms by Pal and Bhandari. [25] In contrast to discrepancy methods described in Section 4, this method takes the image to segment directly as the "reference" image. Although this correlation measure is seemed different in appearance than other measures, it has been proved [51] that the square of the correlation coefficient used in Brink's method is just the class separability quotient used by Otsu [26] in the "goodness" measure for threshold selection.…”

Section: < 9 > (2)mentioning

confidence: 99%

“…This entropy is also used by Pal and Bhandari [25] as a measure of the region homogeneity in segmented images for the performance evaluation of segmentation results.…”

Section: Goodness Based On Intra-region Uniformitymentioning

confidence: 99%

“…If we consider both the segmented image and the reference image as probability distributions, the difference between them would be reflected by their divergence. Suppose that the segmented image has N regions and p' i represents the a posterior probability of a pixel to be in the ith region, while p" i is that in the reference image, Pal and Bhandari [25] proposed to use the symmetric divergence (SD):…”

Section: Discrepancy Based On Miscellaneous Quantitiesmentioning

confidence: 99%

See 4 more Smart Citations

A survey on evaluation methods for image segmentation

Zhang

1996

Pattern Recognition

916

501

View full text Add to dashboard Cite

This paper studies different methods proposed so far for segmentation evaluation. Most methods can be classified into three groups: the analytical, the empirical goodness and the empirical discrepancy groups. Each group has its own characteristics. After a brief description of each method in every group, some comparative discussions about different method groups are first carried out. An experimental comparison for some empirical (goodness and discrepancy) methods commonly used is then performed to provide a rank of their evaluation abilities. In addition, some special methods are also discussed. This study is helpful for an appropriate use of existing evaluation methods and for improving their performance as well as for systematically designing new evaluation methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Common Problems For Most Existing Methodsmentioning

confidence: 99%

Section: < 9 > (2)mentioning

confidence: 99%

“…This entropy is also used by Pal and Bhandari [25] as a measure of the region homogeneity in segmented images for the performance evaluation of segmentation results.…”

Section: Goodness Based On Intra-region Uniformitymentioning

confidence: 99%

Section: Discrepancy Based On Miscellaneous Quantitiesmentioning

confidence: 99%

See 3 more Smart Citations

A survey on evaluation methods for image segmentation

Zhang

1996

Pattern Recognition

916

501

View full text Add to dashboard Cite

show abstract

Advances in automated 3-D image analysis of cell populations imaged by confocal microscopy

et al. 1996

View full text Add to dashboard Cite

Automated three‐dimensional (3‐D) image analysis methods are presented for rapid and effective analysis of populations of fluorescently labeled cells or nuclei in thick tissue sections that have been imaged three dimensionally using a confocal microscope. The methods presented here greatly improve upon our earlier work (Roysam et al.: J Microsc 173: 115–126, 1994). The principal advances reported are: algorithms for efficient data pre‐processing and adaptive segmentation, effective handling of image anisotropy, and fast, 3‐D morphological algorithms for separating overlapping or connected clusters utilizing image gradient information whenever available. A particular feature of this method is its ability to separate densely packed and connected clusters of cell nuclei. Some of the challenges overcome in this work include the efficient and effective handling of imaging noise, anisotropy, and large variations in image parameters such as intensity, object size, and shape. The method is able to handle significant inter‐cell, intra‐cell, inter‐image, and intra‐image variations. Studies indicate that this method is rapid, robust, and adaptable. Examples were presented to illustrate the applicability of this approach to analyzing images of nuclei from densely packed regions in thick sections of rat liver, and brain that were lableled with a fluorescent Schiff reagent. © 1996 Wiley‐Liss, Inc.

show abstract

Image processing of multiphase images obtained via X‐ray microtomography: A review

Schlüter

Sheppard

Brown

et al. 2014

Water Resources Research

547

323

View full text Add to dashboard Cite

Easier access to X-ray microtomography (lCT) facilities has provided much new insight from high-resolution imaging for various problems in porous media research. Pore space analysis with respect to functional properties usually requires segmentation of the intensity data into different classes. Image segmentation is a nontrivial problem that may have a profound impact on all subsequent image analyses. This review deals with two issues that are neglected in most of the recent studies on image segmentation: (i) focus on multiclass segmentation and (ii) detailed descriptions as to why a specific method may fail together with strategies for preventing the failure by applying suitable image enhancement prior to segmentation. In this way, the presented algorithms become very robust and are less prone to operator bias. Three different test images are examined: a synthetic image with ground-truth information, a synchrotron image of precision beads with three different fluids residing in the pore space, and a lCT image of a soil sample containing macropores, rocks, organic matter, and the soil matrix. Image blur is identified as the major cause for poor segmentation results. Other impairments of the raw data like noise, ring artifacts, and intensity variation can be removed with current image enhancement methods. Bayesian Markov random field segmentation, watershed segmentation, and converging active contours are well suited for multiclass segmentation, yet with different success to correct for partial volume effects and conserve small image features simultaneously.

show abstract

Image thresholding: Some new techniques

Cited by 59 publications

References 11 publications

A survey on evaluation methods for image segmentation

A survey on evaluation methods for image segmentation

Advances in automated 3-D image analysis of cell populations imaged by confocal microscopy

Image processing of multiphase images obtained via X‐ray microtomography: A review

Contact Info

Product

Resources

About