Evaluating sharpness metrics for HE stained blood cell images

Windisch, Gergely; Kozlovszky, Miklós

doi:10.1109/cinti.2014.7028679

Cited by 3 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As for our own implementation only the most successful metrics are shown here (RGB gradient based metric and edge based metric), for more details on the other metrics omitted in this publication see [1]. In both tables there are three columns: hit, miss and ratio.…”

Section: B Resultsmentioning

confidence: 99%

“…For the evaluation we have been using two of our own methods as described in [1], one based on the gradients of the image, the other based on edge detection and edge strengths. There have also been five other metrics taken from the literature: variance based [3], autocorrelation based [4], first and second derivatives based [3], "noticeable blur" based [5] and "no reference blur metric" [6].…”

Section: A Methodologymentioning

confidence: 99%

“…There are many known sharpness metrics available in the literature [1], [3], [4], [5] and [6], a thorough comparison of the most important ones can be found in [2].…”

Section: State Of the Art -Sharpness Metricsmentioning

confidence: 99%

“…There has already been research comparing such metrics and the results are usually outstanding but those measurements have usually been conducted on photos taken with a digital camera where the focus value has been changed a little for each subsequent image, or even synthesized -meaning the sharp image is blurred with a Gaussian blur using different blur radius and then use a metric to choose the sharpest image of these sets. One of our research efforts aim at automatical analysis of images taken with a digital microscope of HE stained blood smears (mainly to find white blood cell count and other properties in the image), and we have developed two image sharpness metrics but the results both have yielded [1] have been significantly poorer than the results published in other research articles [2]. Our goal in this publication is to evaluate image sharpness algorithms using out-of focus images taken with a digital microscope by comparing image sets consisting of six images taken of the same slide segment with different subject distances and choosing the sharpest image of each image set by the different algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Image sharpness metrics for digital microscopy

Windisch

Kozlovszky

2015

2015 IEEE 13th International Symposium on Applied Machine Intelligence and Informatics (SAMI)

Self Cite

View full text Add to dashboard Cite

Image sharpness measurements are important parts of many image processing applications. To measure image sharpness multiple algorithms have been proposed and measured in the past but they have been developed with having out-of-focus photographs in mind and they do not work so well with images taken using a digital microscope. In this article we show the difference between images taken with digital cameras, images taken with a digital microscope and artificially blurred images. The conventional sharpness measures are executed on all these categories to measure the difference and a standard image set taken with a digital microscope is proposed and described to serve as a common baseline for further sharpness measures in the field.I.

show abstract

Section: B Resultsmentioning

confidence: 99%

Section: A Methodologymentioning

confidence: 99%

“…There are many known sharpness metrics available in the literature [1], [3], [4], [5] and [6], a thorough comparison of the most important ones can be found in [2].…”

Section: State Of the Art -Sharpness Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Image sharpness metrics for digital microscopy

Windisch

Kozlovszky

2015

2015 IEEE 13th International Symposium on Applied Machine Intelligence and Informatics (SAMI)

Self Cite

View full text Add to dashboard Cite

show abstract

“…As with (3), the higher the result, the sharper the image. These metrics have different properties, especially when dealing with image noise, but they perform quite well [14].…”

mentioning

confidence: 99%

Parallel image sharpness measure for supercomputing environment

Windisch

Kozlovszky

2015

2015 IEEE 13th International Symposium on Applied Machine Intelligence and Informatics (SAMI)

Self Cite

View full text Add to dashboard Cite

Image sharpness is an important part of the overall quality of an image. There are multiple metrics to evaluate image sharpness, the algorithms are mainly created for regular desktop computers. This article describes the sharpness metrics devised and implemented at Obuda University parallelized and ported to an HPC infrastructure. Along with the native ported application a workflow has been created on the gUSE/WS-PGRADE portal system and an ASM portlet has been developed to make the service readily available to I.

show abstract

Image quality evaluation for FIB‐SEM images

Roldán,

Redenbach,

Schladitz

et al. 2024

Journal of Microscopy

View full text Add to dashboard Cite

SummaryFIB‐SEM tomography is a serial sectioning technique where a Focused Ion Beam (FIB) mills off slices from the material sample that is being analyzed. After every slicing, a Scanning Electron Microscopy (SEM) image is taken showing the newly exposed layer of the sample. By combining all slices in a stack, a 3D image of the material is generated. However, specific artifacts caused by the imaging technique distort the images, hampering the morphological analysis of the structure. Typical quality problems in microscopy imaging are noise and lack of contrast or focus. Moreover, specific artifacts are caused by the FIB milling, namely, curtaining and charging artifacts. We propose quality indexes for the evaluation of the quality of FIB‐SEM data sets. The indexes are validated on real and experimental data of different structures and materials.This article is protected by copyright. All rights reserved

show abstract

Evaluating sharpness metrics for HE stained blood cell images

Cited by 3 publications

References 8 publications

Image sharpness metrics for digital microscopy

Image sharpness metrics for digital microscopy

Parallel image sharpness measure for supercomputing environment

Image quality evaluation for FIB‐SEM images

Contact Info

Product

Resources

About