A comparison of image quality metric performances under practical conditions

Zampolo, Ronaldo; Seara, Rui

doi:10.1109/icip.2005.1530611

Cited by 9 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2(g) ( ), in which the structural details are prominent and the noise is markedly reduced. For a quantitative assessment of WBNS image processing, we calculated the mean square error (MSE) and the Pearson correlation coefficient (PCC) [ 18 ] between the ground-truth image ( Fig. 2(a) ) and the “pseudo” microscopy image ( Fig.…”

Section: Performance Assessment Of Wbns Using Synthetic Imagesmentioning

confidence: 99%

“…Processed images with (f) subtraction of background only (WBS) and (g) noise subtraction in addition (WBNS), showing more prominent structural details and markedly reduced noise. (h) Mean square error (MSE) and Pearson correlation coefficient (PCC) [ 18 ], calculated between the ground-truth image (panel (a)) and the “pseudo” microscope image (panel (b)), the background corrected image (panel (f)) and the background and noise corrected image (panel (g)). All images have been normalized to the same mean intensity.…”

Section: Performance Assessment Of Wbns Using Synthetic Imagesmentioning

confidence: 99%

See 1 more Smart Citation

Wavelet-based background and noise subtraction for fluorescence microscopy images

Hüpfel

Kobitski

Zhang

et al. 2021

Biomed. Opt. Express

View full text Add to dashboard Cite

Fluorescence microscopy images are inevitably contaminated by background intensity contributions. Fluorescence from out-of-focus planes and scattered light are important sources of slowly varying, low spatial frequency background, whereas background varying from pixel to pixel (high frequency noise) is introduced by the detection system. Here we present a powerful, easy-to-use software, wavelet-based background and noise subtraction (WBNS), which effectively removes both of these components. To assess its performance, we apply WBNS to synthetic images and compare the results quantitatively with the ground truth and with images processed by other background removal algorithms. We further evaluate WBNS on real images taken with a light-sheet microscope and a super-resolution stimulated emission depletion microscope. For both cases, we compare the WBNS algorithm with hardware-based background removal techniques and present a quantitative assessment of the results. WBNS shows an excellent performance in all these applications and significantly enhances the visual appearance of fluorescence images. Moreover, it may serve as a pre-processing step for further quantitative analysis.

show abstract

Section: Performance Assessment Of Wbns Using Synthetic Imagesmentioning

confidence: 99%

Section: Performance Assessment Of Wbns Using Synthetic Imagesmentioning

confidence: 99%

Wavelet-based background and noise subtraction for fluorescence microscopy images

Hüpfel

Kobitski

Zhang

et al. 2021

Biomed. Opt. Express

View full text Add to dashboard Cite

show abstract

“…EPIC values) and subjective scales, the Pearson's correlation coefficient (r) was used [12,13]. A degree of correlation larger than a level of significance at 1% probability level indicates that the degree of correlation between the two variables is statically significant.…”

Section: Epic As An Overall Quality Predictormentioning

confidence: 99%

Device-dependent scene-dependent quality predictions using effective pictorial information capacity

Triantaphillidou

Jacobson

2011

SPIE Proceedings

View full text Add to dashboard Cite

This study aims to introduce improvements in the predictions of device-dependent image quality metrics (IQMs). A validation experiment was first carried out to test the success of such a metric, the Effective Pictorial Information Capacity (EPIC), using results from subjective tests involving 32 test scenes replicated with various degrees of sharpness and noisiness. The metric was found to be a good predictor when tested against average ratings but, as expected by device-dependent metrics, it predicted less successfully the perceived quality of individual, non-standard scenes with atypical spatial and structural content. Improvement in predictions was attempted by using a modular image quality framework and its implementation with the EPIC metric. It involves modeling a complicated set of conditions, including classifying scenes into a small number of groups. The scene classification employed for the purpose uses objective scene descriptors which correlate with subjective criteria on scene susceptibility to sharpness and noisiness. The implementation thus allows automatic grouping of scenes and calculation of the metric values. Results indicate that model predictions were improved. Most importantly, they were shown to correlate equally well with subjective quality scales of standard and non-standard scenes. The findings indicate that a device-dependent, scene-dependent image quality model can be achieved.

show abstract

“…There are many numerical approaches to compare synthetic images [7,8]. They are mostly designed for digital images created by digital camera.…”

Section: Numerical Metrics For Noise Measurementmentioning

confidence: 99%

Measurement of noise in the Monte Carlo point sampling method

Guzek¹,

Napieralski²

2011

Bulletin of the Polish Academy of Sciences: Technical Sciences

View full text Add to dashboard Cite

Abstract. This paper gives a concise overview of the techniques we have used to find out the degree of measuring the quality of rendered images and a level of noise in particular. First part of the paper presents designed and conducted psychophysical experiment involving human subjective judgment. Then, two of the existing numerical image comparison methods are considered in the context of assessing the level of noise produced by global illuminations algorithms. The results of the participants' subjective responses are correlated with the data obtained from objective mathematical metrics. The main goal of research was to determine the objective and perceptual measure of quality for images with fixed sampling strategy. The results will help to establish the measures of identifying the human perception in the assessment of images generated with global illumination algorithms.

show abstract

A comparison of image quality metric performances under practical conditions

Cited by 9 publications

References 9 publications

Wavelet-based background and noise subtraction for fluorescence microscopy images

Wavelet-based background and noise subtraction for fluorescence microscopy images

Device-dependent scene-dependent quality predictions using effective pictorial information capacity

Measurement of noise in the Monte Carlo point sampling method

Contact Info

Product

Resources

About