Comparative analysis of image quality measures

Devnani, Ashish; Rawat, Chandan Singh

doi:10.1109/icgtspicc.2016.7955327

Cited by 7 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The former methods are used to assess the quality of the generated results by using subjective evaluation, and the latter methods are used to evaluate model fitting in the echo domain and image domain by using the following evaluation metrics. NCC: The similarity of the two signals is assessed with the NCC [29]. When it is −1, the inversion signal is negatively correlated with the original echo, when it is 0, it is not correlated, and when it is 1, it is positively correlated.where M and N represent the number of SAR signal data range lines and range sampling points, respectively, a and r represent the azimuth and range positions, respectively, J ( a , r ) represents the jamming signal, E ( a , r ) represents the original echo signal, μ J and σ J represent the mean and standard deviation of the jamming signal, respectively, and μ E and σ E represent the mean and standard deviation of the original echo signal, respectively. PSNR: The PSNR [30] is a quantitative metric to evaluate the quality of the inversion image according to the error between the original image and the inversion image. It is defined as follows:where MAX represents the maximum value in the dynamic range of the pixel values, and I J and I E represent the inversion image and the original image, respectively.…”

Section: Resultsmentioning

confidence: 99%

“…PSNR: The PSNR [30] is a quantitative metric to evaluate the quality of the inversion image according to the error between the original image and the inversion image. It is defined as follows:…”

Section: Resultsmentioning

confidence: 99%

“…(3) Pixelshuffle [28] is used for up-sampling to improve the inversion quality of the echo signal. The proposed method is evaluated using the normalised cross-correlation (NCC) [29], peak signal-to-noise ratio (PSNR) [30], feature similarity (FSIM) [31], and learnt perceptual image patch similarity (LPIPS) [32] on the MSTAR data set and Sentinel-1 data set.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Generation of a synthetic aperture radar deception jamming signal based on a deep echo inversion network

Xiao

Dai

et al. 2023

IET Radar Sonar & Navi

View full text Add to dashboard Cite

Existing methods for generating synthetic aperture radar (SAR) deception jamming signals have slow speed, low imaging quality, and insufficient intelligence in complex electromagnetic environments. This paper proposes a deep learning-based SAR deception jamming signal generation method based on deep echo inversion Unet (DEIUnet). This method has high speed and provides high-image quality of the interference signal. A Swin Next (SN) block is proposed to combine local and non-local information in the image and echo data. The Unet structure consists of SN blocks, and a residual connection is used as the jump connection to fuse the multi-scale feature information from the echo and image data. PixelShuffle is utilised for up-sampling to generate high-quality echo data. The experimental results on MSTAR and Sentinel-1 data sets verify the effectiveness and superiority of DEIUnet for echo inversion. The imaging results of the SAR deception jamming signal generated by DEIUnet on an MSTAR scene confirm the effectiveness of the proposed method. K E Y W O R D S deception jamming signal generation, deep echo inversion unet (DEIUnet), synthetic aperture radar (SAR)This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Generation of a synthetic aperture radar deception jamming signal based on a deep echo inversion network

Xiao

Dai

et al. 2023

IET Radar Sonar & Navi

View full text Add to dashboard Cite

show abstract

“…Let us assume 𝑫𝒔 is the image set 1, which is original dataset, comprises of Np images and let 𝑫 ̂𝒔 be the image set 2, which is compressed dataset. The average SSIM (𝑺 𝒂𝒗𝒈 ) is calculated using the following equation (1) [24][25].…”

Section: B Study Of Performance Of Wavelet-based Compressed Domain Le...mentioning

confidence: 99%

“…In addition, the average PSNR (𝑃𝑆𝑁𝑅 𝑎𝑣𝑔 )is calculated using the equation (2) [25][26]. Case (i) here the approximation images are used for training and the PWH masked approximation images are used for testing, for 𝑷=100 the obtained training accuracy was 97% which is adequately good which implies no information loss in testing set.…”

Section: B Study Of Performance Of Wavelet-based Compressed Domain Le...mentioning

confidence: 99%

Compressive Wavelet Domain Deep CNN for Image Classification Using Genetic Algorithm Based Sensing Mask Learning

Ali

Ramachandran

2023

IEEE Access

View full text Add to dashboard Cite

Using a novel Genetic Algorithm-based Compressive Learning (GACL), a compressed domain-learning framework is proposed that is implemented on the Haar wavelet approximation coefficient images of the standard kaggle RGB cat dog dataset with every images resized to 256x256x3. The compressive sensing (CS) measurements on the selected dataset is achieved by using a simple reduced pixel scheme by retaining only P% of the pixels of the approximation coefficient images and forcing the remaining pixels to 0 using the Primitive Walsh Hadamard (PWH) binary mask and the masked images are used for further learning. A numerical experiment is conducted to analyze the image classification performance of deep convolution neural network (DCNN) learning on compressive sensing (CS) measurements of wavelet approximation coefficient image of the selected dataset. The unmasked wavelet approximation coefficients images are of size only one fourth of the original image, but they visually resembles the original image. The numerical experiment shows that when learning is done on this unmasked wavelet approximation coefficient images a training accuracy of 97% and validation accuracy of 77% are achieved which is remarkable and as good as using the complete spatial domain image. It is found from numerical experiment that, when PWH masking with P=10 is applied only to the test images the validation accuracy falls up to 58% and this fall is due to the fact that the training is done on unmasked images and tested on masked images. On the other hand in a compressive learning framework the DCNN is trained using masked images and when tested using masked images the validation accuracy rises up to 62% due to the fact both the trained images and test images are masked. Further, it is demonstrated that the best PWH masks can be learned by GACL in which the training accuracy increases up to 89% when vertical cross over is used in GACL and increases up to 96% when diagonal crossover is used in GACL. in this case of GACL using diagonal crossover, the 96% of training accuracy using only (10/4=2.5) 2.5% of the image is very remarkable and stand as proof of concept to implement compressive learning framework which need very less pixel thus very less measurement rate (MR) both in training and testing phase minimizing the bandwidth and storing requirement in applications related to IoT and cloud solutions. The average SSIM (𝑆 𝑎𝑣𝑔 )and average PSNR (𝑃𝑆𝑁𝑅 𝑎𝑣𝑔 )are used as quality measurements, which reduce as P reduces, and it is demonstrated that the average SSIM and average PSNR improves when GACL is used to learn the mask, which is the key reason for the performance improvement.

show abstract

Speckle noise removal in medical ultrasonic image using spatial filters and DnCNN

Kavand,

Bekrani

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Comparative analysis of image quality measures

Cited by 7 publications

References 6 publications

Generation of a synthetic aperture radar deception jamming signal based on a deep echo inversion network

Generation of a synthetic aperture radar deception jamming signal based on a deep echo inversion network

Compressive Wavelet Domain Deep CNN for Image Classification Using Genetic Algorithm Based Sensing Mask Learning

Speckle noise removal in medical ultrasonic image using spatial filters and DnCNN

Contact Info

Product

Resources

About