scholarly journals Super-Resolution of Digital Images using CNN with Leaky ReLU

2019 ◽  
Vol 8 (2S11) ◽  
pp. 210-212 ◽  
Keyword(s):  
Digital Images ◽  
Signal To Noise Ratio ◽  
Super Resolution ◽  
Image Resolution ◽  
Signal To Noise ◽  
Analysis Process ◽  
Real World Applications ◽  
Image Super Resolution ◽  
Leaky Rectified Linear Unit

Image super-resolution (SR) has been used in many real world applications as a preprocessing phase. The improvement in image resolution increases the performance of image analysis process. The SR of digital images is achieved by taking the low resolution images as inputs. In this article, a novel deeplearning based super-resolution approach is proposed. The proposed approach uses Convolutional Neural Network (CNN) with leaky rectified linear unit (ReLU) for learning and generalization. The experiments with test images taken from USC-SIPI dataset indicate that the proposed approach increases the quality of the images in terms of the quantitative metric peak signal to noise ratio.

scholarly journals Learning Based Resolution Enhancement of Digital Images

2019 ◽  
Vol 8 (6) ◽  
pp. 3026-3030
Keyword(s):  
Digital Images ◽  
Signal To Noise Ratio ◽  
Resolution Enhancement ◽  
Super Resolution ◽  
Image Resolution ◽  
Test Dataset ◽  
Analysis Process ◽  
Image Super Resolution ◽  
Leaky Rectified Linear Unit

Image super-resolution (SR), the process that improves the resolution, has been used in many real world applications. SR is the preprocessing phase of majority of these applications. The improvement in image resolution improves the performance of image analysis process. The SR of digital images take the low resolution images as inputs. In this article, a learning based digital image SR approach is proposed. The proposed approach uses Convolutional Neural Network (CNN) with leaky rectified linear unit (ReLU) for learning and generalization. The experiments with the test dataset from USC-SIPI indicate that the proposed approach increases the quality of the images in terms of the quantitative metric peak signal to noise ratio. Further, it avoided the problem of dying ReLU.

scholarly journals Evaluation of sted super-resolution image quality by image correlation spectroscopy (QuICS)

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Elena Cerutti ◽  
Morgana D’Amico ◽  
Isotta Cainero ◽  
Gaetano Ivan Dellino ◽  
Mario Faretta ◽  
...  
Keyword(s):  
Autocorrelation Function ◽  
Signal To Noise Ratio ◽  
Super Resolution ◽  
Image Contrast ◽  
Correlation Spectroscopy ◽  
Image Correlation ◽  
Signal To Noise ◽  
Image Correlation Spectroscopy ◽  
Noise Ratio

AbstractQuantifying the imaging performances in an unbiased way is of outmost importance in super-resolution microscopy. Here, we describe an algorithm based on image correlation spectroscopy (ICS) that can be used to assess the quality of super-resolution images. The algorithm is based on the calculation of an autocorrelation function and provides three different parameters: the width of the autocorrelation function, related to the spatial resolution; the brightness, related to the image contrast; the relative noise variance, related to the signal-to-noise ratio of the image. We use this algorithm to evaluate the quality of stimulated emission depletion (STED) images of DNA replication foci in U937 cells acquired under different imaging conditions. Increasing the STED depletion power improves the resolution but may reduce the image contrast. Increasing the number of line averages improves the signal-to-noise ratio but facilitates the onset of photobleaching and subsequent reduction of the image contrast. Finally, we evaluate the performances of two different separation of photons by lifetime tuning (SPLIT) approaches: the method of tunable STED depletion power and the commercially available Leica Tau-STED. We find that SPLIT provides an efficient way to improve the resolution and contrast in STED microscopy.

scholarly journals Multifocus Images Fusion Based On Homogenity and Edges Measures

2014 ◽  
Vol 11 (2) ◽  
pp. 660-672
Author(s):  
Baghdad Science Journal
Keyword(s):  
Digital Image ◽  
Digital Images ◽  
Signal To Noise Ratio ◽  
Evaluation Process ◽  
Statistical Techniques ◽  
Signal To Noise ◽  
High Quality ◽  
Simulation Process ◽  
Statistical Criteria

Image fusion is one of the most important techniques in digital image processing, includes the development of software to make the integration of multiple sets of data for the same location; It is one of the new fields adopted in solve the problems of the digital image, and produce high-quality images contains on more information for the purposes of interpretation, classification, segmentation and compression, etc. In this research, there is a solution of problems faced by different digital images such as multi focus images through a simulation process using the camera to the work of the fuse of various digital images based on previously adopted fusion techniques such as arithmetic techniques (BT, CNT and MLT), statistical techniques (LMM, RVS and WT) and spatial techniques (HPFA, HFA and HFM). As these techniques have been developed and build programs using the language MATLAB (b 2010). In this work homogeneity criteria have been suggested for evaluation fused digital image's quality, especially fine details. This criterion is correlation criteria to guess homogeneity in different regions within the image by taking a number of blocks of different regions in the image and different sizes and work shifted blocks per pixel. As dependence was on traditional statistical criteria such as (mean, standard deviation, and signal to noise ratio, mutual information and spatial frequency) and compared with the suggested criteria to the work. The results showed that the evaluation process was effective and well because it took into measure the quality of the homogenous regions.

scholarly journals Learning Weighted Forest and Similar Structure for Image Super Resolution

2019 ◽  
Vol 9 (3) ◽  
pp. 543 ◽  
Author(s):  
Ziwei Lu ◽  
Chengdong Wu ◽  
Xiaosheng Yu
Keyword(s):  
Clustering Algorithm ◽  
Signal To Noise Ratio ◽  
Super Resolution ◽  
Low Rank ◽  
Training Dataset ◽  
Image Patches ◽  
Non Local ◽  
External Training ◽  
Image Super Resolution

Image super resolution (SR) based on example learning is a very effective approach to achieve high resolution (HR) image from image input of low resolution (LR). The most popular method, however, depends on either the external training dataset or the internal similar structure, which limits the quality of image reconstruction. In the paper, we present a novel SR algorithm by learning weighted random forest and non-local similar structures. The initial HR image patches are obtained from a weighted forest model, which is established by calculating the approximate fitting error of the leaf nodes. The K-means clustering algorithm is exploited to get a non-local similar structure inside the initial HR image patches. In addition, a low rank constraint is imposed on the HR image patches in each cluster. We further apply the similar structure model to establish an effective regularization prior under a reconstruction-based SR framework. Comparing with current typical SR algorithms, the results of comprehensive experiments implemented on three publicly datasets show that peak signal-to-noise ratio (PSNR) has been effectively promoted by the presented SR approach, and a better visual effect has been realized.

scholarly journals EVALUATION OF STED SUPER-RESOLUTION IMAGE QUALITY BY IMAGE CORRELATION SPECTROSCOPY (QuICS)

2021 ◽  
Author(s):  
Elena Cerutti ◽  
Morgana D'Amico ◽  
Isotta Cainero ◽  
Gaetano Ivan Dellino ◽  
Mario Faretta ◽  
...  
Keyword(s):  
Autocorrelation Function ◽  
Signal To Noise Ratio ◽  
Super Resolution ◽  
Image Contrast ◽  
Correlation Spectroscopy ◽  
Image Correlation ◽  
Signal To Noise ◽  
Image Correlation Spectroscopy ◽  
Noise Ratio

Quantifying the imaging performances in an unbiased way is of outmost importance in super-resolution microscopy. Here, we describe an algorithm based on image correlation spectroscopy (ICS) that can be used to assess the quality of super-resolution images. The algorithm is based on the calculation of an autocorrelation function and provides three different parameters: the width of the autocorrelation function, related to the spatial resolution; the brightness, related to the image contrast; the relative noise variance, related to the signal-to-noise ratio of the image. We use this algorithm to evaluate the quality of stimulated emission depletion (STED) images of DNA replication foci in U937 cells acquired under different imaging conditions. Increasing the STED power improves the resolution but may reduce the image contrast. Increasing the number of line averages improves the signal-to-noise ratio but facilitates the onset of photobleaching and subsequent reduction of the image contrast. Finally, we evaluate the performances of two different separation of photons by lifetime tuning (SPLIT) approaches: the method of tunable STED power and the commercially available Leica Tau-STED. We find that SPLIT provides an efficient way to improve the resolution and contrast in STED microscopy.

Image Quality Enhancing by Efficient Histogram Equalization

2014 ◽  
Vol 2 (2) ◽  
pp. 47-58
Author(s):  
Ismail Sh. Baqer
Keyword(s):  
Image Quality ◽  
Contrast Enhancement ◽  
Mean Squared Error ◽  
Signal To Noise Ratio ◽  
Histogram Equalization ◽  
Gray Level ◽  
Signal To Noise ◽  
Squared Error ◽  
Noise Ratio

A two Level Image Quality enhancement is proposed in this paper. In the first level, Dualistic Sub-Image Histogram Equalization DSIHE method decomposes the original image into two sub-images based on median of original images. The second level deals with spikes shaped noise that may appear in the image after processing. We presents three methods of image enhancement GHE, LHE and proposed DSIHE that improve the visual quality of images. A comparative calculations is being carried out on above mentioned techniques to examine objective and subjective image quality parameters e.g. Peak Signal-to-Noise Ratio PSNR values, entropy H and mean squared error MSE to measure the quality of gray scale enhanced images. For handling gray-level images, convenient Histogram Equalization methods e.g. GHE and LHE tend to change the mean brightness of an image to middle level of the gray-level range limiting their appropriateness for contrast enhancement in consumer electronics such as TV monitors. The DSIHE methods seem to overcome this disadvantage as they tend to preserve both, the brightness and contrast enhancement. Experimental results show that the proposed technique gives better results in terms of Discrete Entropy, Signal to Noise ratio and Mean Squared Error values than the Global and Local histogram-based equalization methods

Singular Values Decomposition and Lifting Wavelet Transform for Speech Signal Embedding into Digital Image

2019 ◽  
Vol 12 (2) ◽  
pp. 138-151
Author(s):  
Mourad Talbi ◽  
Med Salim Bouhlel
Keyword(s):  
Wavelet Transform ◽  
Speech Signal ◽  
Signal To Noise Ratio ◽  
Perceptual Quality ◽  
Lifting Wavelet Transform ◽  
Signal To Noise ◽  
Perceptual Evaluation ◽  
Lifting Wavelet ◽  
Noise Ratio

Background: In this paper, we propose a secure image watermarking technique which is applied to grayscale and color images. It consists in applying the SVD (Singular Value Decomposition) in the Lifting Wavelet Transform domain for embedding a speech image (the watermark) into the host image. Methods: It also uses signature in the embedding and extraction steps. Its performance is justified by the computation of PSNR (Pick Signal to Noise Ratio), SSIM (Structural Similarity), SNR (Signal to Noise Ratio), SegSNR (Segmental SNR) and PESQ (Perceptual Evaluation Speech Quality). Results: The PSNR and SSIM are used for evaluating the perceptual quality of the watermarked image compared to the original image. The SNR, SegSNR and PESQ are used for evaluating the perceptual quality of the reconstructed or extracted speech signal compared to the original speech signal. Conclusion: The Results obtained from computation of PSNR, SSIM, SNR, SegSNR and PESQ show the performance of the proposed technique.

scholarly journals Small Object Detection in Remote Sensing Images with Residual Feature Aggregation-Based Super-Resolution and Object Detector Network

2021 ◽  
Vol 13 (9) ◽  
pp. 1854
Author(s):  
Syed Muhammad Arsalan Bashir ◽  
Yi Wang
Keyword(s):  
Remote Sensing ◽  
Object Detection ◽  
Resolution Enhancement ◽  
Super Resolution ◽  
Detection Performance ◽  
Image Resolution ◽  
Small Object ◽  
Remote Sensing Images ◽  
Feature Aggregation ◽  
Image Super Resolution

This paper deals with detecting small objects in remote sensing images from satellites or any aerial vehicle by utilizing the concept of image super-resolution for image resolution enhancement using a deep-learning-based detection method. This paper provides a rationale for image super-resolution for small objects by improving the current super-resolution (SR) framework by incorporating a cyclic generative adversarial network (GAN) and residual feature aggregation (RFA) to improve detection performance. The novelty of the method is threefold: first, a framework is proposed, independent of the final object detector used in research, i.e., YOLOv3 could be replaced with Faster R-CNN or any object detector to perform object detection; second, a residual feature aggregation network was used in the generator, which significantly improved the detection performance as the RFA network detected complex features; and third, the whole network was transformed into a cyclic GAN. The image super-resolution cyclic GAN with RFA and YOLO as the detection network is termed as SRCGAN-RFA-YOLO, which is compared with the detection accuracies of other methods. Rigorous experiments on both satellite images and aerial images (ISPRS Potsdam, VAID, and Draper Satellite Image Chronology datasets) were performed, and the results showed that the detection performance increased by using super-resolution methods for spatial resolution enhancement; for an IoU of 0.10, AP of 0.7867 was achieved for a scale factor of 16.

Contribution of enhanced DWT and non-negative structured sparse representation for image super resolution: A performance analysis

2020 ◽  
Vol 18 (06) ◽  
pp. 2050049
Author(s):  
A. Valli Bhasha ◽  
B. D. Venkatramana Reddy
Keyword(s):  
Sparse Representation ◽  
Hyperspectral Image ◽  
Super Resolution ◽  
Image Resolution ◽  
Discrete Wavelet ◽  
Spotted Hyena ◽  
Resolution Model ◽  
Deep Cnn ◽  
Image Super Resolution ◽  
Two Phases

The image super-resolution methods with deep learning using Convolutional Neural Network (CNN) have been producing admirable advancements. The proposed image resolution model involves the following two main analyses: (i) analysis using Adaptive Discrete Wavelet Transform (ADWT) with Deep CNN and (ii) analysis using Non-negative Structured Sparse Representation (NSSR). The technique termed as NSSR is used to recover the high-resolution (HR) images from the low-resolution (LR) images. The experimental evaluation involves two phases: Training and Testing. In the training phase, the information regarding the residual images of the dataset are trained using the optimized Deep CNN. On the other hand, the testing phase helps to generate the super resolution image using the HR wavelet subbands (HRSB) and residual images. As the main novelty, the filter coefficients of DWT are optimized by the hybrid Fire Fly-based Spotted Hyena Optimization (FF-SHO) to develop ADWT. Finally, a valuable performance evaluation on the two benchmark hyperspectral image datasets confirms the effectiveness of the proposed model over the existing algorithms.

Multilag Correlation Estimators for Polarimetric Radar Measurements in the Presence of Noise

2012 ◽  
Vol 29 (6) ◽  
pp. 772-795 ◽  
Author(s):  
Lei Lei ◽  
Guifu Zhang ◽  
Richard J. Doviak ◽  
Robert Palmer ◽  
Boon Leng Cheong ◽  
...  
Keyword(s):  
Theoretical Analysis ◽  
Data Quality ◽  
Signal To Noise Ratio ◽  
Simulated Data ◽  
Radar Data ◽  
Polarimetric Radar ◽  
Signal To Noise ◽  
Spectral Moments ◽  
Radar Measurements

Abstract The quality of polarimetric radar data degrades as the signal-to-noise ratio (SNR) decreases. This substantially limits the usage of collected polarimetric radar data to high SNR regions. To improve data quality at low SNRs, multilag correlation estimators are introduced. The performance of the multilag estimators for spectral moments and polarimetric parameters is examined through a theoretical analysis and by the use of simulated data. The biases and standard deviations of the estimates are calculated and compared with those estimates obtained using the conventional method.

Sign in / Sign up

Export Citation Format

Share Document