Search results for "Image quality"

showing 10 items of 136 documents

Enforcing Perceptual Consistency on Generative Adversarial Networks by Using the Normalised Laplacian Pyramid Distance

2019

In recent years there has been a growing interest in image generation through deep learning. While an important part of the evaluation of the generated images usually involves visual inspection, the inclusion of human perception as a factor in the training process is often overlooked. In this paper we propose an alternative perceptual regulariser for image-to-image translation using conditional generative adversarial networks (cGANs). To do so automatically (avoiding visual inspection), we use the Normalised Laplacian Pyramid Distance (NLPD) to measure the perceptual similarity between the generated image and the original image. The NLPD is based on the principle of normalising the value of…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer scienceImage qualitymedia_common.quotation_subjectComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern RecognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONMachine Learning (stat.ML)Translation (geometry)Image (mathematics)Machine Learning (cs.LG)Consistency (database systems)Statistics - Machine LearningPerceptionFOS: Electrical engineering electronic engineering information engineeringmedia_commonbusiness.industryDeep learningImage and Video Processing (eess.IV)Contrast (statistics)Pattern recognitionGeneral MedicineImage segmentationElectrical Engineering and Systems Science - Image and Video ProcessingGenerative Adversarial NetworkPerceptionArtificial intelligencebusiness
researchProduct

PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance

2019

Traditionally, the vision community has devised algorithms to estimate the distance between an original image and images that have been subject to perturbations. Inspiration was usually taken from the human visual perceptual system and how the system processes different perturbations in order to replicate to what extent it determines our ability to judge image quality. While recent works have presented deep neural networks trained to predict human perceptual quality, very few borrow any intuitions from the human visual system. To address this, we present PerceptNet, a convolutional neural network where the architecture has been chosen to reflect the structure and various stages in the human…

FOS: Computer and information sciencesComputer Science - Machine LearningVisual perceptionComputer scienceImage qualitymedia_common.quotation_subjectFeature extractionMachine Learning (stat.ML)02 engineering and technology01 natural sciencesConvolutional neural networkhuman visual systemMachine Learning (cs.LG)010309 opticsStatistics - Machine LearningPerception0103 physical sciences0202 electrical engineering electronic engineering information engineeringFOS: Electrical engineering electronic engineering information engineeringperceptual distancemedia_commonArtificial neural networkbusiness.industryDeep learningImage and Video Processing (eess.IV)Pattern recognitionElectrical Engineering and Systems Science - Image and Video Processingneural networksHuman visual system model020201 artificial intelligence & image processingArtificial intelligencebusiness
researchProduct

Automatable sample fabrication process for pump-probe X-ray holographic imaging

2014

Soft X-ray holography is a recently developed imaging technique with sub-50 nm spatial resolution. Key advantages of this technique are magnetic and elemental sensitivity, compatibility with imaging at free electron laser facilities, and immunity to in-situ sample excitations and sample drift, which enables the reliable detection of relative changes between two images with a precision of a few nanometers. In X-ray holography, the main part of the experimental setup is integrated in the sample, which consequently requires a large number of fabrication steps. Here we present a generic design and an automatable fabrication process for samples suitable, and optimized for, efficient high resolut…

FabricationMaterials scienceImage qualityDynamic imagingHolographyComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONHolography02 engineering and technologyIterative reconstruction01 natural scienceslaw.inventionOpticslaw0103 physical sciencesDigital image processing010306 general physicsImage resolutionLithographybusiness.industryEquipment Design021001 nanoscience & nanotechnologyAtomic and Molecular Physics and OpticsEquipment Failure AnalysisComputer-Aided DesignRadiographic Image Interpretation Computer-Assisted0210 nano-technologybusinessOptics Express
researchProduct

Quantification of Myocardial Blood Flow Using Magnetic Resonance Imaging with Different accelerated Pulse Sequences

2009

The aim of this study was to compare SRTurboFLASH, SR-TrueFISP, and SR-segEPI pulse sequences using a twofold TSENSE-acceleration with regard to their use in quantification of myocardial blood flow (MBF). Six healthy volunteers were examined at 1.5T by first pass myocardial perfusion MRI at rest using all three TSENSE-accelerated pulse sequences. For absolute quantifi-cation of MBF XSIM software with the MMID4 model has been used. MBF analyses revealed significant MBF differences between SRTurboFLASH and SR-segEPI compared to SR-TrueFISP (p<0.005 and p<0.001, respectively). Differences between SRTurboFLASH and SR-segEPI were not statistically significant. The median MBF values for SR-TurboF…

First passMyocardial perfusion imagingNuclear magnetic resonancemedicine.diagnostic_testPulse (signal processing)Image qualityHealthy volunteersmedicineMagnetic resonance imagingBlood flowPerfusionBiomedical engineeringMathematics
researchProduct

Subjective image fidelity metric based on bit allocation of the human visual system in the DCT domain

1997

Until now, subjective image distortion measures have partially used diverse empirical facts concerning human perception: non-linear perception of luminance, masking of the impairments by a highly textured surround, linear filtering by the threshold contrast frequency response of the visual system, and non-linear post-filtering amplitude corrections in the frequency domain. In this work, we develop a frequency and contrast dependent metric in the DCT domain using a fully non-linear and suprathreshold contrast perception model: the Information Allocation Function (IAF) of the visual system. It is derived from experimental data about frequency and contrast incremental thresholds and it is cons…

Frequency responsegenetic structuresImage qualitybusiness.industrymedia_common.quotation_subjectDistortionFrequency domainSignal ProcessingMetric (mathematics)Human visual system modelContrast (vision)Computer visionComputer Vision and Pattern RecognitionArtificial intelligencebusinessData compressionmedia_commonMathematics
researchProduct

Image Quality Assessment by saliency maps

2012

Image Quality Assessment (IQA) is an interesting challenge for image processing applications. The goal of IQA is to replace human judgement of perceived image quality with a machine evaluation. A large number of methods have been proposed to evaluate the quality of an image which may be corrupted by noise, distorted during acquisition, transmission, compression, etc. Many methods, in some cases, do not agree with human judgment because they are not correlated with human visual perception. In the last years the most modern IQA models and metrics considered visual saliency as a fundamental issue. The aim of visual saliency is to produce a saliency map that replicates the human visual system (…

Image Quality Assessment Visual Saliency Saliency Map Human Visual System Perceptual Quality
researchProduct

A Color Image Database for Haze Model and Dehazing Methods Evaluation

2016

International audience; One of the major issues related to dehazing methods (single or multiple image based) evaluation is the absence of the haze-free image (ground-truth). This is also a problem when it concerns the validation of Koschmieder model or its subsequent dehazing methods. To overcome this problem, we created a database called CHIC (Color Hazy Image for Comparison), consisting of two scenes in controlled environment. In addition to the haze-free image, we provide 9 images of different fog densities. Moreover, for each scene, we provide a number of parameters such as local scene depth, distance from the camera of known objects such as Macbeth Color Checkers, their radiance, and t…

Image formationHazeDatabaseColor imageComputer scienceImage qualitybusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONEnvironment controlled020207 software engineering02 engineering and technologycomputer.software_genreImage (mathematics)[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]Computer graphics (images)[ INFO.INFO-TI ] Computer Science [cs]/Image Processing0202 electrical engineering electronic engineering information engineeringTransmittanceRadiance020201 artificial intelligence & image processingComputer visionArtificial intelligencebusinesscomputerComputingMethodologies_COMPUTERGRAPHICS
researchProduct

Dual-beam confocal light-sheet microscopy via flexible acousto-optic deflector

2019

Confocal detection in digital scanned laser light-sheet fluorescence microscopy (DSLM) has been established as a gold standard method to improve image quality. The selective line detection of a complementary metal-oxide-semiconductor camera (CMOS) working in rolling shutter mode allows the rejection of out-of-focus and scattered light, thus reducing background signal during image formation. Most modern CMOS have two rolling shutters, but usually only a single illuminating beam is used, halving the maximum obtainable frame rate. We report on the capability to recover the full image acquisition rate via dual confocal DSLM by using an acoustooptic deflector. Such a simple solution enables us t…

Image formationPaperMaterials scienceImage qualityConfocalBiomedical Engineeringacousto-optic deflector; confocal detection; digital scanned laser light-sheet fluorescence microscopy; high contrast; high-throughput microscopy; light-sheet microscopy; mouse brain; zebrafish brainconfocal detection01 natural scienceslaw.invention010309 opticsBiomaterialsMiceacousto-optic deflectorOpticslaw0103 physical sciencesMicroscopyImage Processing Computer-AssistedAnimalsZebrafishhigh-throughput microscopyconfocal light-sheet microscopyMicroscopyMicroscopy Confocalbusiness.industryhigh contrastRolling shutterBrainEquipment DesignLaserFrame ratezebrafish brainAtomic and Molecular Physics and OpticsElectronic Optical and Magnetic MaterialsHigh-Throughput Screening AssaysMice Inbred C57BLdigital scanned laser light-sheet fluorescence microscopyMicroscopy FluorescenceLight sheet fluorescence microscopyLarvamouse brainbusinesslight-sheet microscopyJournal of Biomedical Optics
researchProduct

Real-time image rotation using B-spline interpolation on FPGA's board

1998

The aim of our work is to realize the implementation of a real-time high-quality image rotation on FPGA's board. The method we used is based on M. Unser's work and consists in applying a B-spline interpolator. The difficulty of this problem is due to the relatively weak integration capacity of FPGAs. To solve this problem we have searched for determining the minimum number of bits to code the filter while keeping a good accuracy of filtering output. In this article, we remind a few definitions about B-spline functions and we present how we use B- spline interpolation for the image rotation problem. Then, we describe the way we calculate probability density function of the output error in or…

Image qualityB-splineElectronic engineeringImage processingFilter (signal processing)Spline interpolationAlgorithmRotation (mathematics)Digital filterMathematicsInterpolationSPIE Proceedings
researchProduct

HDR image generation from LDR image with highlight removal

2015

The emergency of High Dynamic Range (HDR) display device impels the study of generating HDR image from Low Dynamic Range (LDR) image. Most existing generation methods apply complicated handing to highlight areas in image, which perplexes the algorithm and introduces the probability of generating artifacts. In this paper, we investigate a separated scheme: instead of sophisticated treatment to the highlight areas during expanding, the processing to the highlight areas is separated from the dynamic range expansion, which facilitates the framework and reduces the artifacts. The image quality metric shows that the separated scheme reveals more details with little artifacts compared to the algor…

Image qualityComputer scienceDynamic rangebusiness.industryDistortion (optics)ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONIterative reconstructionImage (mathematics)Display deviceDistortionMetric (mathematics)Computer visionArtificial intelligencebusinessHigh dynamic range2015 IEEE International Conference on Multimedia &amp; Expo Workshops (ICMEW)
researchProduct