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…
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…
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…
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…
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…
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 (…
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…
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…
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…
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…