Topic
Parametric Image
About: Parametric Image is a research topic. Over the lifetime, 311 publications have been published within this topic receiving 6095 citations.
Papers published on a yearly basis
Papers
More filters
Posted Content•
TL;DR: This work proposes class-specific segmentation models that leverage parametric max-flow image segmentation and a large dataset of human shapes that allows the shape prior to be constructed on-the-fly, for arbitrary viewpoints and partial views.
Abstract: The figure-ground segmentation of humans in images captured in natural environments is an outstanding open problem due to the presence of complex backgrounds, articulation, varying body proportions, partial views and viewpoint changes. In this work we propose class-specific segmentation models that leverage parametric max-flow image segmentation and a large dataset of human shapes. Our contributions are as follows: (1) formulation of a sub-modular energy model that combines class-specific structural constraints and data-driven shape priors, within a parametric max-flow optimization methodology that systematically computes all breakpoints of the model in polynomial time; (2) design of a data-driven class-specific fusion methodology, based on matching against a large training set of exemplar human shapes (100,000 in our experiments), that allows the shape prior to be constructed on-the-fly, for arbitrary viewpoints and partial views. (3) demonstration of state of the art results, in two challenging datasets, H3D and MPII (where figure-ground segmentation annotations have been added by us), where we substantially improve on the first ranked hypothesis estimates of mid-level segmentation methods, by 20%, with hypothesis set sizes that are up to one order of magnitude smaller.
4 citations
23 Sep 1990
TL;DR: In this article, a high spatial and temporal resolution parametric image processing program has been developed, which utilizes angiographic images acquired by a constant radiographic technique and corrects for scatter and veiling glare and constructs a number of parametric images that can be quantitated.
Abstract: A new high spatial and temporal resolution parametric image processing program has been developed The program utilizes angiographic images acquired by a constant radiographic technique, and corrects for scatter and veiling glare and constructs a number of parametric images that can be quantitated Because of its high resolution, the program permits a better understanding of the data and allows detection of imaging artifacts, ie, overlapping recirculation regions The program is applicable to various organs including the heart, kidney and gills >
4 citations
15 Sep 2016
TL;DR: A novel parametric image representation which is derived from the generic image prior (GIP), which utilizes the classic fields of experts model to capture the prior distribution of an image with respect to a random field, which is learned from a great deal of natural images.
Abstract: No reference image quality assessment (NR-IQA) has attracted great attention due to the increasing demand in developing perceptually friendly applications. The crucial challenge of this task is how to accurately measure the naturalness of an image. In this paper, we propose a novel parametric image representation which is derived from the generic image prior (GIP). More specifically, we utilize the classic fields of experts model to capture the prior distribution of an image with respect to a random field, which is learned from a great deal of natural images. Then, the parameters in modeling this prior distribution are used as the quality-relevant image feature, which is represented by a simple two-dimension vector. Experimental results show that the proposed method achieves competitive quality prediction accuracy in comparison with the state-of-the-art NR-IQA algorithms at the expense of much less memory usage and computational complexity.
4 citations
01 Jan 1994
TL;DR: Several types of parametric images have been proposed from equilibrium ventriculography in an attempt to break up the complexity of the cardiac cycle into its several components and to display them to the clinician in a more accessible format as discussed by the authors.
Abstract: Several types of parametric images have been proposed from equilibrium ventriculography in an attempt to break up the complexity of the cardiac cycle into its several components and to display them to the clinician in a more accessible format. Even if, following this approach, each component can be separately analysed, the clinical evaluation should be global and should take into consideration the clinical condition of the patient. Of all these types of images, amplitude and phase images derived from the adjustment to the first Fourier’s harmonic are certainly those that are used the most in everyday practice. As such, they will receive preferential treatment here.
3 citations
01 Jan 1988
TL;DR: Some of the characteristics and advantages of graphic oriented user interfaces for medical image processing and analysis and some of the new approaches in displaying complex analysis results in color coded parametric images are reviewed.
Abstract: The recent development of advanced computer graphic techniques has significantly contributed to the design of new image processing and image analysis algorithms. Most image processing workstations rely nowadays on sophisticated computer graphics for the simplification of user interactions and for the enhancement of the display of the results. In this paper we would like to outline some of the characteristics and advantages of graphic oriented user interfaces for medical image processing and analysis. Also we will review some of the new approaches in displaying complex analysis results in color coded parametric images. The use of graphics and color coded images can significantly improve the practicability of medical image analysis and allow an easier access to sophisticated quantitative algorithms for non computer-oriented clinicians.
3 citations