Results 1 - 10
of
73
3D Object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints
- International Journal of Computer Vision
, 2006
"... Abstract. This article introduces a novel representation for three-dimensional (3D) objects in terms of local affine-invariant descriptors of their images and the spatial relationships between the corresponding surface patches. Geometric constraints associated with different views of the same patche ..."
Abstract
-
Cited by 118 (14 self)
- Add to MetaCart
Abstract. This article introduces a novel representation for three-dimensional (3D) objects in terms of local affine-invariant descriptors of their images and the spatial relationships between the corresponding surface patches. Geometric constraints associated with different views of the same patches under affine projection are combined with a normalized representation of their appearance to guide matching and reconstruction, allowing the acquisition of true 3D affine and Euclidean models from multiple unregistered images, as well as their recognition in photographs taken from arbitrary viewpoints. The proposed approach does not require a separate segmentation stage, and it is applicable to highly cluttered scenes. Modeling and recognition results are presented.
Image alignment and stitching: a tutorial
, 2006
"... This tutorial reviews image alignment and image stitching algorithms. Image alignment algorithms can discover the correspondence relationships among images with varying degrees of overlap. They are ideally suited for applications such as video stabilization, summarization, and the creation of panora ..."
Abstract
-
Cited by 115 (2 self)
- Add to MetaCart
This tutorial reviews image alignment and image stitching algorithms. Image alignment algorithms can discover the correspondence relationships among images with varying degrees of overlap. They are ideally suited for applications such as video stabilization, summarization, and the creation of panoramic mosaics. Image stitching algorithms take the alignment estimates produced by such registration algorithms and blend the images in a seamless manner, taking care to deal with potential problems such as blurring or ghosting caused by parallax and scene movement as well as varying image exposures. This tutorial reviews the basic motion models underlying alignment and stitching algorithms, describes effective direct (pixel-based) and feature-based alignment algorithms, and describes blending algorithms used to produce
Survey of image-based representations and compression techniques
- IEEE TRANS. CIRCUITS SYST. VIDEO TECHNOL
, 2003
"... ..."
Computer Vision Applied to Super-Resolution”,
- IEEE Signal Processing Magazine,
, 2003
"... ..."
(Show Context)
Eigenface-domain super-resolution for face recognition
- IEEE Trans. Image Process
, 2003
"... Abstract—Face images that are captured by surveillance cameras usually have a very low resolution, which significantly limits the performance of face recognition systems. In the past, super-resolution techniques have been proposed to increase the resolution by combining information from multiple ima ..."
Abstract
-
Cited by 56 (1 self)
- Add to MetaCart
Abstract—Face images that are captured by surveillance cameras usually have a very low resolution, which significantly limits the performance of face recognition systems. In the past, super-resolution techniques have been proposed to increase the resolution by combining information from multiple images. These techniques use super-resolution as a preprocessing step to obtain a high-resolution image that is later passed to a face recognition system. Considering that most state-of-the-art face recognition systems use an initial dimensionality reduction method, we propose to transfer the super-resolution reconstruction from pixel domain to a lower dimensional face space. Such an approach has the advantage of a significant decrease in the computational complexity of the super-resolution reconstruction. The reconstruction algorithm no longer tries to obtain a visually improved high-quality image, but instead constructs the information required by the recognition system directly in the low dimensional domain without any unnecessary overhead. In addition, we show that face-space super-resolution is more robust to registration errors and noise than pixel-domain super-resolution because of the addition of model-based constraints. Index Terms—Dynamic range extension, face recognition, multiframe reconstruction, super-resolution. I.
Parameter Estimation in Bayesian High-Resolution Image Reconstruction With Multisensors
- IEEE Transactions on Image Processing
, 2003
"... In this paper, we consider the estimation of the unknown parameters for the problem of reconstructing a high-resolution image from multiple undersampled, shifted, degraded frames with subpixel displacement errors. We derive mathematical expressions for the iterative calculation of the maximum likeli ..."
Abstract
-
Cited by 37 (10 self)
- Add to MetaCart
(Show Context)
In this paper, we consider the estimation of the unknown parameters for the problem of reconstructing a high-resolution image from multiple undersampled, shifted, degraded frames with subpixel displacement errors. We derive mathematical expressions for the iterative calculation of the maximum likelihood estimate of the unknown parameters given the low resolution observed images. These iterative procedures require the manipulation of block-semi circulant (BSC) matrices, that is block matrices with circulant blocks. We show how these BSC matrices can be easily manipulated in order to calculate the unknown parameters. Finally the proposed method is tested on real and synthetic images. Index Terms---Bayesian methods, high-resolution image reconstruction, parameter estimation.
based blind image super resolution
- in Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV’05). Patch
"... In this paper, a novel method for learning based im-age super resolution (SR) is presented. The basic idea is to bridge the gap between a set of low resolution (LR) im-ages and the corresponding high resolution (HR) image us-ing both the SR reconstruction constraint and a patch based image synthesis ..."
Abstract
-
Cited by 33 (4 self)
- Add to MetaCart
(Show Context)
In this paper, a novel method for learning based im-age super resolution (SR) is presented. The basic idea is to bridge the gap between a set of low resolution (LR) im-ages and the corresponding high resolution (HR) image us-ing both the SR reconstruction constraint and a patch based image synthesis constraint in a general probabilistic frame-work. We show that in this framework, the estimation of the LR image formation parameters is straightforward. The whole framework is implemented via an annealed Gibbs sampling method. Experiments on SR on both single image and image sequence input show that the proposed method provides an automatic and stable way to compute super-resolution and the achieved result is encouraging for both synthetic and real LR images. 1.
Multi-Modal Tensor Face for Simultaneous Super-Resolution and Recognition
- Proc. IEEE International Conference on Computer Vision
, 2005
"... Face images of non-frontal views under poor illumination with low resolution reduce dramatically face recognition accuracy. This is evident most compellingly by the very low recognition rate of all existing face recognition systems when applied to live CCTV camera input. In this paper, we present a ..."
Abstract
-
Cited by 30 (4 self)
- Add to MetaCart
(Show Context)
Face images of non-frontal views under poor illumination with low resolution reduce dramatically face recognition accuracy. This is evident most compellingly by the very low recognition rate of all existing face recognition systems when applied to live CCTV camera input. In this paper, we present a Bayesian framework to perform multimodal (such as variations in viewpoint and illumination) face image super-resolution for recognition in tensor space. Given a single modal low-resolution face image, we benefit from the multiple factor interactions of training tensor, and super-resolve its high-resolution reconstructions across different modalities for face recognition. Instead of performing pixel-domain super-resolution and recognition independently as two separate sequential processes, we integrate the tasks of super-resolution and recognition by directly computing a maximum likelihood identity parameter vector in high-resolution tensor space for recognition. We show results from multi-modal super-resolution and face recognition experiments across different imaging modalities, using low-resolution images as testing inputs and demonstrate improved recognition rates over standard tensorface and eigenface representations. 1.
