The aim of this paper is to find the best representation for the appearance of surfaces with Lambertian reflectance under varying illumination. Previous work using principal component analysis (PCA) found the best sub...
详细信息
The aim of this paper is to find the best representation for the appearance of surfaces with Lambertian reflectance under varying illumination. Previous work using principal component analysis (PCA) found the best sub-space to represent all images of an object under a varying point light source. We extend this to images from any illumination distribution. Specifically we calculate the bases for all configurations of a point plus ambient light source and two point light sources, as well as from a database of captured real world illumination. We also reformulate the optimization criterion used in PCA. The resulting basis, we believe has higher representability and is better for analysing images of shaded objects. The different bases are compared on a database of images to test the representability.
This paper proposes a novel algorithm to clean up a large collection of historical handwritten documents kept in the National Archives of Singapore. Due to the seepage of ink over long period of storage, the front pag...
详细信息
This paper proposes a novel algorithm to clean up a large collection of historical handwritten documents kept in the National Archives of Singapore. Due to the seepage of ink over long period of storage, the front page of each document has been severely marred by the reverse side writing. Earlier attempts have been made to match both sides of a page to identify the offending strokes originating from the back so as to eliminate them with the aid of a wavelet transform. Perfect matching, however, is difficult due to document skews, differing resolutions, inadvertently missing out reverse side and warped pages during image capture. A new approach is now proposed to do away with double side mapping by using a directional wavelet transform that is able to distinguish the foreground and reverse side strokes much better than the conventional wavelet transform. Experiments have shown that the method indeed enhances the readability of each document significantly after the directional wavelet operation without the need for mapping with its reverse side.
Motion blur due to camera motion can significantly degrade the quality of an image. Since the path of the camera motion can be arbitrary, deblurring of motion blurred images is a hard problem. Previous methods to deal...
详细信息
Motion blur due to camera motion can significantly degrade the quality of an image. Since the path of the camera motion can be arbitrary, deblurring of motion blurred images is a hard problem. Previous methods to deal with this problem have included blind restoration of motion blurred images, optical correction using stabilized lenses, and special CMOS sensors that limit the exposure time in the presence of motion. In this paper, we exploit the fundamental tradeoff between spatial resolution and temporal resolution to construct a hybrid camera that can measure its own motion during image integration. The acquired motion information is used to compute a point spread function (PSF) that represents the path of the camera during integration. This PSF is then used to deblur the image. To verify the feasibility of hybrid imaging for motion deblurring, we have implemented a prototype hybrid camera. This prototype system was evaluated in different indoor and outdoor scenes using long exposures and complex camera motion paths. The results show that, with minimal resources, hybrid imaging outperforms previous approaches to the motion blur problem.
This paper presents a novel method to model and recognize human faces in video sequences. Each registered person is represented by a low-dimensional appearance manifold in the ambient image space. The complex nonlinea...
详细信息
This paper presents a novel method to model and recognize human faces in video sequences. Each registered person is represented by a low-dimensional appearance manifold in the ambient image space. The complex nonlinear appearance manifold expressed as a collection of subsets (named pose manifolds), and the connectivity among them. Each pose manifold is approximated by an affine plane. To construct this representation, exemplars are sampled from videos, and these exemplars are clustered with a K-means algorithm;each cluster is represented as a plane computed through principal component analysis (PCA). The connectivity between the pose manifolds encodes the transition probability between images in each of the pose manifold and is learned from a training video sequences. A maximum a posteriori formulation is presented for face recognition in test video sequences by integrating the likelihood that the input image comes from a particular pose manifold and the transition probability to this pose manifold from the previous frame. To recognize faces with partial occlusion, we introduce a weight mask into the process. Extensive experiments demonstrate that the proposed algorithm outperforms existing frame-based face recognition methods with temporal voting schemes.
Helmholtz stereopsis has been previously introduced as a surface reconstruction technique that does not assume a model of surface reflectance. This technique relies on the use of multiple cameras and light sources, an...
详细信息
Helmholtz stereopsis has been previously introduced as a surface reconstruction technique that does not assume a model of surface reflectance. This technique relies on the use of multiple cameras and light sources, and it has been shown to be effective when the camera and source positions are known. Here, we take a stratified look at uncalibrated Helmholtz stereopsis. We derive a new photometric matching constraint that can be used to establish correspondence without any knowledge of the cameras and sources (except that they are co-located), and we determine conditions under which we can obtain affine and metric reconstructions. An implementation and experimental results are presented.
We consider the problem of segmenting an image into foreground and background, with foreground containing solely objects of interest known a priori. We propose an integration model that incorporates both edge detectio...
详细信息
We consider the problem of segmenting an image into foreground and background, with foreground containing solely objects of interest known a priori. We propose an integration model that incorporates both edge detection and object part detection results. It consists of two parallel processes: low-level pixel grouping and high-level patch grouping. We seek a solution that optimizes a joint grouping criterion in a reduced space enforced by grouping correspondence between pixels and patches. Using spectral graph partitioning, we show that a near global optimum can be found by solving a constrained eigenvalue problem. We report promising experimental results on a dataset of 15 objects under clutter and occlusion.
It is now common practice in machine vision to define the variability in an object's appearance in a factored manner, as a combination of shape and texture transformations. In this context, we present a simple and...
详细信息
It is now common practice in machine vision to define the variability in an object's appearance in a factored manner, as a combination of shape and texture transformations. In this context, we present a simple and practical method for estimating non-parametric probability densities over a group of linear shape deformations. Samples drawn from such a distribution do not lie in a Euclidean space, and standard kernel density estimates may perform poorly. While variable kernel estimators may mitigate this problem to some extent, the geometry of the underlying configuration space ultimately demands a kernel which accommodates its group structure. In this perspective, we propose a suitable invariant estimator on the linear group of non-singular matrices with positive determinant. We illustrate this approach by modeling image transformations in digit recognition problems, and present results showing the superiority of our estimator to comparable Euclidean estimators in this domain.
Early biological changes that can be associated with disease are important indicators or biomarkers for the development of preventive screening strategies. Epidemiological studies have shown that the presence of chrom...
详细信息
ISBN:
(纸本)0780377893
Early biological changes that can be associated with disease are important indicators or biomarkers for the development of preventive screening strategies. Epidemiological studies have shown that the presence of chromosome damage or instability in human lymphocytes could be considered as an indicator of cancer risk. Chromosome damage can also be estimated using the micronuclei (MN) assay. MN are nuclear bodies originated by chromosome breakage or chromosome segregation during cell division. MN assay can be performed in epithelial tissues in direct contact with xenobiotics and carcinogens, becoming an indicator of cancer risk. Cell MN are thus geometric configurations that appear in the cell cytoplasm as small round bodies near the cell nucleus after cell division. Scoring micronuclei requires a trained individual to detect and count MN in approximately 3000-5000 cells from images in a microscope, becoming a tedious, subjective and error-prone task. In this paper we describe automated detection and counting techniques using digital imageprocessing.and patternrecognition, allowing automated detection and quantification of the cellular micronuclei configurations, making this technique much more effective for fast and reliable assessing of DNA damage by exposure to radiation and toxic substances.
In this paper, we propose an extension of the principle of the interval's approach to define new directional and qualitative topological relations where the description is more precise and where an adaptation of t...
详细信息
ISBN:
(纸本)0780379187
In this paper, we propose an extension of the principle of the interval's approach to define new directional and qualitative topological relations where the description is more precise and where an adaptation of the concept of earlier methods based on Ellen's algebra is possible. Thus, for any reference position we want to locate (beginning, middle, between two sets, under,...), we had only to locate the position by the reference sets and then define the desired spatial relationships by comparing the percentage of the interior parts/exteior parts regarding this reference.
Although important contributions on face recognition have been recently reported, few are focused on how to robustly recognize expression variant faces from as little as one single training sample per class. Since lea...
详细信息
Although important contributions on face recognition have been recently reported, few are focused on how to robustly recognize expression variant faces from as little as one single training sample per class. Since learning cannot generally be applied when only one sample per class is available, matching techniques (distance measures) are usually employed instead (e.g. correlations). However, distance measures generally attempt to match all features with equal importance (weighting), because not only it is difficult to know which features are more useful (for classification), but when or under which circumstances this happens. For example, when recognizing faces in the original image space (e.g. using the Euclidean distance-correlation), it is not known which pixels are more and which are less appropriate to be used. In this contribution, we use the optical flow between the testing and sample images as a measure of how good each pixel is. Pixels that have a small flow will have high weights, pixels with a large flow will have small weights. Our experimental results show that the method proposed in this contribution outperforms the classical Euclidean distance (correlation) measure and the PCA approach.
暂无评论