WorldCat Identities

Nayar, Shree K.

Overview
Works: 31 works in 84 publications in 1 language and 1,177 library holdings
Genres: Conference papers and proceedings 
Roles: Author, Other, Editor
Publication Timeline
.
Most widely held works by Shree K Nayar
Early visual learning( Book )

8 editions published between 1996 and 1997 in English and Undetermined and held by 238 WorldCat member libraries worldwide

Computer vision : ACCV 2006 : 7th Asian Conference on Computer Vision, Hyderabad, India, January 13-16, 2006 : proceedings by Asian Conference on Computer Vision( Book )

10 editions published in 2006 in English and held by 132 WorldCat member libraries worldwide

Computer vision - ACCV 2006 : 7th Asian Conference on Computer Vision, Hyderabad, India, January 13 - 16, 2006; proceedings by P. J Narayanan( Book )

14 editions published in 2006 in English and held by 14 WorldCat member libraries worldwide

Welcometothe7thAsianConferenceonComputerVision. Itgivesusgreatpl- sure to bring forth its proceedings. ACCV has been making its rounds through the Asian landscape and came to India this year. We are proud of the technical program we have put together and we hope you enjoy it. Interest in computer vision is increasing and ACCV 2006 attracted about 500 submission. The evaluation team consisted of 27 experts serving as Area Chairs and about 270 reviewers in all. The whole process was conducted electronically in a double-blind manner, a?rstfor ACCV. Eachpaper wasassignedto an Area Chair who found three competent reviewers for it. We were able to contain the maximum load on the reviewers to nine and the average load to less than six. The review form had space for qualitative and quantitative evaluation of the paper on nine aspects. The submitted reviews underwent an elaborate process. First, they were seen by the Area Chair, who resolved divergences of opinion among reviewers, if any. The Area Chair then wrote qualitative comments and a quantitative score along with his/her initial recommendation on the paper. These were looked at by Program Co-chairs and compiled into a probables list. The Area Chairs and Program Co-chairs met in Beijing during ICCV to discuss this list and arrivedat the?nal list of 64 oral papers and 128 posters. Naturally, many deserving papers could not be accommodated
Computer vision - ACCV 2006 : 7th Asian Conference on Computer Vision, Hyderabad, India, January 13 - 16, 2006; proceedings by P. J Narayanan( Book )

8 editions published between 2006 and 2007 in English and held by 9 WorldCat member libraries worldwide

Annotation
Computer vision - ACCV 2006 : 7th Asian Conference on Computer Vision, Hyderabad, India, January 13 - 16, 2006; proceedings( )

1 edition published in 2006 in English and held by 9 WorldCat member libraries worldwide

Computer vision - ACCV 2006 : 7th Asian Conference on Computer Vision, Hyderabad, India, January 13 - 16, 2006; proceedings( )

1 edition published in 2006 in English and held by 9 WorldCat member libraries worldwide

Implementation and evaluation of a three-dimensional photometric sampler by Hideichi Sato( Book )

3 editions published in 1992 in English and held by 6 WorldCat member libraries worldwide

An extraction algorithm uses the set of image brightness values measured at each surface point in order to compute orientation as well as the strengths of the Lambertian and specular reflection components. In order to increase the accuracy in measured orientations and reflectance parameters, we have developed a calibration method to overcome the the [sic] difference between the theoretical and the actual distributions of extended source brightness. The experimental conducted on Lambertian surfaces, specular surfaces, and hybrid surfaces show high accuracy in both estimated orientations as well as reflectance parameters. We have demonstrated the ability of our system to detect cracks, and reflectance parameter variances in several industrial objects."
Shape from interreflections by Shree K Nayar( Book )

2 editions published in 1990 in English and held by 5 WorldCat member libraries worldwide

The recovery algorithm works on Labertian surfaces of arbitrary shape with possibly varying and unknown reflectance. The general behavior of the algorithm and its convergence properties are discussed. Both simulation as well as experimental results are included to demonstrate the accuracy and stability of the algorithm."
The appearance of human skin : a survey by Takanori Igarashi( Book )

4 editions published in 2007 in English and held by 5 WorldCat member libraries worldwide

Skin is the outer-most tissue of the human body. As a result, people are very aware of, and very sensitive to, the appearance of their skin. Consequently, skin appearance has been a subject of great interest in various fields of science and technology. In particular, research on skin appearance has been intensely pursued in the fields of computer graphics, computer vision, cosmetology, and medicine. In this survey, we review the most prominent results related to skin in these fields and show how these seemingly disconnected studies are related to one another. In each of the fields, the optical behaviors of specific skin components have been studied from the viewpoint of the specific objectives of the field. However, the different components of skin produce different types of optical phenomena that are determined by their physio-anatomical characteristics (sizes, shapes, and functions of the components). The final appearance of skin has contributions from complex optical interactions of many different skin components with light. In order to view these interactions in a unified manner, we describe and categorize past works based on the physiological and anatomical characteristics of the various skin components
Extracting shape and reflectance of lambertian, specular, and hybrid surfaces by Shree K Nayar( Book )

2 editions published in 1988 in English and held by 5 WorldCat member libraries worldwide

All existing shape extraction techniques that are based on photometric measurements rely on assumed surface reflection properties. A method is proposed for determining the shape of surfaces whose reflectance properties may vary from Lambertian to specular without prior knowledge of the relative strengths of the Lambertian and specular components of reflection. The object surface is illuminated using extended light sources and is viewed from a single direction. Surface illumination using extended sources makes it possible to ensure the detection of both Lambertian and specular reflections. Multiple source directions are used to obtain an image sequence of the object. An extraction algorithm uses the set of image intensity values measured at each surface point to compute orientation as well as the relative strengths of the Lambertian and specular reflection components. The proposed methods has been named photometric sampling as it uses samples of a photometric function that relates image intensity to surface orientation, reflectance, and light source characteristics that describes the reflectance model and orientation of a surface point. Experiments were conducted on Lambertian surfaces, specular surfaces, and hybrid surfaces whose reflectance model is composed of both Lambertian and specular components. The results show high accuracy in measured orientations and estimated reflectance parameters. Keywords: Extraction techniques; Photometric measurements; Reflectance properties; Specular reflectance; Photometric sampling
Surface reflection : physical and geometrical perspectives by Shree K Nayar( Book )

2 editions published in 1989 in English and held by 3 WorldCat member libraries worldwide

Machine vision can greatly benefit from the development of accurate reflectance models. There are two approaches to the study of reflection: physical and geometrical optics. While geometrical models may be construed as mere approximations to physical models, they possess simpler mathematical forms that often render them more usable than physical models. However, geometrical models are applicable only when the wavelength of incident light is small compared to the dimensions of the surface imperfections. Therefore, it is incorrect to use these models to interpret or predict reflections from smooth surfaces, and only physical models are capable of describing the underlying reflection mechanism. This paper is directed towards unifying physical and geometrical approaches to describe reflection from surfaces that may vary from smooth to rough. More specifically, we consider the Beckmann-Spizzichino (physical optics) model and the Torrance-Sparrow (geometrical optics) model. These two models were chosen in particular as they have been reported to fit experimental data very well. Each model is described in detail, and the conditions that determine the validity of the model are clearly stated. From studying the behaviors of both models. A model is proposed comprising three reflection components: the diffuse lobe, the specular lobe, and the specular spike. The dependencies of the three components on the surface roughness and the angles of incidence and reflection are analyzed in detail
Computer vision, graphics and image processing : recent advances ; [proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP '98) held at Indian Institute of Technology, Delhi, during December 21-23,1998( Book )

1 edition published in 1999 in English and held by 3 WorldCat member libraries worldwide

Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing, held at Delhi during 21-23 December 1998
Shape from focus by Shree K Nayar( Book )

2 editions published in 1989 in English and held by 3 WorldCat member libraries worldwide

We present two algorithms for depth estimation. The first algorithm simply looks for the focus level that maximizes the focus measure at each point. The other algorithm models the SML focus measure variations at each point as a Gaussian distribution and use this model to interpolate the computed focus measures to obtain more accurate depth estimates. The algorithms were implemented and tested using surfaces of different roughness and reflectance properties. We conclude with a brief discussion on how the proposed method can be applied to smooth textures and smooth non-textured surfaces."
Computer Vision - ACCV 2006 (vol. # 3851) 7th Asian Conference on Computer Vision, Hyderabad, India, January 13-16, 2006, Proceedings, Part I by P. J Narayanan( Book )

4 editions published in 2006 in English and held by 2 WorldCat member libraries worldwide

A theory of pattern rejection by Simon Baker( Book )

1 edition published in 1995 in English and held by 2 WorldCat member libraries worldwide

Abstract: "The efficiency of pattern recognition is critical when there are a large number of classes to be discriminated, or when the recognition algorithm must be applied a large number of times. We propose and analyze a general technique, namely pattern rejection, that leads to great efficiency improvements in both cases. Rejectors are introduced as algorithms that very quickly eliminate from further consideration, most of the classes or inputs (depending on the setting). Importantly, a number of rejectors may be combined to form a composite rejector, which performs far more effectively than any of its component rejectors. Composite rejectors are analyzed, and conditions derived which guarantee both efficiency and practicality. A general technique is proposed for the construction of rejectors, based on a single assumption about the pattern classes. The generality is shown through a close relationship with the Karhunen-Loev́e expansion. Further, a comparison with Fisher's discriminant analysis is included to illustrate the benefits of pattern rejection. Composite rejectors were constructed for two applications, namely, object recognition and local feature detection. In both cases, a substantial improvement in efficiency over existing techniques is demonstrated."
Computer Vision - ACCV 2006 (vol. # 3852) 7th Asian Conference on Computer Vision, Hyderabad, India, January 13-16, 2006, Proceedings, Part II by P. J Narayanan( Book )

4 editions published in 2006 in English and held by 2 WorldCat member libraries worldwide

Stereo in the presence of specular reflection by Dinkar N Bhat( Book )

1 edition published in 1994 in English and held by 2 WorldCat member libraries worldwide

Abstract: "The problem of accurate depth estimation using stereo in the presence of specular reflection is addressed. Specular relection is viewpoint dependent and can cause large intensity differences at corresponding points. Hence, mismatches can result causing significant depth errors. Current stereo algorithms largely ignore specular reflection which is a fundamental reflection phenomenon from surfaces, both smooth and rough. We analyzed the physics of specular reflection and the geometry of stereopsis which led us to an interesting relationship between stereo vergence, surface roughness, and the likelihood of a correct match. Given the lower bound on surface roughness, an optimal binocular stereo configuration can be determined which maximizes precision in depth estimation despite specular reflection. However, surface roughness is difficult to estimate in unstructured environments. Therefore, multiple view configurations independent of surface roughness are determined such that at each scene point visible to all sensors, at least one stereo pair provides a correct depth estimate. We have developed a simple algorithm to reconstruct depth from the multiple view images. Experiments with real surfaces confirm the viability of our approach. A key feature of this approach is that we do not seek to eliminate or avoid specular reflection, but rather minimize its effect on stereo matching."
Parametric feature detection by Shree K Nayar( Book )

1 edition published in 1995 in English and held by 2 WorldCat member libraries worldwide

Abstract: "A large number of visual features are parametric in nature, including, [sic] edges, lines, corners, and junctions. We present a general framework for the design and implementation of detectors for parametrized features. For robustness, we argue in favor of elaborate modeling of features as they appear in the physical world. In addition, optical and sensing artifacts are incorporated to achieve realistic feature models in image domain. Each feature is represented as a densely sampled parametrized manifold in a low-dimensional subspace. During detection, the brightness distribution around each image pixel is projected to the subspace. If the projection lies close to the feature manifold, the exact location of the closest manifold point reveals the parameters of the feature. The concepts of parameter reduction by normalization, dimension reduction, pattern rejection, and efficient search are employed to achieve high efficiency. Detectors have been implemented for five specific features, namely, step edge (5 parameters), roof edge (5 parameters), line (6 parameters), corner (5 parameters), and circular disc (6 parameters). All five of these detectors were generated using the same technique by simply inputing [sic] different feature models. Detailed experiments are reported on the robustness of detection and the accuracy of parameter estimation. In the case of the step edge, our results are compared with those obtained using popular detectors. We conclude with a brief discussion on the use of relaxation to refine outputs from multiple feature detectors, and sketch a hardware architecture for a general feature detection machine."
2009 IEEE International Conference on Computational Photography, ICCP : the Palace Hotel, San Francisco, CA : April 16-17, 2009 : ICCP 09 by IEEE International Conference on Computational Photography( )

2 editions published in 2009 in English and held by 0 WorldCat member libraries worldwide

Polycameras: Camera Clusters for Wide Angle Imaging( )

1 edition published in 2005 in English and held by 0 WorldCat member libraries worldwide

We present the idea of a polycamera which is defined as a tightly packed camera cluster. The cluster is arranged so as to minimize the overlap between adjacent views. The objective of such clusters is to be able to image a very large field of view without loss of resolution. Since these clusters do not have a single viewpoint, analysis is provided on the effects of such non-singularities. We also present certain configurations for polycameras which cover varying fields of view. We would like to minimize the number of sensors required to capture a given field of view. Therefore we recommend the use of wide-angle sensors as opposed to traditional long focal length sensors. However, such wide-angle sensors tend to have severe distortions which pull points towards the optical center. This paper also proposes a method for recovering the distortion parameters without the use of any calibration objects. Since distortions cause straight lines in the scene to appear as curves in the image, our algorithm seeks to find the distortions parameters that would map the image curves to straight lines. The user selects a small set of points along the image curves. Recovery of the distortion parameters is formulated as the minimization of an objective function which is designed to explicitly account for noise in the selected image points. Experimental results are presented for synthetic data with different noise levels as well as for real images. Once calibrated, the image stream from a wide angle camera can be undistorted in real time using look up tables. Finally, we apply our distortion correction technique to a polycamera made of four wide-angle cameras to create a high resolution 360 degree panorama in real-time
 
moreShow More Titles
fewerShow Fewer Titles
Audience Level
0
Audience Level
1
  Kids General Special  
Audience level: 0.64 (from 0.49 for Computer v ... to 0.99 for Polycamera ...)

Computer vision - ACCV 2006 : 7th Asian Conference on Computer Vision, Hyderabad, India, January 13 - 16, 2006; proceedingsComputer vision - ACCV 2006 : 7th Asian Conference on Computer Vision, Hyderabad, India, January 13 - 16, 2006; proceedings
Alternative Names
Shree K. Nayar Indian-American engineer

Languages
English (71)

Covers
Computer vision - ACCV 2006 : 7th Asian Conference on Computer Vision, Hyderabad, India, January 13 - 16, 2006; proceedingsComputer vision - ACCV 2006 : 7th Asian Conference on Computer Vision, Hyderabad, India, January 13 - 16, 2006; proceedingsComputer vision - ACCV 2006 : 7th Asian Conference on Computer Vision, Hyderabad, India, January 13 - 16, 2006; proceedingsComputer vision - ACCV 2006 : 7th Asian Conference on Computer Vision, Hyderabad, India, January 13 - 16, 2006; proceedingsThe appearance of human skin : a survey