Narendra Ahuja

A Vision System for Monitoring Intermodal Freight Trains (2009)

A real-world object category can be viewed as a characteristic configuration of its parts, that are themselves simpler, smaller (sub)categories. Recognition of a category can therefore be made easier...

Avinash Kumar, Narendra Ahuja, John M Hart

We describe the design and implementation of a vision based Intermodal Train Monitoring System(ITMS) for extracting various features like length of gaps in an intermodal(IM) train which can later be...

Scale-invariant Region-based Hierarchical Image Matching (2009)

A Tensor Approximation Approach to Dimensionality Reduction (2009)

This paper presents an approach to scale-invariant image matching. Given two images, the goal is to find correspondences between similar subimages, e.g., representing similar objects, even when the...

Hongcheng Wang, Narendra Ahuja, H. Wang, N. Ahuja

Abstract Dimensionality reduction has recently been extensively studied for computer vision applications. We present a novel multilinear algebra based approach to reduced dimensionality...

for (2009)

Tianli Yu, Jiebo Luo, Amit Singhal, Narendra Ahuja

regularized active contour based on dynamic programming

Connected Segmentation Tree – A Joint Representation of Region Layout and Hierarchy (2009)

Extracting a Fluid Dynamic Texture and the Background from Video (2009)

This paper proposes a new object representation, called Connected Segmentation Tree (CST), which captures canonical characteristics of the object in terms of the photometric, geometric, and spatial...

Design Analysis of a High-Resolution Panoramic Camera Using Conventional Imagers and a Mirror Pyramid (2009)

Given the video of a still background occluded by a fluid dynamic texture (FDT), this paper addresses the problem of separating the video sequence into its two constituent layers. One layer...

Hong Hua, Narendra Ahuja, Chunyu Gao, Student Member

Abstract—Wide field of view (FOV) and high-resolution image acquisition is highly desirable in many vision-based applications. Several systems have reported the use of reflections off mirror...

SEGMENTATION-BASED PERCEPTUAL IMAGE QUALITY ASSESSMENT (SPIQA) (2009)

Bernard Ghanem, Esther Resendiz, Narendra Ahuja

Computational representation of perceived image quality is a fundamental problem in computer vision and image processing, which has assumed increased importance with the growing role of images and...

Phase Based Modelling of Dynamic Textures (2009)

Robust Registration and Tracking Using Kernel Density Correlation (2008)

This paper presents a model of spatiotemporal variations in a dynamic texture (DT) sequence. Most recent work on DT modelling represents images in a DT sequence as the responses of a linear dynamical...

Maneesh Singh, Himanshu Arora, Narendra Ahuja

Challenges to accurate registration come from three factors —presence of background clutter, occlusion of the pattern being registered and changes in feature values across images. To address these...

ON THE USE OF DEPTH-FROM-FOCUS IN 3D OBJECT MODELLING FROM MULTIPLE VIEWS (2008)

Ning Xu, Narendra Ahuja

This paper is concerned with depth estimation from focus for acquiring 3D models of objects from multiple views. Depth-from-focus usually involves a single viewpoint but many different focus...

Real-time Omni-directional Distance Measurement with Active Panoramic Vision* (2008)

Sooyeong Yi, Byoungwook Choi, Narendra Ahuja

Abstract: Autonomous navigation of mobile robot requires a ranging system for measurement of distance to environmental objects. It is obvious that the wider and the faster distance measurement gives...

PHASE PCA FOR DYNAMIC TEXTURE VIDEO COMPRESSION (2008)

FACE DETECTION USING LARGE MARGIN CLASSIFIERS (2008)

Temporal or dynamic textures (DT’s) are video sequences that are spatially repetitive and temporally stationary. DT’s are temporal analogs of the well known spatial still image texture. Examples...

Ming-hsuan Yung, Dan Roth, Narendra Ahuja

Large margin classifiers have demonstrated their advantages in many visual learning tasks, and have attracted much at-tention in vision and image processing communities. In this paper we apply and...

Development of Machine Vision Technology for Railcar Safety Appliance Inspection (2008)

J. Riley Edwards, John M. Hart, Sinisa Todorovic, Narendra Ahuja, Zeziong Chua, ...

Summary: Before North American trains depart a terminal or rail yard, many aspects of the cars and locomotives undergo inspection, including their safety appliances. Safety appliances are handholds,...

NETRA- A Parallel Architecture for Integrated Vision Systems II: Algorithms and Performance Evaluation (2008)

Alok N. Choudhary, Janak H. Patel, Narendra Ahuja, Alok N. Choudhary, Janak H. Patel, Narendra Ahuja, ...

InpartI of thispaper we presentedarcMtectureof NETRA [I].Thispaper presentsperformance evaluationof NETRA using several common vision algorithms. Performance of algorithms when they are mapped on one...

Learning the Taxonomy and Models of Categories Present in Arbitrary Images (2008)

N.: Modeling dynamical textures using subspace mixtures (2008)

This paper proposes, and presents a solution to, the problem of simultaneous learning of multiple visual categories present in an arbitrary image set and their intercategory relationships. These...

Che-bin Liu, Ruei-sung Lin, Narendra Ahuja

In this paper, we aim at modeling video sequences that exhibit temporal appearance variation. The dynamic texture model proposed in [6] is effective to model simple dynamic scenes. However, because...

Multispectral Machine Vision for Improved Undercarriage Inspection of Railroad Rolling Stock (2008)

Benjamin Freid, Narendra Ahuja, John M. Hart, Sinisa Todorvic, Nicholas Kocher

Summary: Multispectral machine vision systems have the potential to provide mechanical inspection personnel with a tool to automatically assess and monitor the condition of rolling stock. By...

24 A Novel Omnidirectional Stereo Vision System with a Single Camera 1 (2008)

Sooyeong Yi, Narendra Ahuja

The omnidirectional vision system has been given increasing attentions in recent years in many engineering research areas such as computer vision and mobile robot since it has wide field of view...

A Vision System for Monitoring Intermodal Freight Trains (2008)

Avinash Kumar, Narendra Ahuja, John M Hart

We describe the design and implementation of a vision based Intermodal Train Monitoring System(ITMS) for extracting various features like length of gaps in an intermodal(IM) train which can later be...

CSG-117 N90-14S39 Uncl._s (2008)

De Ember, Alok N. Choudhary, Janak H. Patel, Narendra Ahuja

_ _r ¸-:7 im iB N ID W _t hJ i W,- =_7: = SECuRItY CLASSJF;CATION OF TMIS PAGE m ii i i

A Robust Nonparametric Estimation Framework for Implicit Image Models (2008)

Himanshu Arora, Maneesh Singh, Narendra Ahuja

Robust model fitting is important for computer vision tasks due to the occurrence of multiple model instances, and, unknown nature of noise. The linear errors-in-variables (EIV) model is frequently...

3D Texture Classification Using the Belief Net of a Segmentation Tree (2008)

GRADIENT ADAPTIVE IMAGE RESTORATION AND ENHANCEMENT (2008)

This paper presents a statistical approach to 3D texture classification from a single image obtained under unknown viewpoint and illumination. Unlike in prior work, in which texture primitives...

Hongcheng Wang, Yunqiang Chen, Tong Fang, Jason Tyan, Narendra Ahuja

Various methods have been proposed for image enhancement and restoration. The main difficulty is how to enhance the structures uniformly while suppressing the noise without artifacts. In this paper,...

NOVEL COMPLEX VALUED NEURAL NETWORKS (2008)

Garimella Rama Murthy, Narendra Ahuja

In view of many applications, in recent years, there has been increasing interest in complex valued neural networks. In this paper, it is reasoned that transforming real valued signals into complex...

SHAPE FROM COLOR CONSISTENCY USING NODE CUT (2008)

Ning Xu, Tianli Yu, Narendra Ahuja

In this paper, we present a method to estimate the shape of a three dimensional (3D) object by enforcing color consistency in the views of object points in images acquired from different viewpoints....

(in press) IEEE Trans. Pattern Analysis Machine Intelligence (TPAMI), 2007 Unsupervised Category Modeling, Recognition and Segmentation in Images (2008)

Unsupervised Segmentation of Objects using Efficient Learning (2008)

Suppose a set of arbitrary (unlabeled) images contains frequent occurrences of 2D objects from an unknown category. This paper is aimed at simultaneously solving the following related problems: (1)...

Himanshu Arora, Nicolas Loeff, David A. Forsyth, Narendra Ahuja

We describe an unsupervised method to segment objects detected in images using a novel variant of an interest point template, which is very efficient to train and evaluate. Once an object has been...

PHASE PCA FOR DYNAMIC TEXTURE VIDEO COMPRESSION (2008)

A Refractive Camera for Acquiring Stereo and Super-resolution Images (2008)

Temporal or dynamic textures (DT’s) are video sequences that are spatially repetitive and temporally stationary. DT’s are temporal analogs of the well known spatial still image texture. Examples...

Chunyu Gao, Narendra Ahuja

We propose a novel depth sensing system composed of a single camera, and a transparent plate which is placed in front of the camera and rotates about the optical axis of the camera. The camera takes...

A Tale of Two Classifiers: SNoW vs. SVM in Visual Recognition (2008)

Ming-hsuan Yang, Dan Roth, Narendra Ahuja

Abstract. Numerous statistical learning methods have been developed for visual recognition tasks. Few attempts, however, have been made to address theoretical issues, and in particular, study the...

GRADIENT ADAPTIVE IMAGE RESTORATION AND ENHANCEMENT (2008)

Hongcheng Wang, Yunqiang Chen, Tong Fang, Jason Tyan, Narendra Ahuja

Various methods have been proposed for image enhancement and restoration. The main difficulty is how to enhance the structures uniformly while suppressing the noise without artifacts. In this paper,...

LETTER Communicated by Shimon Edelman Learning to Recognize Three-Dimensional Objects (2008)

Modelling Objects using Distribution and Topology of Multiscale Region Pairs (2008)

A learning account for the problem of object recognition is developed within the probably approximately correct (PAC) model of learnability. The key assumption underlying this work is that objects...

Himanshu Arora, Narendra Ahuja

We propose a method for simultaneous detection, localization and segmentation of objects of a known category. We show that this is possible by using segments as features. To this end, we propose an...

Phase Based Modelling of Dynamic Textures (2008)

Shape Regularized Active Contour using Iterative Global Search and Local Optimization ∗ (2008)

This paper presents a model of spatiotemporal variations in a dynamic texture (DT) sequence. Most recent work on DT modelling represents images in a DT sequence as the responses of a linear dynamical...

Tianli Yu, Narendra Ahuja

Recently, nonlinear shape models have been shown to improve the robustness and flexibility of segmentation. In this paper, we propose Shape Regularized Active Contour (ShRAC) that incorporates...

3D Texture Classification Using the Belief Net of a Segmentation Tree (2008)

Region-based hierarchical image matching (2008)

This paper presents a statistical approach to 3D texture classification from a single image obtained under unknown viewpoint and illumination. Unlike in prior work, in which texture primitives...

held in conjunction with ECCV 2002, Copenhagen, Denmark. Multiview Panoramic Cameras Using a Mirror Pyramid (2008)

This paper presents an approach to region-based hierarchical image matching, where, given two images, the goal is to identify the largest part in image 1 and its match in image 2 having the maximum...

Kar-han Tan, Hong Hua, Narendra Ahuja

A mirror pyramid consists of a set of flat mirror faces arranged around an axis of symmetry, inclined to form a pyramid. By strategically positioning a number of conventional cameras around a mirror...

Uniformity and Homogeneity Based Hierachical Clustering (2007)

Peter Bajcsy, Narendra Ahuja

This paper presents a clustering algorithm for dot patterns in n-dimensional space. The n-dimensional space often represents a multivariate (n f -dimensional) function in a n s -dimensional space (n...

Cv (2007)

Krishna Ratakonda, Supervisor Dr. Ibrahim Sezan, Supervisor Prof, Narendra Ahuja

(5/93 - 7/93) Implemented a multi-channel, parallel, time-shared gateway connecting an X.25 based satellite communication link with a Novell LAN. The system is currently operational. PATENT...

A Fast Scheme for Downsampling and Upsampling in the DCT Domain (2007)

R. DUGAD AND N. AHUJA: A FAST SCHEME FOR IMAGE SIZE CHANGE IN THE COMPRESSED DOMAIN 1 A Fast Scheme for Image Size Change in the Compressed Domain (2007)

Given a video frame or image in terms of its 8 8 block-DCT coecients we wish to obtain a downsized or upsized (by factor of two) version of this frame also in terms of 8 8 block-DCT coecients. We...

Rakesh Dugad, Student Member, Narendra Ahuja

Given a video frame in terms of its 8 8 block-DCT coecients we wish to obtain a downsized or upsized version of this frame also in terms of 8 8 block-DCT coecients. The DCT being a linear unitary...

Fusion of frequency and spatial domain information for motion analysis (2007)

Alexia Briassouli, Narendra Ahuja

This paper presents an approach to the analysis of multiple motions in video, which combines frequency and spatial domain information in a new manner. The tasks of interest are finding the number of...

Learning the taxonomy and models of categories present in arbitrary images (2007)

Extracting texels in 2.1D natural textures (2007)

This paper proposes, and presents a solution to, the problem of simultaneous learning of multiple visual categories present in an arbitrary image set and their intercategory relationships. These...

Learning Nonlinear Manifolds from Time Series (2006)

This paper proposes the problem of unsupervised extraction of texture elements, called texels, which repeatedly occur in the image of a frontally viewed, homogeneous, 2.1D, planar texture, and...

Ruei-sung Lin, Che-bin Liu, Ming-hsuan Yang, Narendra Ahuja, Stephen Levinson

Abstract. There has been growing interest in developing nonlinear dimensionality reduction algorithms for vision applications. Although progress has been made in recent years, conventional nonlinear...

Int J Comput Vis DOI 10.1007/s11263-007-0077-5 Region-Based Hierarchical Image Matching (2006)

Sinisa Todorovic, Narendra Ahuja, S. Todorovic, N. Ahuja, N. Ahuja

Abstract This paper presents an approach to region-based hierarchical image matching, where, given two images, the goal is to identify the largest part in image 1 and its match in image 2 having the...

Extracting subimages of an unknown category from a set of images (2006)

An omnidirectional stereo vision system using a single camera (2006)

Suppose a set of images contains frequent occurrences of objects from an unknown category. This paper is aimed at simultaneously solving the following related problems: (1) unsupervised...

Sooyeong Yi, Narendra Ahuja

We describe a new omnidirectional stereo imaging system that uses a concave lens and a convex mirror to produce a stereo pair of images on the sensor of a conventional camera. The light incident from...

Sparse lumigraph relighting by illumination and reflectance estimation from multi-view images, Eurograpics Symposium on Rendering (EGSR (2006)

Tianli Yu, Hongcheng Wang, Narendra Ahuja

and generate the final composite image (right). Abstract We present a novel image-based modeling technique which allows simultaneous estimation of illumination, diffuse, and specular albedo maps...

Extracting subimages of an unknown category from a set of images (2006)

Perceptual Structure and Shape from Texture. (2005)

Suppose a set of images contains frequent occurrences of objects from an unknown category. This paper is aimed at simultaneously solving the following related problems: (1) unsupervised...

Videoshop: A New Framework for Spatio-Temporal Video Editing (2005)

There were two major objectives of our research under grant AFOSR-88 -0219. The first of our research concerned perceptual grouping. The goal here is to segment an image into its perceptual...

Hongcheng Wang, Ning Xu, Ramesh Raskar, Narendra Ahuja

This paper proposes a new framework for video editing in gradient domain. The spatio-temporal gradient fields of target videos are modified and/or mixed to generate a new gradient field which is...

Out-of-Core Tensor Approximation of Multi-Dimensional Matrices Of Visual Data (2005)

Hongcheng Wang, Qing Wu, Lin Shi, Yizhou Yu, Narendra Ahuja

Tensor approximation is necessary to obtain compact multilinear models for multi-dimensional visual datasets. Traditionally, each multi-dimensional data item is represented as a vector. Such a scheme...

Mitsubishi Electric Research Laboratories (2005)

Http Www Merl, Hongchen Wang, Hongcheng Wang, Ramesh Raskar, Ramesh Raskar, Narendra Ahuja, ...

This paper presents a new framework for seamless video Editing in the gradient domain. The spatio-temporal gradient fields of target videos are modified or mixed to generate a new gradient field,...

Rank-R Approximation of Tensors Using Image-as-Matrix Representation (2005)

Hongcheng Wang, Narendra Ahuja

We present a novel multilinear algebra based approach for reduced dimensionality representation of image ensembles. We treat an image as a matrix, instead of a vector as in traditional dimensionality...

High dynamic range video using split aperture camera (2005)

Hongcheng Wang, Ramesh Raskar, Narendra Ahuja

We present a new approach to display High Dynamic Range (HDR) video using gradient based high dynamic range compression. To obtain HDR video, we utilize the split aperture camera. We apply a...

Two-channel predictive multiple description coding (2005)

Ashish Jagmohan, Anshul Sehgal, Narendra Ahuja

This paper presents a multiple description (MD) video codec based on the principles side-information coding. In particular, we highlight certain key components of the codec design that contribute...

A robust probabilistic estimation framework for parametric image models (2004)

Maneesh Singh, Himanshu Arora, Narendra Ahuja

Abstract. Models of spatial variation in images are central to a large number of low-level computer vision problems including segmentation, registration, and 3D structure detection. Often, images are...

A robust probabilistic estimation framework for parametric image models (2004)

Maneesh Singh, Himanshu Arora, Narendra Ahuja

Abstract. Models of spatial variation in images are central to a large number of low-level computer vision problems including segmentation, registration, and 3D structure detection. Often, images are...

Multiview panoramic cameras using mirror pyramids (2004)

Hong Hua, Ieee Computer Society, Narendra Ahuja

Abstract—A mirror pyramid consists of a set of planar mirror faces arranged around an axis of symmetry and inclined to form a pyramid. By strategically positioning a number of conventional cameras...

Wyner-Ziv Coding of Video: An Error-Resilient Compression Framework (2004)

Anshul Sehgal, Ashish Jagmohan, Narendra Ahuja

This paper addresses the problem of video coding in a joint source-channel setting. In particular, we propose a video encoding algorithm that prevents the indefinite propagation of errors in...

Robust Registration and Tracking Using Kernel Density Correlation (2004)

Maneesh Singh Himanshu, Maneesh Singh, Himanshu Arora, Narendra Ahuja

Challenges to accurate registration come from three factors ---presence of background clutter, occlusion of the pattern being registered and changes in feature values across images. To address these...

Single Camera Stereo Using Planar Parallel Plate (2004)

Chunyu Gao, Narendra Ahuja

A system of using a planar parallel plate to achieve single camera stereo has been proposed by Nishimoto and Shirai[5].Their work was based on an assumption that the optical axis of the camera was...

Shape and view independent reflectance map from multiple views (2004)

Tianli Yu, Ning Xu, Narendra Ahuja

Abstract. We consider the problem of estimating the 3D shape and reflectance properties of an object made of a single material from a calibrated set of multiple views. To model reflectance, we...

N.: Recovering shape and reflectance model of nonlambertian objects from multiple views (2004)

Tianli Yu, Ning Xu, Narendra Ahuja

This paper proposes an algorithm to simultaneously estimate both the 3D shape and parameters of a surface reflectance model from multiple views of an object made of a single material. The algorithm...

Seamless video editing (2004)

Hongcheng Wang, Ramesh Raskar, Narendra Ahuja

This paper presents a new framework for seamless video Editing in the gradient domain. The spatio-temporal gradient fields of target videos are modified or mixed to generate a new gradient field,...

Scalable video coding using Wyner-Ziv codes (2004)

Anshul Sehgal, Ashish Jagmohan, Narendra Ahuja

This papers proposes a solution to the problem of scalable predictive coding of video by posing it as a variant of the Wyner-Ziv side information problem. We model the predictor for each frame of a...

Compact representation of multidimensional data using tensor rank-one decomposition (2004)

Hongcheng Wang, Narendra Ahuja

This paper presents a new approach for representing multidimensional data by a compact number of bases. We consider the multidimensional data as tensors instead of matrices or vectors, and propose a...

Regression based Bandwidth Selection for Segmentation using Parzen Windows (2003)

Maneesh Singh Narendra, Narendra Ahuja

We consider the problem of segmentation of images that can be modelled as piecewise continuous signals having unknown, non-stationary statistics. We propose a solution to this problem which first...

Facial Expression Decomposition (2003)

Hongcheng Wang Narendra, Narendra Ahuja

In this paper, we propose a novel approach for facial expression decomposition - Higher-Order Singular Value Decomposition (HOSVD), a natural generalization of matrix SVD. We learn the expression...

Piecewise Approximation of Pictures: Further Experiments. (2002)

Ahuja,Narendra, Davis,Larry S., Milgram,David L., Rosenfeld,Azriel

In an earlier report, a new method of generating skeleton representations of noisy, grayscale pictures was described. This supplemental report investigates some variations on the basic method, and...

A Survey of Random Pattern Generation Processes. (2002)

Schachter,Bruce, Ahuja,Narendra

Random pattern generation processes can provide a rich class of models for both the synthesis and analysis of visual textures. This report describes a variety of such processes including point...

A Note on the Use of Second-Order Gray Level Statistics for Threshold Selection. (2002)

Ahuja,Narendra, Rosenfeld,Azriel

The gray level histogram of an image is commonly used as an aid in selecting thresholds for segmenting the image. Various methods have been proposed to make threshold selection easier. This note...

Statistical Inference Theory Applied to Image Modeling. (2002)

Chellappa,Ramalingam, Ahuja,Narendra

This paper considers the application of system identification techniques using spectral representation for fitting models to textures and images and consists of two parts. In part I, we develop...

Mosaic Models for Image Analysis and Synthesis. (2002)

Fitting Mosaic Models to Textures. (2002)

This report is concerned with a class of models for natural images that treat an image as a mosaic, composed of patches generated by a random geometric process. These models are contrasted with...

Ahuja,Narendra, Rosenfeld,Azriel

Mosaic image models are defined by random geometric processes. Various properties of the patterns generated by such models can be predicted. Using these properties, we can fit the models to real...

Extracting Perceptual Structure in Dot Patterns: An Integrated Approach. (2002)

Tuceryan,Mihran, Ahuja,Narendra

This paper presents a computational approach to perceptual grouping in dot patterns. Detection of perceptual organization is done in two steps. The first step called thelowest level grouping,...

Multiview Panoramic Cameras Using Mirror Pyramids (2002)

Kar-han Tan, Kar-han Tan, Hong Hua, Hong Hua, ...

A mirror pyramid consists of a set of planar mirror faces arranged around an axis of symmetry and inclined to form a pyramid. By strategically positioning a number of conventional cameras around a...

Detecting faces in images: A survey (2002)

Ming-hsuan Yang, David J. Kriegman, Senior Member, Narendra Ahuja

Abstract—Images containing faces are essential to intelligent vision-based human computer interaction, and research efforts in face processing include face recognition, face tracking, pose...

Extraction of 2d motion trajectories and its application to hand gesture recognition (2002)

Ming-hsuan Yang, Narendra Ahuja, Mark Tabb

AbstractÐWe present an algorithm for extracting and classifying two-dimensional motion in an image sequence based on motion trajectories. First, a multiscale segmentation is performed to generate...

Extraction of 2d motion trajectories and its application to hand gesture recognition (2002)

Ming-hsuan Yang, Narendra Ahuja, Mark Tabb

AbstractÐWe present an algorithm for extracting and classifying two-dimensional motion in an image sequence based on motion trajectories. First, a multiscale segmentation is performed to generate...

Using a head-mounted projective display in interactive augmented environments (2001)

Hong Hua, Chunyu Gao, Leonard D. Brown, Narendra Ahuja, Email Honghuauiuc Edu, Jannick P. Rolland

Head-mounted projective displays (HMPD) have been recently proposed as an alternative to conventional eyepiece-type head-mounted displays (HMDs). HMPDs consist of a pair of miniature projection...

Face detection using multimodal density models (2001)

Ming-hsuan Yang, David Kriegman, Narendra Ahuja

We present two methods using multimodal density models for face detection in gray-level images. One generative method uses a mixture of factor analyzers to concurrently perform clustering and, within...

Representation and Three-Dimensional Interpretation of Image Texture: An Integrated Approach (2000)

Blostein, Dorothea, Ahuja, Narendra

A perspective view of a slanted textured surface shows systematic changes in density, area and aspect-ratio of texture elements. The apparent changes in texture element properties can be analyzed to...

Estimating sensor orientation in cameras (2000)

Manoj Aggarwal, Narendra Ahuja

For most imaging cameras, it is desirable that the sensor plane be perpendicular to the optical axis. Such an orientation ensures that the imaging configuration is perspective and planar scene...

Learning to recognize objects (2000)

Face Detection Using Mixtures of Linear Subspaces (2000)

A learning account for the problem of object recognition is developed within the PAC (Probably Approximately Correct) model of learnability. The proposed approach makes no assumptions on the...

Learning to Recognize 3D Objects (2000)

We present two methods using mixtures of linear subspaces for face detection in gray level images. One method uses a mixture of factor analyzers to concurrently perform clustering and, within each...

Face Recognition Using Kernel Eigenfaces (2000)

A learning account for the problem of object recognition is developed within the PAC (Probably Approximately Correct) model of learnability. The key assumption underlying this work is that objects...

A SNoW-Based Face Detector (2000)

Eigenceface or Principal Component Analysis (PCA) methods have demonstrated their success in face recognition, detection, and tracking. The representation in PCA is based on the second order...

Ming-hsuan Yang, Dan Roth, Narendra Ahuja

A novel learning approach for human face detection using a network of linear units is presented. The SNoW learning architecture is a sparse network of linear functions over a pre-defined or...

View-Based 3D Object Recognition Using SNoW (2000)

Ming-hsuan Yang, Narendra Ahuja, Dan Roth

This paper describes a novel view-based algorithm for 3D object recognition using a network of linear units. The SNoW learning architecture is a sparse network of linear functions over a pre-defined...

Learning to Recognize 3D Objects with SNoW (2000)

Ming-Hsuan Yang, Dan Roth, Narendra Ahuja

This paper describes a novel view-based learning algorithm for 3D object recognition from 2D images using a network of linear units. The SNoW learning architecture is a sparse network of linear...

Learning to Recognize Objects (2000)

A Geometric Approach to Train Support Vector Machines (2000)

A learning account for the problem of object recognition is developed within the PAC (Probably Approximately Correct) model of learnability. The proposed approach makes no assumptions on the...

A SNoW-Based Face Detector (2000)

Support Vector Machines (SVMs) have shown great potential in numerous visual learning and pattern recognition problems. The optimal decision surface of a SVM is constructed from its support vectors...

A SNoW-Based Face Detector (2000)

A novel learning approach for human face detection using a network of linear units is presented. The SNoW learning architecture is a sparse network of linear functions over a pre-defined or...

Face Detection Using Mixtures of Linear Subspaces (2000)

A novel learning approach for human face detection using a network of linear units is presented. The SNoW learning architecture is a sparse network of linear functions over a pre-defined or...

Ming-Hsuan Yang, Narendra Ahuja, David Kriegman

We present two methods using mixtures of linear subspaces for face detection in gray level images. One method uses a mixture of factor analyzers to concurrently perform clustering and, within each...

Recognizing Hand Gestures Using Motion Trajectories (2000)

Ming-Hsuan Yang, Narendra Ahuja

We present an algorithm for extracting and classifying two-dimensional motion in an image sequence based on motion trajectories. First, a multiscale segmentation is performed to generate homogeneous...

Face detection using mixtures of linear subspaces (2000)

Learning to Recognize 3D Objects with SNoW (2000)

We present two methods using mixtures of linear subspaces for face detection in gray level images. One method uses a mixture of factor analyzers to concurrently perform clustering and, within each...

Ming-hsuan Yang, Dan Roth, Narendra Ahuja

Abstract. This paper describes a novel view-based learning algorithm for 3D object recognition from 2D images using a network of linear units. The SNoW learning architecture is a sparse network of...

A fast scheme for altering resolution in the compressed domain (1999)

Video Denoising by Combining Kalman and Wiener Estimates (1999)

Given a video frame or image in terms of its 8 8 block-DCT coecients we wish to obtain a downsized (lower resolution) or upsized (higher resolution) version of this frame also in terms of 8 8...

Face Detection Using A Mixture Of Factor Analyzers (1999)

This paper proposes a computationally fast scheme for denoising a video sequence. Temporal processing is done separately from spatial processing and the two are then combined to get the denoised...

A Survey on Face Detection Methods (1999)

We present a probabilistic method to detect human faces using a mixture of factor analyzers. One characteristic of this mixture model is that it concurrently performs clustering and, within each...

Gaussian Mixture Model for Human Skin Color and Its Applications in Image and Video Databases (1999)

Human faces provide enormous information and a friendly interface in intelligent human computer interaction. This has motivated a very active research area on, among others, face recognition, face...

Gaussian mixture model for human skin color and its application in image and video databases (1999)

This paper is concerned with estimating a probability density function of human skin color using a finite Gaussian mixture model whose parameters are estimated through the EM algorithm. Hawkins'...

Texture Perception and Shape from Texture. (1998)

This paper is concerned with estimating a probability density function of human skin color using a nite Gaussian mixture model whose parameters are estimated through the EM algorithm. Hawkins '...

Software Modules for Stereo, Texture and Perceptual Grouping in Early Vision. (1998)

This report describes the progress of research in texture perception. The goal of the research included perceptual grouping in dot textures, where the goal was to segment a given dot pattern into its...

Perceptual Grouping and Shape from Texture. (1998)

The goal of this project was to develop fast algorithms for performing the computations required by the various early vision modules that we have been developing. The early vision modulus require...

Unsupervised multidimensional hierarchical clustering (1998)

This report summarizes the progress made during the year 1990 under grant AFOSR-90-0061. During the grant period of December 1989 to November 1990, we have concentrated on the projects on motion...

Digital image watermarking: Issues in resolving rightful ownership (1998)

A method for multidimensional hierarchical clustering that is invariant to monotonic transformations of the distance metric is presented. The method derives a tree of clusters organized according to...

Krishna Ratakonda, Rakesh Dugad, Narendra Ahuja

In recent literature many strategies for attacking and subverting a watermark have been presented. Such attacks suggest that the ability to embed non-erasable watermarks does not necessarily imply...

Robust Video Shot Change Detection (1998)

Rakesh Dugad, Krishna Ratakonda, Narendra Ahuja

In this paper we present a novel improvement to existing schemes for abrupt shot change detection. Existing schemes declare a shot change whenever the frame to frame histogram difference (FFD) value...

Extracting Gestural Motion Trajectories (1998)

Detecting Human Faces in Color Images (1998)

This paper is concerned with the extraction of spatiotemporal patterns in video sequences with focus on trajectories of gestural motions associated with American Sign Language. An algorithm is...

Extracting gestural motion trajectories (1998)

We propose a new method to detect human faces in color images. A human skin color model is built to capture the chromatic properties based on multivariate statistical analysis. Given a color image,...