Narendra Ahuja - Academia.edu (original) (raw)

Papers by Narendra Ahuja

Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems

A supervised algorithm for computing perceptual groupings in dot patterns is presented. The algor... more A supervised algorithm for computing perceptual groupings in dot patterns is presented. The algorithm uses shape features of the polygons in the Voronoi tessellation of the input pattern. The training patterns identified by humans are used to obtain an initial noncontextual classification which is then refined by a probabilistic relaxation labeling.

LiU-1 4 (7b)~~~~~~~~~~~~~~~~~~ 13 U~ti1~a~.t~~d. A. D. LLOST echnj ca] Inf o rmation Officoi The ... more LiU-1 4 (7b)~~~~~~~~~~~~~~~~~~ 13 U~ti1~a~.t~~d. A. D. LLOST echnj ca] Inf o rmation Officoi The support of the D irectora te of Ma thema tical an d Information Sciences , U .S. Air Force Office of Scientific Research , under Grant AFOSR-77-3271, is gratefully acknowledged , a s is the help of Mrs. Shelly Rowe in preparing this paper. Approved for pub 1j~ re1ea~ev diStrjbutjo~ UnJ.iwjted.

Computer Vision, Graphics, and Image Processing, 1983

Approaches to polygonal decomposition for hierarchical image representation are described. For pl... more Approaches to polygonal decomposition for hierarchical image representation are described. For planar decomposition, quad trees using square and triangular neighborhoods are found to be the only feasible methods, having the same computational complexity. For grid images the choice of the appropriate tree type is determined by the grid topology. Triangular and square quad trees are appropriate for the triangular and square grids, whereas trees of order 7 are necessary for the hexagonal grid.

IEEE Transactions on Systems, Man, and Cybernetics, 1980

Experimental results are presented on some properties of random mosaic models for textures. These... more Experimental results are presented on some properties of random mosaic models for textures. These observations are with the theoretcally predicted values. The preditions are also compared with observations on a real Image.

This paper deals with a class of image models based on random geometric processes. Theoretical an... more This paper deals with a class of image models based on random geometric processes. Theoretical and empirical results on properties of patterns generated using these models are summarized. These properties can be used as aids in fitting the models to images.

2& SECuRtTV CL.ASSIFiCATION AUTORIT' 3. OiSTRIBUTION/AVAILABILITY Of REPORT Approved for public r... more 2& SECuRtTV CL.ASSIFiCATION AUTORIT' 3. OiSTRIBUTION/AVAILABILITY Of REPORT Approved for public release; distribution b. DECLASIF ICATION/IOOWNGRADING SCHEDULE unlimited. 4.IPFORMING ORGANIZATION REPORT NIUMII160' iS. MONITORING ORGANIZATION REPORT NUMBERiS) AD-A154 449 AFOSRTR.8-0349 S NAME Of PERPOIRMING ORGANIZATION ib OFFICE SYMBOL 7s. NAME OF MONITORING ORGANIZATION

Computer Vision, Graphics, and Image Processing, 1985

The cells of the Voronoi tessellation are used as primitives to represent image regions. The tess... more The cells of the Voronoi tessellation are used as primitives to represent image regions. The tessellation is derived from a Poisson point process. The random shapes of cells make the representation attractive for Secure traIWIIi.SSiOn.

This proposal summarizes the progress made during the year 1984-85 under grant AFOSR 82-0317. We ... more This proposal summarizes the progress made during the year 1984-85 under grant AFOSR 82-0317. We have examined the problem of extracting simple. perceptually significant representations of natural textures, and developed a system for lowest level perceptual grouping of dots in dot pattern representation. We have also developed procedures for deriving a "scale-space" representation of natural textures in terms of discs.

Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001

We present an algorithm for computing a representation of image structure, or image segmentation,... more We present an algorithm for computing a representation of image structure, or image segmentation, and use it for selecting objects in the image with freehand sketches drawn by the user over the image. The sketches are mapped onto image segments whose union forms the intended object. The mapping operation is performed with the aid of a simplicial decomposition of the image segmentation-a triangulation formed with vertices chosen to lie along the medial axes of the segments. Each edge of a triangle lies entirely inside the two segments that contains its vertices. This decomposition captures the adjacency information about the segments as well as the shape of the segment boundaries. Any object boundary is completely contained in a set of triangles. The triangles are also used to formulate the problem of estimating gradual photometric transition across an object boundary, called alpha channel estimation, as a set of local, intratriangle alpha channel estimation problems that can then be solved more accurately, independently, and in parallel. Experimental results are included to show how the algorithm allows selection of image objects with complex boundaries using roughly drawn simple sketches.

2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008

This paper proposes a new object representation, called Connected Segmentation Tree (CST), which ... more 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 adjacency and containment properties of its constituent image regions. CST is obtained by augmenting the object's segmentation tree (ST) with inter-region neighbor links, in addition to their recursive embedding structure already present in ST. This makes CST a hierarchy of region adjacency graphs. A region's neighbors are computed using an extension to regions of the Voronoi diagram for point patterns. Unsupervised learning of the CST model of a category is formulated as matching the CST graph representations of unlabeled training images, and fusing their maximally matching subgraphs. A new learning algorithm is proposed that optimizes the model structure by simultaneously searching for both the most salient nodes (regions) and the most salient edges (containment and neighbor relationships of regions) across the image graphs. Matching of the category model to the CST of a new image results in simultaneous detection, segmentation and recognition of all occurrences of the category, and a semantic explanation of these results.

Proceedings of 13th International Conference on Pattern Recognition, 1996

This paper presents a clustering algorithm for dot patterns in n-dimensional space. The n-dimensi... more 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 s + n f = n). The proposed algorithm decomposes the clustering problem into the two lower dimensional problems. Clustering in n f-dimensional space is performed to detect the sets of dots in n-dimensional space having similar n f-variate function values (location based clustering using a homogeneity model). Clustering in n sdimensional space is performed to detect the sets of dots in n-dimensional space having similar interneighbor distances (density based clustering with a uniformity model). Clusters in the n-dimensional space are obtained by combining the results in the two subspaces.

Computer Graphics and Image Processing, 1979

This paper describes some geometric processes giving rise to patterns that may be useful for imag... more This paper describes some geometric processes giving rise to patterns that may be useful for image modelling. Some properties of these processes are described. Several statistics are suggested for modelling purposes. Examples of t,ho patterns that can be generated in this way are provided.

Computer Vision, Graphics, and Image Processing, 1989

This paper presents a computational approach to extracting basic perceptual structure, or the low... more This paper presents a computational approach to extracting basic perceptual structure, or the lowest level grouping in dot patterns. The goal is to extract the perceptual segments of dots that group together because of their relative locations. The dots are interpreted as belonging to the interior or the border of a perceptual segment, or being along a perceived curve, or being isolated. To perform the lowest level grouping, first the geometric structure of the dot pattern is represented in terms of certain geometric properties of the Voronoi neighborhoods of the dots. The grouping is accomplished through independent modules that possess narrow expertise for recognition of typical interior dots, border dots, curve dots, and isolated dots, from the properties of the Voronoi neighborhoods. The results of the modules are allowed to influence and change each other so as to result in perceptual components that satisfy global, Gestalt criteria such as border and curve smoothness and component compactness. Such lateral communication among the modules makes feasible a perceptual interpretation of the local structure in a manner that best meets the global expectations. Thus, an integration is performed of multiple constraints, active at different perceptual levels and having different scopes in the dot pattern, to infer the lowest level perceptual structure. The local interpretations as well as lateral corrections are performed through constraint propagation.using a probabilistic relaxation process. The result is a partitioning of the dot pattern into different perceptual segments or tokens. Unlike dots, these segments possess size and shape properties' in addition t0 lOCatiOnS 8 19X9 Academic Press. Inc.

Computer Vision, Graphics, and Image Processing, 1990

An algorithm is presented that performs set operations (e.g., union or intersection) on two unali... more An algorithm is presented that performs set operations (e.g., union or intersection) on two unaligned images represented by linear quadtrees. This algorithm seeks to minimize the number of nodes that must be searched for or inserted into the disk-based node lists that represent the trees. Windowing and matching operations can also be cast as unaligned set functions; these operations can then be solved by similar algorithms.

Optical and Digital Pattern Recognition, 1987

ABSTRACT

Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181)

A method for multidimensional hierarchical clustering that is invariant to monotonic transformati... more 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 the homogeneity of intracluster and interpoint distances. Higher levels correspond to coarser clusters. At any level the method can detect clusters of different densities, shapes and sizes. The number of clusters and the parameters for clustering are determined automatically and adaptively for a given data set which makes it unsupervised and non-parametric. The method is simple, noniterative and requires low computation. Results on various sample data sets are presented.

2009 IEEE 12th International Conference on Computer Vision, 2009

Given an arbitrary image, our goal is to segment all distinct texture subimages. This is done by ... more Given an arbitrary image, our goal is to segment all distinct texture subimages. This is done by discovering distinct, cohesive groups of spatially repeating patterns, called texels, in the image, where each group defines the corresponding texture. Texels occupy image regions, whose photometric, geometric, structural, and spatial-layout properties are samples from an unknown pdf. If the image contains texture, by definition, the image will also contain a large number of statistically similar texels. This, in turn, will give rise to modes in the pdf of region properties. Texture segmentation can thus be formulated as identifying modes of this pdf. To this end, first, we use a low-level, multiscale segmentation to extract image regions at all scales present. Then, we use the meanshift with a new, variable-bandwidth, hierarchical kernel to identify modes of the pdf defined over the extracted hierarchy of image regions. The hierarchical kernel is aimed at capturing texel substructure. Experiments demonstrate that accounting for the structural properties of texels is critical for texture segmentation, leading to competitive performance vs. the state of the art.

Lecture Notes in Computer Science, 1996

This paper presents a coarse-to-fine algorithm to obtain pinel trajectories in a long image seque... more This paper presents a coarse-to-fine algorithm to obtain pinel trajectories in a long image sequence and to segment it into subsets corresponding to distinctly moving objects. Much of the previous related work has addressed the computation of optical flow over two frames or sparse feature trajectories in sequences. The features used are often small in number and restrictive assumptions are made about them such as the visibility of features in all the frames. The algorithm described here uses a coarse scale point feature detector to form a 3-D dot pattern in the spatiotemporal space. The trajectories are extracted as 3-D curves formed by the points using perceptual grouping. Increasingly dense correspondences are obtained iteratively from the sparse feature trajectories. At the finest level, which is the focus of this paper, all pixels are matched and the finest boundaries of the moving objects are obtained.

Lecture Notes in Computer Science, 2010

We present a novel scale adaptive, nonparametric approach to clustering point patterns. Clusters ... more We present a novel scale adaptive, nonparametric approach to clustering point patterns. Clusters are detected by moving all points to their cluster cores using shift vectors. First, we propose a novel scale selection criterion based on local density isotropy which determines the neighborhoods over which the shift vectors are computed. We then construct a directed graph induced by these shift vectors. Clustering is obtained by simulating random walks on this digraph. We also examine the spectral properties of a similarity matrix obtained from the directed graph to obtain a K-way partitioning of the data. Additionally, we use the eigenvector alignment algorithm of [1] to automatically determine the number of clusters in the dataset. We also compare our approach with supervised[2] and completely unsupervised spectral clustering[1], normalized cuts[3], K-Means, and adaptive bandwidth meanshift[4] on MNIST digits, USPS digits and UCI machine learning data.