By Topic

Object recognition supported by user interaction for service robots

2002

Go

Filter Results

Displaying Results 1 - 25 of 95
  • A comparative study of centroid-based, neighborhood-based and statistical approaches for effective document categorization

    Publication Year: 2002, Page(s):235 - 238 vol.4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (464 KB) | HTML iconHTML

    Associating documents to relevant categories is critical for effective document retrieval. Here, we compare the well-known k-nearest neighborhood (kNN) algorithm, the centroid-based classifier and the highest average similarity over retrieved documents (HASRD) algorithm, for effective document categorization. We use various measures such as the micro and macro F1 values to evaluate their performan... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Classification using a hierarchical Bayesian approach

    Publication Year: 2002, Page(s):103 - 106 vol.4
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (437 KB) | HTML iconHTML

    A key problem faced by classifiers is coping with styles not represented in the training set. We present an application of hierarchical Bayesian methods to the problem of recognizing degraded printed characters in a variety of fonts. The proposed method works by using training data of various styles and classes to compute prior distributions on the parameters for the class conditional distribution... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Proceedings 16th International Conference on Pattern Recognition

    Publication Year: 2002, Page(s):iii - xi
    Request permission for commercial reuse | PDF file iconPDF (333 KB)
    Freely Available from IEEE
  • List of referees

    Publication Year: 2002, Page(s):xv - xvii
    Request permission for commercial reuse | PDF file iconPDF (132 KB)
    Freely Available from IEEE
  • Content based image retrieval using optimum Peano scan

    Publication Year: 2002, Page(s):130 - 133 vol.4
    Cited by:  Papers (2)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (530 KB) | HTML iconHTML

    We present a new technique for content based image retrieval where feature vector to be matched is very much specific to the query image. A particular Peano scan which is optimal in encoding the query image is used to convert the scanning pattern of all database images. Features are derived from these scan converted images to calculate the similarity measure. As the features being query specific, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Author index

    Publication Year: 2002, Page(s):397 - 418
    Request permission for commercial reuse | PDF file iconPDF (1066 KB)
    Freely Available from IEEE
  • Motion estimation and figure-ground segmentation using log-polar images

    Publication Year: 2002, Page(s):166 - 169 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (427 KB) | HTML iconHTML

    A motion estimation algorithm for log-polar images, based on the general framework of Hager and Belhumeur (1998), is presented. The advantages and disadvantages brought by the use of this kind of foveal imaging are discussed. Within this context, a simple, but quite effective approach for figure-ground segmentation is also proposed. Performance results concerning motion estimation and target segme... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image retrieval using re-segmentation driven by query rectangles

    Publication Year: 2002, Page(s):142 - 145 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (463 KB) | HTML iconHTML

    In this paper we address two key issues in image retrieval: (1) the use of rectangles in queries to express properties of regions in the desired target images; and (2) the use of over-segmentation to build the index of images in the database. In our method, the rectangles in the user's query are used to control a partial re-segmentation of each candidate image. These query-driven partial re-segmen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Context-based image modelling

    Publication Year: 2002, Page(s):162 - 165 vol.4
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (503 KB) | HTML iconHTML

    In this work we address the task of adapting the model representation of a given image, in the context of a second target image model. We present the BlobEMD framework, in which the images are represented as sets of blobs, and optimal correspondences are found between the representations of the images and are used to adapt the representation of the source image to that of the target image. The con... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • To each according to its need: kernel class specific classifiers

    Publication Year: 2002, Page(s):94 - 97 vol.4
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (421 KB) | HTML iconHTML

    We present in this paper a new multi-class Bayes classifier that permits using separate feature vectors, chosen specifically for each class. This technique extends previous work on feature class specific classifier to kernel methods, using a new class of Gibbs probability distributions with nonlinear kernel mapping as energy function. The resulting method, that we call kernel class specific classi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parzen-window network intrusion detectors

    Publication Year: 2002, Page(s):385 - 388 vol.4
    Cited by:  Papers (22)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (445 KB) | HTML iconHTML

    Network intrusion detection is the problem of detecting anomalous network connections caused by intrusive activities. Many intrusion detection systems proposed before use both normal and intrusion data to build their classifiers. However, intrusion data are usually scarce and difficult to collect. We propose to solve this problem using a novelty detection approach. In particular, we propose to tak... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning quadratic discriminant function for handwritten character classification

    Publication Year: 2002, Page(s):44 - 47 vol.4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (413 KB) | HTML iconHTML

    For handwriting recognition integrating segmentation and classification, the underlying classifier is desired to give both high accuracy and resistance to outliers. In a previous evaluation study, the modified quadratic discriminant function (MQDF) proposed by Kimura et al. (1987) was shown to be superior in outlier rejection but inferior in classification accuracy as compared to neural classifier... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Probabilistic neural networks supporting multi-class relevance feedback in region-based image retrieval

    Publication Year: 2002, Page(s):138 - 141 vol.4
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (546 KB) | HTML iconHTML

    There are several relevance feedback algorithms available, some algorithms use ad-hoc heuristics or assume that feature vectors are independent regardless of their correlation. In this paper, we propose a new relevance feedback algorithm using probabilistic neural networks (PNN) supporting multi-class learning. In our approach, there is no need to assume that feature vectors are independent and it... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature selection for pose invariant face recognition

    Publication Year: 2002, Page(s):306 - 309 vol.4
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (463 KB) | HTML iconHTML

    One of the major difficulties in face recognition systems is the in-depth pose variation problem. Most face recognition approaches assume that the pose of the face is known. In this work, we have designed a feature based pose estimation and face recognition system using 2D Gabor wavelets as local feature information. The difference of our system from the existing ones lies in its simplicity and it... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new algorithm for inexact graph matching

    Publication Year: 2002, Page(s):180 - 183 vol.4
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (446 KB) | HTML iconHTML

    The graph is an essential data structure for representing relational information. When graphs are used to represent objects, comparing objects amounts to graph matching. Inexact graph matching is the process of finding the best possible matching between two graphs when exact matching is impossible. We propose a new algorithm for the inexact matching problem. The new algorithm decomposes the matchi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Layered detection for multiple overlapping objects

    Publication Year: 2002, Page(s):156 - 161 vol.4
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (505 KB) | HTML iconHTML

    This paper describes a method for detecting multiple overlapping objects from a real-time video stream. Layered detection is based on two processes: pixel analysis and region analysis. Pixel analysis determines whether a pixel is stationary or transient by observing its intensity over time. Region analysis detects regions consisting of stationary pixels corresponding to stopped objects. These regi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improving classification rates by modelling the clusters of training sets in features space using mathematical morphology operators

    Publication Year: 2002, Page(s):90 - 93 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (431 KB) | HTML iconHTML

    The exploration of features presented by the training sets of each class (size, shape and orientation) in order to construct the respective decision region borders without making explicitly any statistical hypothesis is presented in this paper. Its incorporation allows one to define more correct decision borders since there is a significant improvement in the classification rates obtained. Mathema... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Media-integrated biometric person recognition based on the Dempster-Shafer theory

    Publication Year: 2002, Page(s):381 - 384 vol.4
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (414 KB) | HTML iconHTML

    The paper describes a new integration method of speech and facial image information for person recognition problems based on the Dempster-Shafer probability theory. The Dempster-Shafer theory provides an attractive methodology by which to integrate multiple numerical evidences containing ambiguities. However, no concrete and reasonable methodology exists to enumerate the reliability of evidences. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stochastic filtering for motion trajectory in image sequences using a Monte Carlo filter with estimation of hyper-parameters

    Publication Year: 2002, Page(s):68 - 73 vol.4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (536 KB) | HTML iconHTML

    False matching due to errors in feature extraction and changes in illumination between frames may occur in feature tracking in image sequences. False matching leads to outliers in feature motion trajectory. One way of reducing the effect of outliers is stochastic filtering using a state space model for motion trajectory. Hyper-parameters in the state space model, e.g., variances of noise distribut... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optical snow and the aperture problem

    Publication Year: 2002, Page(s):264 - 267 vol.4
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (433 KB) | HTML iconHTML

    Classical studies of measuring image motion by computer have concentrated on the case of optical flow, in which there is a unique velocity near each point of the image. In Langer and Mann (2001), we introduced a generalization of optical flow in which a range of parallel velocities can occur near each point in the image. Such image motion arises in many natural situations, such as camera motion in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Differentiation between alphabetic and numeric data using NN ensembles

    Publication Year: 2002, Page(s):40 - 43 vol.4
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (438 KB) | HTML iconHTML

    Presents an approach to differentiating handwritten alphabetic words from numeric strings, which is motivated by an application in a real-life bank cheque processing system. Neural networks are first considered with the focus on effective feature extraction and architecture selection. The combination of networks is then implemented to achieve highly reliable and accurate results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fast near-optimal algorithm for approximation of polygonal curves

    Publication Year: 2002, Page(s):335 - 338 vol.4
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (402 KB) | HTML iconHTML

    Approximation of polygonal curves can be solved by dynamic programming. These methods provide an optimal solution but are slow for a large number of vertices. We propose a new optimization approach based on dynamic programming with a reduced-search in the state space. The proposed algorithm is simple, fast, and has low space complexity. The time and quality trade-off can be controlled by selecting... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Building a latent semantic index of an image database from patterns of relevance feedback

    Publication Year: 2002, Page(s):134 - 137 vol.4
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (548 KB) | HTML iconHTML

    This paper proposes a novel view of the information generated by relevance feedback. The latent semantic analysis is adapted to this view to extract useful inter-query information. The view presented in this paper is that the fundamental vocabulary of the system is the images in the database and that relevance feedback is a document whose words are the images. A relevance feedback document contain... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Face detection and synthesis using Markov random field models

    Publication Year: 2002, Page(s):201 - 204 vol.4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (574 KB) | HTML iconHTML

    Markov random fields (MRFs) are proposed as viable stochastic models for the spatial distribution of gray levels for images of human faces. These models are trained using data bases of face and non-face images. The trained MRF models are then used for detecting human faces in test images. We investigate the performance of the face detection algorithm for two classes of MRFs given by the first- and... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Head pose estimation using view based eigenspaces

    Publication Year: 2002, Page(s):302 - 305 vol.4
    Cited by:  Papers (19)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (402 KB) | HTML iconHTML

    View based eigenspaces can improve the performance of face recognition algorithms. In this work, we demonstrate their use in head pose estimation from head and shoulders video sequences. Our method compares the projected energies of the test image in multiple eigenspaces. We also demonstrate that very few eigenspaces are necessary for a rough estimate of head pose. The method is robust and computa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.