Showing papers in "Image and Vision Computing in 2002"

TL;DR: It is demonstrated that a small number of 2D linear statistical models are sufficient to capture the shape and appearance of a face from a wide range of viewpoints and can be used to predict new views of a faces seen from one view and to constrain search algorithms which seek to locate a face in multiple views simultaneously.

TL;DR: A morphological approach to cell image segmentation, that is, more accurate than the classical watershed-based algorithm, is introduced for detecting and classifying malaria parasites in images of Giemsa stained blood slides.

TL;DR: A new method for detecting the three mutually orthogonal directions of such an environment is presented, and compared to existing techniques, this approach is furthermore more rigorous, since all conditions given by three mutually Orthogonal Directions are identified and utilized.

TL;DR: A method that tries to take into account information about discontinuities or sharp luminance variations while doubling the input picture is proposed, which is competitive both for quality and efficiency with bicubic interpolation.

TL;DR: This study supports the hypothesis that the SVM approach is able to extract the relevant discriminatory information from the training data, and believes that this is the main reason for its superior performance over benchmark methods.

TL;DR: This paper addresses the problem of automatically extracting frequently used pedestrian pathways from video sequences of natural outdoor scenes by using path models learnt from the accumulation of trajectory data over long time periods to augment the classification of subsequent track data.

TL;DR: A vision-based system that can interpret a user's gestures in real time to manipulate windows and objects within a graphical user interface and users who tested it found the gestures intuitive and the application easy to use.

TL;DR: A novel force field transformation has been developed in which the image is treated as an array of Gaussian attractors that act as the source of a force field, and shows promising results in automatic ear recognition.

TL;DR: This work describes the construction of accurate panoramic mosaics from multiple images taken with a rotating camera, or alternatively of a planar scene, and demonstrates that the method achieves better results than the alternative approach of optimising over pairs of images.

TL;DR: An end-to-end analysis of a simple model-based vehicle detection algorithm for aerial parking lot images by combining four elongated edge operators designed to collect edge responses from the sides of a vehicle is performed.

TL;DR: This paper derives quantitative measures for the spatial uncertainty of the results provided by SSD-based feature trackers by scale the SSD correlation surface, fit a Gaussian distribution to this surface, and use this distribution to estimate values for a covariance matrix.

TL;DR: A new contour tracing algorithm for tracing boundary contours in a 2D binary image, which plays a very important role in digital image processing, pattern recognition and machine vision system, which is faster on implementation than existing algorithms.

TL;DR: Experiments confirm that the self-learning ability, fault tolerance and adaptability of the two-stage SOM lead to a good segmentation results.

TL;DR: A new approach for estimating and tracking three-dimensional pose of a human face from the face images obtained from a single monocular view with full perspective projection, which is more robust than the existing feature-based approaches for face pose estimation.

TL;DR: A review of both theoretical and experimental research directed towards better understanding of the underlying mechanisms of visual search is presented and some of the major psychophysical models that have been developed over the years are reviewed.

TL;DR: This work extends SVMs to model the appearance of human faces which undergo non-linear change across multiple views and uses inherent factors in the nature of the input images and the SVM classification algorithm to perform both multi-view face detection and pose estimation.

TL;DR: This work considers the self-calibration problem for a moving camera whose intrinsic parameters are known, except the focal length, which may vary freely across different views, and gives a complete catalogue of the so-called critical motion sequences.

TL;DR: This paper introduces the human hand model with 27 degrees of freedom (DOFs) and analyzes some of its constraints to reduce the 27 to 12 DOFs without any significant degradation of performance.

TL;DR: A system for person-independent classification of hand postures against complex backgrounds in video images is presented that employs elastic graph matching, which has already been successfully applied for object and face recognition.

TL;DR: This paper first introduces the Gabor wavelet network (GWN) as a model-based approach for effective and efficient object representation and presents an approach for the estimation of head pose based on the GWNs.

TL;DR: A novel three-dimensional model-based tracking system which has been incorporated into a visual servoing system which combines modern graphical rendering technology with constrained active contour tracking techniques to create wire-frame-snakes.

TL;DR: This paper provides algorithms for adding and subtracting eigenspaces, thus allowing for incremental updating and downdating of data models, and keeps an accurate track of the mean of the data, which allows the methods to be used in classification applications.

TL;DR: In this paper, an automatic technique for the identification of printed Roman, Chinese, Arabic, Devnagari and Bangla text lines from a single document has been presented, using shape-based features, statistical features and some features obtained from the concept of water overflow from the reservoir.

TL;DR: A critical analysis of the performance of the classical ARG and 2D string matching methods indicates that in retrieving images by spatial content, retrieval response time and accuracy are traded-off.

TL;DR: This paper introduces a statistical dynamic framework to model and recognise human activities based on learning prior and continuous propagation of density models of behaviour patterns by addressing problems of probabilistic and uncertain nature of motion patterns, non-linear temporal scaling and ambiguities in temporal segmentation.

TL;DR: A skew estimation algorithm for printed and handwritten documents, based on the document’s horizontal projection profile and its Wigner – Ville distribution, is presented and is able to correct skew angles detecting the right oriented position of the page by the alternations of the horizontal projections.

TL;DR: A novel multi-modal histogram thresholding method in which no a priori knowledge about the number of clusters to be extracted is needed and an optimal parameter estimation interval was defined before the estimation procedure.

TL;DR: An improved algorithm for ovarian follicle detection in ultrasound images that is composed of three successive steps and deals with the entire information in the ultrasound image sequence, which is covered in Part II of this paper.

TL;DR: A fast and reliable optical flow algorithm which produces a dense optical flow map by using fast cross correlation and 3D shortest path techniques is presented.

TL;DR: The system uses a hybrid co-operation approach and is almost automatic and unsupervised and has been measured on two remote sensing applications: agricultural landscape segmentation and forestry vegetation classification.