Chair: Rama Chellappa, University of Maryland (USA)
M. Koschinski, University of Technology, Munich (GERMANY)
H.-J. Winkler, University of Technology, Munich (GERMANY)
M. Lang, University of Technology, Munich (GERMANY)
In this paper an efficient on-line recognition system for symbols within handwritten mathematical expressions is proposed. The system is based on the generation of a symbol hypotheses net and the classification of the elements within the net. The final classification is done by calculating the most probable path through the net under regard of the stroke group probabilities and the probabilities obtained by the symbol recognizer based on Hidden Markov Models.
Abbas Edalat, University of London (UK)
David W.N. Sharp, University of London (UK)
R. Lyndon While, University of Western Australia (AUSTRALIA)
Fractal images defined by an iterated function system (IFS) are specified by a finite number of contractive affine transformations. In order to plot the image specified by the transformations on the screen of a digital computer, it is necessary to determine a bounding area for the image. This paper derives a formula that expresses the dimensions of this bounding area in terms of the transformations.
Richard Buse, University of Melbourne (AUSTRALIA)
Zhi-Qiang Liu, University of Melbourne (AUSTRALIA)
An innovative and powerful method is proposed for measuring physical parameters of lines using the responses from a bank of Gabor filters. These measurements are made without resorting to an image ruler. First the system is calibrated by establishing a relationship between the frequency of the Gabor filter and line length, then the length and angle of of isolated lines can be measured. A constraint on this method is that the lines in the scene need to be separated and isolated by a minimum distance. Results indicate that Gabor filters can be successfully applied to the measurement of geometric properties of objects, especially where Gabor filters are already being used for processing tasks. The best accuracies in terms of measurement error for the line length and angle measurements were 0.81% and 0.0% respectively.
Edward R. Dowski Jr., University of Colorado (USA)
W. Thomas Cathey, University of Colorado (USA)
We present a unique method of designing incoherent optical systems for detection and estimation tasks. Our approach is novel in that it physically consists of a phase mask placed at the lens of a standard incoherent optical system. This phase mask provides the ability to shift the phase of the incoming light at discrete regions at the lens. The use of this phase mask allows control of the optical transfer function (OTF) and impulse response, or point spread function (PSF), of the incoherent optical system. With the combination phase mask/incoherent optical system, and digital processing of resulting intermediate image, the overall detection and estimation performance of the system can be greatly enhanced. We describe three applications of this method. These are single-lens, single-image passive range estimation, high-resolution extended depth of field, and passive range detection.
Nelson L. Chang, University of California at Berkeley (USA)
Avideh Zakhor, University of California at Berkeley (USA)
This paper focuses on the representation and arbitrary view generation of three dimensional (3-D) scenes. In contrast to existing methods that construct a full 3-D model or those that exploit geometric invariants, our representation consists of dense depth maps at several preselected viewpoints from an image sequence. Furthermore, instead of using multiple calibrated stationary cameras or range data, we derive our depth maps from image sequences captured by an uncalibrated camera. We propose an adaptive matching algorithm which assigns various confidence levels to different regions. Nonuniform bicubic spline interpolation is then used to fill in low confidence regions in the depth maps. Once the depth maps are computed at preselected viewpoints, the intensity and depth at these locations are used to reconstruct arbitrary views of the 3-D scene. Experimental results are presented to verify our approach.
H.-J. Winkler, University of Technology (GERMANY)
H. Fahrner, University of Technology (GERMANY)
M. Lang, University of Technology (GERMANY)
In this paper an efficient system for structural analysis of handwritten mathematical expressions is proposed. To handle the problems caused by handwriting, this system is based on a soft-decision approach. This means that alternatives for the solution are generated during the analysis process if the relation between two symbols within the expression is ambiguous. Finally a string containing the mathematical information is generated and syntactical verified for each alternative. Strings failing this verification are considered as invalid.
Stefano Fioravanti, Saclant Undersea Research Center
Daniele D. Giusto, University of Cagliari (ITALY)
The paper addresses the analysis of singular distributions defined on a fractal support, called fractal measures. In general, a fractal measure has an infinite number of singularities of infinitely many types. The term multifractals expresses the fact that points, corresponding to a given type of singularity, tipically form a fractal subset whose dimensions depend on the type of singularity. The theory of the q-th order generalized fractal dimensions supplies a tool for the characterization of such multifractal measures. This theory results from an extension of the fractal dimension to different-order statistics. The paper exploits such concepts in order to face the problem of texture recognition. In particular the fractal measure taken into account is the 2D distribution of the optical mass of an image; some theoretical aspects related to this problem are addressed. Results on real images are presented and discussed.
Jane You, University of South Australia (AUSTRALIA)
Edwige Pissaloux, Universite Paris XI (FRANCE)
H.A. Cohen, La Trobe University (AUSTRALIA)
This paper presents a parallel approach to a hierarchical image matching scheme using the Hausdorff distance for object recognition and localization in aerial images. Unlike the conventional matching methods in which edge pixels are considered as image feature pixels in distance transform and the blind pointwise comparison procedure in terms of the Hausdorff distance is applied, a guided image matching system is developed by the hierarchical detection of interesting points via a dynamic thresholding scheme for thesearch of the best matching between two image sets. Furthermore, the concept of remote procedure call (RPC) in distributed systems is introduced for the parallel implementation to achieve the speedup without specific software and hardware requirement .Key words and phrases: Image matching, distance transform, edge detection, interesting point, parallel implementation, remote procedure call (RPC).
Magnus Snorrason, Charles River Analytics (USA)
Harald Ruda, Charles River Analytics (USA)
Alper Caglayan, Charles River Analytics (USA)
This paper presents an Automatic Target Recognition (ATR) system for laser radar (LADAR) imagery, designed to classify objects at multiple levels of discrimination (target detection, classification, and recognition) from single LADAR images. Segmentation is performed in both the range and non-range LADAR channels and results combined to increase object detection rate or decrease false positive detection rate. Through use of the range data, object subimages are projected and rotated to canonical orientations, providing invariance to translation, scale and rotations in 3-D. Global features are extracted for rapid target detection and local receptive field features are computed for target recognition. 100% detection and recognition rates are shown for a small set of real LADAR data.
Quang Minh Tieng, Queensland University of Technology (AUSTRALIA)
W.W. Boles, Queensland University of Technology (AUSTRALIA)
A wavelet based representation of planar objects is introduced. Based on this representation, a matching algorithm using indexing techniques is also developed for identifying unknown objects. Rather than considering all points on the representation, only extrema are used in constructing the look-up table and matching. Simulations demonstrate that the proposed algorithm is effective and accurate in classifying objects under similarity transformations and in a noisy environment.