By Topic

# Image Processing and Its Applications, 1999. Seventh International Conference on (Conf. Publ. No. 465)

## Filter Results

Displaying Results 1 - 25 of 83
• ### A common image processing framework for 2D barcode reading

Publication Year: 1999, Page(s):652 - 655 vol.2
Cited by:  Papers (24)
| | PDF (208 KB)

The present work describes an image processing system able to locate, segment and decode the most common 2D symbol used in bar code applications. The different symbol are treated by exploiting their similarities, in order to achieve an unified computational structure View full abstract»

• ### Learning structural change for identification and tracking of vehicles moving in open world scenes

Publication Year: 1999, Page(s):706 - 710 vol.2
Cited by:  Papers (1)
| | PDF (432 KB)

This paper describes a system, which is able to track multiple man made objects, typically vehicles moving in a natural open world scene. The system interprets changes in structural features in the scene across consecutive image frames and uses the change in structure to identify and track man made objects (target). No a priori knowledge of any structure within the image is assumed. Differences in... View full abstract»

• ### Algorithms for ultra-fast location of ellipses in digital images

Publication Year: 1999, Page(s):542 - 546 vol.2
Cited by:  Papers (1)
| | PDF (488 KB)

This paper shows how an earlier sampling approach can be extended by a range of techniques related to our triple bisection algorithm. These techniques are characterised by very high speed of operation coupled with accurate location: a suitable technique can be chosen and tuned for any of a number of scenarios where a specific level of robustness is required. While we have tested these techniques o... View full abstract»

• ### Page similarity and the Hausdorff distance

Publication Year: 1999, Page(s):755 - 759 vol.2
| | PDF (276 KB)

The VideoWriter is a real-time system that uses digitized images from a computer-controlled video camera to find the location of pages on a desktop. Once an image of a page is extracted, the system must determine if the page has been previously stored. We investigate the use of the Hausdorff distance metric to compare two-level versions of page images. The Hausdorff distance metric does not requir... View full abstract»

• ### Automated detection and neural classification of local defects in textile web

Publication Year: 1999, Page(s):647 - 651 vol.2
| | PDF (280 KB)

This paper describes a vision-based fabric inspection system. The general hardware and software platform, developed for solving this problem, is presented and a powerful novel method for defect inspection is proposed. Using a reduced number of defect classes the system gives consistent repeatable results in the experimental and industrial implementations View full abstract»

• ### Tracking using self-initialising active meshes

Publication Year: 1999, Page(s):701 - 705 vol.2
Cited by:  Papers (2)
| | PDF (304 KB)

This paper describes a method of visual tracking using an active-mesh' that is automatically created and configured directly from a single frame of an image sequence. The aim of this approach is to perform visual tracking in unconstrained motion environments, allowing movement of the camera, the scene and even the inclusion of background-independent moving objects View full abstract»

• ### Fuzzy multiscale edge detection (FMED) applied to automatic left ventricle boundary extraction

Publication Year: 1999, Page(s):552 - 556 vol.2
Cited by:  Papers (2)  |  Patents (1)
| | PDF (268 KB)

This paper describes a new fuzzy multiscale edge detection (FMED) technique. The wavelet transform is employed to produce the multiscale representation of the input signal. The process of developing appropriate multiscale fuzzy subsets describing the degree of edginess' for any pixel is explained. The new FMED technique provides an answer to the question “How to effectively combine the edge... View full abstract»

• ### Wordlength estimation for the enhancement of hand-written word recognition

Publication Year: 1999, Page(s):750 - 754 vol.2
| | PDF (240 KB)

Although the problem of recognising machine printed words has been largely solved using available techniques, no ideal solution has been found for the problem of hand-written word recognition, especially with cursive script. This paper describes a method which can be used to estimate the length of hand-written words. The method shares a number of components with recognition techniques. It does not... View full abstract»

• ### Improving detection of clustered microcalcifications using morphological connected operators

Publication Year: 1999, Page(s):498 - 501 vol.2
Cited by:  Papers (3)
| | PDF (316 KB)

Breast cancer is one of the major causes of death among all cancers for middle-aged and older women, mainly in developed countries, and its incidence is rising. Since the origin of this disease is not yet known, early detection is the best way to reduce the breast cancer mortality. Today, early detection is achieved by means of mammography. Radiologists look for certain signs and characteristics i... View full abstract»

• ### Remote bar-code localisation using mathematical morphology

Publication Year: 1999, Page(s):642 - 646 vol.2
Cited by:  Papers (6)  |  Patents (1)
| | PDF (364 KB)

Bar-code labels are used in industry to identify and classify a wide variety of products, tools and equipment, their reading generally being undertaken via a laser scanning system. In most cases the number, position and orientation of the bar-codes are well known. However, a particular application under consideration here involves the identification of radioactive material containers via their bar... View full abstract»

• ### Handwriting recognition using HMMs and a conservative level building algorithm

Publication Year: 1999, Page(s):736 - 739 vol.2
| | PDF (240 KB)

We describe a method for the recognition of cursively handwritten words using hidden Markov models (HMMs). The modelling methodology used has previously been successfully applied to the recognition of both degraded machine-printed text and hand-printed numerals. This paper addresses the additional problems that result from the greater degree of variability present in cursive script. The impact of ... View full abstract»

• ### A fast adaptive superresolution technique for image restoration

Publication Year: 1999, Page(s):827 - 831 vol.2
| | PDF (272 KB)

The authors propose a fast adaptive method of superresolution using a Wiener filter in conjunction with iteration for projection onto convex sets (POCS). The algorithm is robust and adaptive in noise reduction and has very fast convergence. Moreover the algorithm does not require knowledge of the point spread function (psf) of the imaging system View full abstract»

• ### A nonrigid-body approach to matching mammograms

Publication Year: 1999, Page(s):484 - 488 vol.2
Cited by:  Papers (3)
| | PDF (360 KB)

This paper has explored the use of a nonrigid-body approach to mammogram registration. Mammogram registration is inherently complicated by factors such as the inhomogeneous composition of the breasts and their nonrigid behavior. We have developed a technique which accounts for such nonrigid-body idiosyncrasies and allows corresponding mammograms to be registered for subsequent fusion. Future work ... View full abstract»

• ### Estimating dense motion fields using a local two-component model

Publication Year: 1999, Page(s):696 - 700 vol.2
Cited by:  Papers (1)
| | PDF (632 KB)

This paper describes a region based approach to computing dense estimates of 2-D motion fields in image sequences. By dense we mean that we would like to have an estimate of the motion at each pixel location at any point in the sequence. In comparison with alternatives, such as optical flow methods, region based approaches to this problem have a number of advantages. Since they involve correlating... View full abstract»

• ### A minimum classification error method for face recognition

Publication Year: 1999, Page(s):630 - 633 vol.2
| | PDF (216 KB)

In this paper, we propose a minimum classification error rate based face recognition system. In our work, the minimum classification error formulation is incorporated into a neural network classifier called a multilayer perceptron. Experimental results show that our system is robust to noisy images and complex background View full abstract»

• ### Treescan V. A second generation system for forestry pre-harvest inventory assessment of large plantation trees

Publication Year: 1999, Page(s):676 - 680 vol.2
Cited by:  Papers (1)
| | PDF (308 KB)

This paper describes the design and implementation of a specialised high aspect ratio, image capture and processing system developed for an industrial client. The process of technology transfer is also briefly discussed as an influence on the design. The system is designed to capture, store and process images of standing forest trees of up to 40 m in height and has a horizontal field of view of ab... View full abstract»

• ### Using tabu search for segmentation of cursive handwriting

Publication Year: 1999, Page(s):745 - 749 vol.2
| | PDF (264 KB)

The recognition of cursive handwriting remains a challenging an open problem, especially for the case of off-line recognition from a scanned image. The authors research on the recognition of handprinted characters has achieved some success as reported in Elliman et al. (1991). In attempting to recognise increasingly careless handprint it becomes necessary to segment touching characters, and to joi... View full abstract»

• ### Tongue tracking in medical X-ray sequences

Publication Year: 1999, Page(s):494 - 497 vol.2
| | PDF (348 KB)

This payer presents a system for the automated tracking of non-rigid anatomic structures in two-dimensional image sequences. It is applied to X-ray image sequences of the vocal tract. In this application articulatory organs have to be measured to investigate the complex dynamic characteristics of human speech production, with particular interest in the robust boundary detection of non-rigid organs... View full abstract»

• ### Automatic classification and recognition of shoeprints

Publication Year: 1999, Page(s):638 - 641 vol.2
Cited by:  Papers (11)
| | PDF (272 KB)

The most common clues left at a crime scene when a crime is committed are shoeprint impressions. These impressions are useful in the detection of criminals and the linking of crime scenes. We are currently working on a fully automatic system utilising novel fractal pattern matching techniques which allow the investigating officer(s) to match collected impressions against a database of known shoepr... View full abstract»

• ### Hierarchical image segmentation using a watershed scale-space tree

Publication Year: 1999, Page(s):522 - 526 vol.2
Cited by:  Papers (3)  |  Patents (4)
| | PDF (336 KB)

The watershed transformation is a useful morphological segmentation tool which has been used in a variety of grey-scale image processing applications. However, a major problem with the watershed transformation is that it produces a severe over-segmentation due to the great number of minima embedded in the image or its gradient, and therefore it is rarely applied directly to images. In this paper w... View full abstract»

• ### A novel multiple-expert approach to the recognition of handwritten words extracted from British cheques

Publication Year: 1999, Page(s):731 - 735 vol.2
Cited by:  Papers (1)
| | PDF (288 KB)

A novel multiple-expert approach to the recognition of handwritten words extracted from British cheques has been presented. It has been demonstrated that this multiple-expert technique has enhanced recognition accuracy than that of the component classifiers. In addition, it has also been demonstrated that this multiple-expert approach has higher throughput than that of the individual experts worki... View full abstract»

• ### A novel watermark embedding and detection scheme for images in DFT domain

Publication Year: 1999, Page(s):780 - 783 vol.2
Cited by:  Papers (8)
| | PDF (236 KB)

This paper presents a novel watermark embedding and detection scheme for copyright protection of images, in the discrete Fourier transform domain. A scheme for generating, embedding and a new concept of detecting the presence of a watermark is proposed. This facilitates the detection of a watermark without any need for the original image. Since the proposed scheme embeds watermarks independent of ... View full abstract»

• ### Computerized classification of breast lesions: shape and texture analysis using an artificial neural network

Publication Year: 1999, Page(s):517 - 521 vol.2
| | PDF (244 KB)

In this study we have investigated two groups of features: shape features, extracted from microcalcifications and texture features, extracted from the original regions of interest (ROI), in order to classify early breast cancers which have microcalcifications associated. These features were analyzed using different topologies of the artificial neural network (ANN) multi-layer perceptron (MLP). The... View full abstract»

• ### Smart CMOS camera for machine vision applications

Publication Year: 1999, Page(s):865 - 869 vol.2
Cited by:  Papers (4)
| | PDF (256 KB)

An edge detection algorithm designed for a custom CMOS hardware implementation is presented. The integration of this edge detector into an image sensing chip has been evaluated through SPICE analysis and measurements on fabricated devices. The performance of this edge detector has been quantified through image processing simulation View full abstract»

• ### A mathematical morphology approach to the extraction of nerve cell structures

Publication Year: 1999, Page(s):823 - 826 vol.2
Cited by:  Patents (2)
| | PDF (176 KB)

This paper presents a new approach to extract nerve cell structures using mathematical morphology tools. Particularly, the structures produced by the proposed method include soma and skeleton of neurons. The process is decomposed into three stages: first, a preprocessing step is implemented to invert the image; second, a separation step is performed to eliminate the dendrites; third, the skeleton ... View full abstract»