# Third International Conference on Image Processing and its Applications, 1989.

## Filter Results

Displaying Results 1 - 25 of 143
• ### An intelligent system for automatic fire detection in forests

Publication Year: 1989, Page(s):563 - 570
Cited by:  Papers (8)
| | PDF (310 KB)

The use of smoke-analysis is described for fire detection by means of suitably placed standard TV cameras. The paper first gives the smoke detection technique and discusses a method to obtain a suitable description of the scene. Then the intelligent part of the system is described and the methods and heuristics to speed-up the decision process discussed. The sub-system devoted to the translation o... View full abstract»

• ### Quantitative evaluation on edge preservation in multiresolution images

Publication Year: 1989, Page(s):623 - 627
| | PDF (372 KB)

Multiresolution image processing and analysis has become popular in recent years. In this approach, image data are represented in a hierarchical manner. The original images are usually placed at the bottom level, Images with reduced resolutions are then generated at successively higher levels. In this paper, a quantitative comparison of five techniques for obtaining multiresolution images is prese... View full abstract»

• ### Optical character recognition using a new connectionist model

Publication Year: 1989, Page(s):63 - 67
Cited by:  Papers (3)
| | PDF (208 KB)

Describes the development of a system for recognising hand drawn capital letters, which is designed to be position, scale and rotation invariant. The object of the paper is to investigate the performance of a new unimodal form of connectionist model when coupled to a reprocessing stage. The new connectionist model is briefly derived and its error surface is shown to be unimodal View full abstract»

• ### Evaluation of edge detection algorithms

Publication Year: 1989, Page(s):618 - 622
Cited by:  Papers (1)
| | PDF (336 KB)

In the past two decades several algorithms have been developed to extract the contour of homogeneous regions within digital images. A lot of the attention is focused to edge detection, being a crucial part in most of the algorithms. The classical edge operators emphasize the high frequency components in the image and therefore act poorly in cases of moderate low SNR and/or low spatial resolution o... View full abstract»

• ### Pyramid vision applied to automatic inspection

Publication Year: 1989, Page(s):59 - 62
| | PDF (268 KB)

A processing structure that is variously called a pyramid, a quadtree, a recognition cone, or a processing cone has been proposed as a means of achieving a high degree of parallelism for tasks such as object recognition in machine vision. In its simplest form the pyramid consists of a base with pm by pn pixels, where typically p=2 or p=3. This is called a retinal memory' View full abstract»

• ### A multiresolution stereopsis algorithm based on the Gabor representation

Publication Year: 1989, Page(s):19 - 22
Cited by:  Papers (2)
| | PDF (268 KB)

A new approach to the stereopsis problem, based on the frequency domain has been described. It has been shown that a multiresolution coarse-fine' algorithm, based on a spatially localised frequency domain (Gabor) representation, can lead to unbiased depth estimates and is capable of being implemented in a fast algorithm, using a pyramidal image representation. The performance of the algorithm has... View full abstract»

• ### Arithmetic coding-an alternative VLC strategy for video coding

Publication Year: 1989, Page(s):613 - 617
| | PDF (292 KB)

Variable length coding (VLC), otherwise known as entropy coding, is often used to achieve maximum compression from a video codec. The technique attempts to exploit any residual correlation exhibited by the coded data following the application of a data compression algorithm. Traditional VLC techniques employing prefix (eg Huffman) coding are examined and the compression limit achievable with such ... View full abstract»

• ### Image presentations for spinal kinematic analysis using digital videofluoroscopy

Publication Year: 1989, Page(s):343 - 347
Cited by:  Patents (1)
| | PDF (344 KB)

The investigation of spinal mechanics in injuries and other painful conditions is frustrated by the difficulty of measuring the kinematics between individual segments. Problems associated with current methods of measurement include the radiation dosage required, the limited accuracy obtainable and the inherent labour-intensive nature of the numerical procedures. The authors have developed a techni... View full abstract»

• ### A knowledge structuring technique for efficient classification in multiple scene analysis

Publication Year: 1989, Page(s):93 - 97
| | PDF (244 KB)

The growing importance of automatic scene analysis is verified in many fields like robotics in factory automation, medical applications, monitoring and control, (environmental control is an important emerging discipline), and others. This considerable growth of interest has created an increasing need for both theoretical methods and experimental software and hardware. The processing steps for imag... View full abstract»

• ### An iterative elastic stretching technique applied to thermographic images

Publication Year: 1989, Page(s):324 - 328
Cited by:  Patents (2)
| | PDF (396 KB)

A new approach has been proposed for the automatic matching of two or more objects based on gradual and sequential deformation of an elastic image onto a target image. It is based on the belief that cooperative and gradual matching minimises mismatches due to ambiguous relationships between features. An efficient but simple nearest neighbour rule is used to supply sufficient information to correct... View full abstract»

• ### An unsharp sieve [image processing]

Publication Year: 1989, Page(s):679 - 681
| | PDF (108 KB)

In some image processing and computer vision applications, it is desirable to be able to extract objects of a certain width from an image. Sifting theory, which is based on operations from mathematical morphology provides a means to extract (sieve out') objects up to a certain prespecified width. More often than not, the exact width of the desired objects is not known in advance. In these cases, ... View full abstract»

• ### A new approach to curvature estimation and description

Publication Year: 1989, Page(s):54 - 58
| | PDF (284 KB)

A new method for detection and estimation of curvature is presented. The algorithm is implemented in the hierarchical feature pyramid proposed in the GOP concept. Curvature is handled at the second level of the pyramid with an orientation description of the image as input. This complex valued image is convolved and the filter responses are combined into a description of curvature direction, magnit... View full abstract»

• ### Three-dimensional range acquisition of line-like objects

Publication Year: 1989, Page(s):14 - 18
| | PDF (280 KB)

Presents a new technique for three-dimensional (3D) range acquisition of line-like objects. The objects are illuminated sequentially by three point light sources causing shadow lines on a working plane. These shadow lines are extracted from images of the scene by a robust image preprocessing procedure. Along the images of epipolar lines defined by the geometrical configuration of light sources, ca... View full abstract»

• ### Knowledge-based image processing system: IPSSENS-II

Publication Year: 1989, Page(s):462 - 466
Cited by:  Papers (2)  |  Patents (1)
| | PDF (372 KB)

The authors have developed an image processing support system, IPSSENS-II, which has knowledge-bases of image processing techniques. With the aid of the knowledge-bases, even the user without much experience can execute image processing easily. There are two types of knowledge built in the system: the knowledge independent of the contents of a given image; and the knowledge dependent on them. The ... View full abstract»

• ### A formal presentation of a few image processing boards

Publication Year: 1989, Page(s):526 - 530
| | PDF (244 KB)

Shows that an image processing board may be described formally in a manner which is suitable for design verification and documentation. The paper first presents the description of an image processing virtual board from which it then derives the specification of two industrial boards. The first one is the Matrox PIP-512; this is a single board for the IBM PC or plug-compatible computer. The second ... View full abstract»

• ### Sampling pattern conversion with 2-D FIR filters

Publication Year: 1989, Page(s):275 - 279
Cited by:  Papers (6)
| | PDF (252 KB)

The problem of conversion between different periodic sampling structures is of importance in a number of applications related to multidimensional signal processing. For instance in areas of image processing, as multiresolution representations or high definition television, one has to modify sampling structures. For these types of processing finite impulse response (FIR) digital filters offer two m... View full abstract»

• ### Parallel architecture for VLSI implementation of a 2-dimensional discrete cosine transform for image coding

Publication Year: 1989, Page(s):609 - 612
| | PDF (196 KB)

A new efficient parallel architecture is presented for high-speed two-dimensional discrete cosine transform (DCT) for image data compression with a block size of 8×8 picture elements. This circuit is applicable in advanced television and HDTV systems working at video sampling-rate up to 80 MHz and can be realized in CMOS technology as a single VLSI component View full abstract»

• ### Monocular computer vision

Publication Year: 1989, Page(s):107 - 111
| | PDF (252 KB)

The human visual system is usually able to recognize objects as well as their spatial relations without the support of depth information like stereo vision. For this reason one can easily understand cartoons, photographs and movies. It is the aim of the authors' current research to exploit this aspect of human perception in the context of computer vision. From a monocular TV image one obtains info... View full abstract»

• ### An investigation into the use of neural networks for an expert system in nuclear medicine image analysis

Publication Year: 1989, Page(s):338 - 342
Cited by:  Papers (1)
| | PDF (240 KB)

Describes exploratory work on the use of neural networks in building an expert system that will emulate the diagnostic skill of an experienced clinician in the area of nuclear medicine. The long term aim of the project is to produce an automatic reporting system which scans medical images, extracts relevant features, and gives a diagnostic output. Nuclear images contain a substantial amount of no... View full abstract»

• ### A knowledge based system for image understanding

Publication Year: 1989, Page(s):88 - 92
Cited by:  Papers (1)
| | PDF (504 KB)

Reports the development, using expert system technology, of a model for image understanding which takes as its input the basic transactions involved in image enhancement and image encodement, and generates as its output recommendations as to the best approach or set of processes to analyse an image. The paper examines the broad area of visual processing and utilises the study of human visual infor... View full abstract»

• ### Vector quantization based on visual masking functions for the DPCM and HDPCM coding of coloured pictures

Publication Year: 1989, Page(s):548 - 552
| | PDF (308 KB)

In DPCM (differential pulse code modulation) or HDPCM (hybrid DPCM) of coloured pictures consisting of three components, every component can be coded with three separate coders, each containing a scalar quantizer. However, more compression can be obtained with one vector quantizer instead of three scalar quantizers. In the article, the attention is focused on the placement of the output vectors in... View full abstract»

• ### The recovery of `Phonovision'

Publication Year: 1989, Page(s):300 - 304
| | PDF (324 KB)

Describes the procedures used in the enhancement and analysis of the earliest known recordings of television pictures. Information not previously available has been derived analytically from the features and defects of the Phonovision recordings. The specific areas that are now better understood are:- (i) the original image scanning process; (ii) the method of image recording; (iii) the apparatus ... View full abstract»

• ### The real-time performance of a universal thresholding algorithm for machine vision with nonstructured light

Publication Year: 1989, Page(s):498 - 500
| | PDF (172 KB)

The extraction of useful image data is achieved by a nonlinear thresholding technique which has been shown to yield useful practical results in a number of different applications through an ad-hoc experimental approach to the establishment of the appropriate thresholding algorithm. The paper illustrates the systematic establishment of the nonlinear algorithm and the resulting real-time performance... View full abstract»

• ### A simple method of segmentation with subpixel accuracy

Publication Year: 1989, Page(s):403 - 405
Cited by:  Patents (4)
| | PDF (216 KB)

In order to identify boundaries with subpixel accuracy it is necessary to construct a continuous or at least high resolution model of the intensity function I inferred from the discrete values of the digitized image. An approach described by Haralick (1984) is to fit a cubic polynomial to the discrete image data in the region under consideration. In the paper an alternative method is described in ... View full abstract»

• ### Quantification of retinal damage during cardiopulmonary bypass

Publication Year: 1989, Page(s):319 - 323
Cited by:  Patents (2)
| | PDF (512 KB)

Microembolic ischaemia in the retina, as revealed by fluorescein angiography, has been reported during cardiovascular bypass. Subsequent neurological and intellectual dysfunction have also been observed. Since the eye is an outgrowth of the brain it is possible to assume that similar microemboli occur in that organ. By comparison of pre- and end-bypass operation retinal images, an estimate of the ... View full abstract»