Robert M. Hodgson

Texture measures for carpet wear assessment

Two standard approaches for texture analysis make use of numerical features of the second-order gray-level statistics, and on first-order statistics of gray-level differences, respectively. Feature sets of these types, all designed analogously, were used to analyze four sets of carpet samples exposed to different degrees of wear. It was found that some of the features extracted from the spatial gray-level-dependence matrix, neighboring gray-level-dependence matrix, gray-level difference method, and the gray-level run-length method allowed discrimination of degrees of wear in wool carpet. The methods developed could be of use in quality control. >

Properties, implementations and applications of rank filters

Abstract The results of research on rank filters are presented. The relationship of rank filters with other filters is briefly discussed. The main properties of rank filters are listed and an explanation is given for these properties. Several software and hardware implementations of the filter are described. Major applications to image processing are discussed, including noise smoothing, cluster detection, skeletization, edge enhancement and edge detection.

Carpet Texture Measurement Using Image Analysis

Image analysis techniques have been applied to the objective measurement of carpet texture. By converting an image into a form that highlights the regions of largest intensity variation, small differences in texture between carpets, due to either wear treatment or construction, can be reliably detected. This has been demonstrated using sets of samples that have received controlled wear treatments in the Hexapod tumbler tester. The optimum conditions for texture measurement are discussed, in particular the requirements for lighting and camera focusing. The influences of sample orientation and substrate color are also stressed. While the emphasis in this study is on plain shade carpets, possible methods of measuring the pile texture of colored pattern carpets are also discussed. Image analysis is considered to have a promising future as a scientific tool in studying carpet performance, as an objective means of carpet grading, and for product optimization and quality control in carpet manufacture.

Range filters: Localintensity subrange filters and their properties

Abstract A local filter which uses the local-intensity subrange of pixel intensity values within a window is described. The range filter is an extension of the rank filter and has been found useful for detecting edges. The deterministic and noise properties of the range filter are described and compared with those of the commonly used Sobel filter.

VIPS—a digital image processing algorithm development environment

Abstract The major requirements of an image processing algorithm development system are presented. VIPS, a Vax-based image processing system developed at the University of Canterbury, New Zealand, is described and discussed in terms of algorithm development. Some of the applications of VIPS are listed.

The Development of a Synthetic Colour Test Image for Subjective and Objective Quality Assessment of Digital Codecs

Subjective and objective quality measures are required for monitoring image and video systems. Our aim is to develop a static colour test image for digital codec and video system evaluation that is analogous to the colour bar signal commonly used in analogue television broadcasting. This approach is capable of highlighting coding colour artefacts, and enables both subjective and objective evaluation. The effectiveness of the developed test image is demonstrated using a JPEG codec. Three objective quality metrics are proposed of which two have been linked to the conventional vectorscope used in analogue television systems

Machine vision for automated optical recognition and classification of pollen grains or other singulated microscopic objects

The location and identification of singulated objects on microscope slides is a problem that is common to many applications, including recognition of pollen. In this paper, we describe a working system to solve this problem and demonstrate that it can be used to effectively locate pollen grains on slides, focus on them, photograph them, and then identify them based on a trained neural network. Our system aims to remove the need for laborious, time-consuming, and inaccurate counting of pollen grains by humans with a low-cost machine solution. It can deal with slides obtained using different preparation techniques and media. As well as describing the system, we present positive test results, including a comparision with human experts on the classification and counting of pollen on slides.

Initialising neural networks with a priori problem knowledge

In general problem knowledge can be used to formulate rules as an aid to finding solutions to specific problems. The rules need not be complete and may be contradictory in some details. This paper develops a number of schemes that map rules to the weights in a special network architecture (FuNN). These weights are used as the initial state for the training of the network. A mapping scheme is also given for a general MLP network. Results of our experiments show that with only a small set of rules, networks used to solve complex problems can converge more reliably and often to a better solution.

A System Design for a Multispectral Sensor Using Two-Dimensional Solid-State Imaging Arrays

The architecture of a system for the simultaneous capture of up to four images from solid-state two-dimensional image sensors is described. The system has been developed for remote sensing from light aircraft in the 400-1100-nm wavelength range. Software generation of sensor drive signals is incorporated in the system.

Educating a neural network for image processing

A preliminary series of experiments is reported in which a neural-network-based window filter was trained to perform complicated image processing tasks. It is shown that the analogy to training a human to perform a complex task is a useful one in developing a training strategy. In particular, four methods of improving learning were investigated. These are: pre-training on simpler but similar tasks, learning to perform useful sub-tasks, use of heuristic rules and structuring of training examples to make the required operation explicit.<<ETX>>