Alastair R. Allen

A similarity metric for edge images

The performance of several discrepancy measures for the comparison of edge images is analyzed and a novel similarity metric aimed at overcoming their problems is proposed. The algorithm finds an optimal matching of the pixels between the images and estimates the error produced by this matching. The resulting Pixel Correspondence Metric (PCM) can take into account edge strength as well as the displacement of edge pixel positions in the estimation of similarity. A series of experimental tests shows the new metric to be a robust and effective tool in the comparison of edge images when a small localization error of the detected edges is allowed.

Fish species recognition by shape analysis of images

Abstract Size and species grading of fish (e.g. on board a fishing boat) might in future be done entirely automatically using image analysis. This has been investigated by creating a data bank of shapes from photographs of seven different types of fish on a computer. Three methods of discriminating between the different species of fish are compared and these are: invariant moments, optimisation of the mismatch, and shape descriptors. Each approach was evaluated using discriminant analysis. The methods sorted the fish with a reliability of 73%, 63% and 90% respectively. Further work is required to make a commercial grading system feasible.

Using self-organising maps in the detection and recognition of road signs

Road sign recognition is a part of driver support systems. Its main aim is the increase of traffic safety by calling the drivers attention to the presence of key traffic signs. Additionally, a vision-based system able to detect and classify traffic signs from road images in real-time would also be useful as a support tool for guidance and navigation of intelligent vehicles. This paper proposes a new method for the detection and recognition of traffic signs using self-organising maps (SOM). This method first detects potential road signs by analysing the distribution of red pixels within the image, and then identifies these road signs from the distribution of dark pixels in their pictograms. Additionally, a novel hybrid system combining programmable hardware and artificial neural networks for embedded machine vision is introduced, and a prototype of this system is used in the implementation of the application. The experiments indicate a good performance of the new approach using SOM in both speed and classification accuracy.

An Image Quality Metric based on Corner, Edge and Symmetry Maps

Image quality metrics have been widely used in imaging systems to maintain and improve the quality of images being processed and transmitted. Due to the close relationship between image quality perception and the human visual system, the development of image quality metrics has been contributed to by both psychologists and computer scientists. In this paper, three novel image quality metrics are proposed by improving the well-known image quality metric structural similarity index (SSIM). In this new approach, images are not compared directly, but their feature maps are (preprocessing is incorporated to extract the corner, edge and symmetry maps). The similarity measured (by SSIM) between corner, edge and symmetry maps of images being compared is used as an indicator of image quality, and named C SSIM, E SSIM and S SSIM respectively. The experiments show that all the proposed image quality metrics have a better performance than SSIM, and E SSIM has the best performance among them.

A method for working out the moments of a polygon using an integration technique

Abstract Moments are used in image processing to describe the shape of objects, to evaluate their principal axes and centre of area. In this paper a new technique is described for calculating the moments of a shape represented by a polygon.

A pervasive design strategy for distributed health care systems

Distributed health care systems require a pervasive design strategy to ensure security, stability and functionality of the system. Furthermore, distributed health care systems are potentially very complex, which makes it necessary to have appropriate abstraction strategies. In this paper we introduce the theory of communicating sequential processes to distributed health care system design. We use this theory to gain further insight into the communication between different system components. In particular this reasoning is applied to the problem of internal and external integration of distributed health care systems. We claim that a high level of internal and external integration can be achieved with the pervasive design strategy. With the pervasive concept of communicating sequential processes we have a formal method to create a model of the complete system. In the practical part of the paper we apply the formal system model to prove security, stability and functionality of a particular system.

A hybrid system for embedded machine vision using FPGAs and neural networks

This paper presents a hybrid model for embedded machine vision combining programmable hardware for the image processing tasks and a digital hardware implementation of an artificial neural network for the pattern recognition and classification tasks. A number of possible architectural implementations are compared. A prototype development system of the hybrid model has been created, and hardware details and software tools are discussed. The applicability of the hybrid design is demonstrated with the development of a vision application: real-time detection and recognition of road signs.

An Image Quality Metric Based on a Colour Appearance Model

Image quality metrics have been widely used in imaging systems to maintain and improve the quality of images being processed and transmitted. Due to the close relationship between image quality and human visual perception, both computer scientists and psychologists have contributed to the development of image quality metrics. In this paper, a novel image quality metric using a colour appearance model is proposed. After the physical colour stimuli of the images being compared are transformed into perceptual colour appearance attributes, the distortion measures between the corresponding attributes are used to predict the subjective scores of image quality, by use of data-driven models: Multiple Linear Regression (MLR), General Regression Neural Network (GRNN) and Back-Propagation Neural Network (BPNN). Based on the data-driven model used, we have developed three image quality metrics, CAM_MLR, CAM_GRNN and CAM_BPNN. The experiments have shown that the performance of CAM_BPNN is better than the well-known image quality metric SSIM.

A single-chip supervised partial self-reconfigurable architecture for software defined radio

Software Defined Radio (SDR) technology seeks to solve the problem of multiple incompatible broadcast/telecom standards available in different locations, by having standard specific processing defined in software. This software is downloaded and run on generic hardware, so that different broadcast/telecom standards can be supported by downloading corresponding software modules. Computing platform based SDR attempts to bridge the worlds of computing and broadcast/telecoms, by exposing the features and resources of computers to SDR and vice versa. However, such a concept results in certain architectural issues that need to be resolved. This paper describes the concept of Computing Platform based SDR, and the resulting issues & desired features of such a system. An innovative system architecture that involves the supervised partial self-reconfiguration of a single FPGA is proposed and detailed. Finally, a system test is conducted to illustrate and verify the reconfiguration operation.

Improving routing performance of underwater wireless sensor networks

In this paper we present a 3D node deployment strategy to improve the routing performance of an Underwater Wireless Sensor Network (UWSN). This is done by carefully considering the unique characteristics of underwater acoustic communication as well as three-dimensional (3D) and dynamic nature of Underwater Wireless Sensor Networks (UWSNs). This strategy targets 3D UWSN and not only improves the routing protocol performance in terms of end to end delay and energy consumption but also provides reliability in data transmission and increases network lifetime. This strategy has been developed step by step from a single line of vertical communication to an effective 3D node deployment for UWSN. Several simulation experiments were carried out after adding different features to the final design, in order to observe their impact on the overall routing performance. Improving the routing performance by carefully analyzing the impact of 3D node deployment strategy and ensuring full sensing, transmission and back-up coverage in a highly unpredictable underwater environment, is a novel approach which can be embedded with other networking protocols to improve their performance.