This paper describes a method for extracting interest points in images and using interrelated groups or cliques to recognize structure common to pairs of images. Feature measurements are commonly selected intuitively and work well on data that are thoroughly understood. This approach avoids the use of global features and relies upon candidate interest points and their relationships with each other. The method is applied to photos of movies posters and the results are compared with those achieved with SIFT key points.

Motion detection and estimation are known to be important in many automated surveillance systems. It has drawn significant research interest in the field of computer vision. This paper proposes a novel approach to motion detection and estimation based on visual attention. The method uses two different thresholding techniques and comparisons are made with black's motion estimation technique [1] based on the measure of overall derived tracking angle. The method is illustrated on various video data on and results show that the new method can extract motion information.

Eye tracking presents an adaptive approach that can capture the user's current needs and tailor the retrieval accordingly. Applying eye tracking to image retrieval requires that new strategies be devised that can use visual and algorithmic data to obtain natural and rapid retrieval of images. Recent work showed that the eye is faster than the mouse as a source of visual input in a target image identification task [Oyekoya and Stentiford 2005]. We explore the viability of using the eye to drive an image retrieval interface. In a visual search task, users are asked to find a target image in a database and the number of steps to the target image are counted. It is reasonable to believe that users will look at the objects in which they are interested during a search [Oyekoya and Stentiford 2004] and this provides the machine with the necessary information to retrieve a succession of plausible candidate images for the user.

Whilst the physical mechanism used by the eye to accommodate has been known since the mid 19th century, there have been few suggestions as to the method by which the human visual system controls the ciliary muscles. This paper proposes and explores an even function which, by building upon existing models of visual attention, could be used to model the eye's focusing mechanism. Specifically, by performing a two dimensional summation of the saliency score for each pixel in the image, it is possible to give the image an overall score. Focus can then be changed to maximise this score. It is anticipated that such an approach could be used to perform other parameter optimisation in image acquisition applications.

Perspective is a fundamental structure that is found to some extent in most images that reflect 3D structure. It is thought to be an important factor in the human visual system for obtaining understanding and extracting semantics from visual material. This paper describes a method of detecting vanishing points in images that does not require prior assumptions about the image being analysed. It enables 3D information to be inferred from 2D images. The approach is derived from earlier work on visual attention that identifies salient regions and translational symmetries.

Symmetry is a fundamental structure that is found to some extent in all images. It is thought to be an important factor in the human visual system for obtaining understanding and extracting semantics from visual material. This paper describes a method of detecting axes of reflective symmetry in images that does not require prior assumptions about the image being analysed. The approach is derived from earlier work on visual attention that identifies salient regions and translational symmetries. Some results are reported on natural colour images taken from the Corel database.

Most higher animals in the world have an ability to sense danger by spotting anomalies in their environment and surviving by taking appropriate evasive action. Those organisms that have the benefit of vision are able to direct attention rapidly towards the unusual without any prior knowledge of the environment. Existing models of visual attention have provided plausible explanations for many of the standard percepts and illusions and yet all have defied implementations that have led to generic applications. This paper describes an evolutionary programming approach to derive a measure of visual attention that may be used to identify regions of interest in many categories of images. A population of individuals, or pixel neighbourhoods, is evolved that performs best at discriminating between salient and non-salient image features. A number of results are provided.

A three-layer two-dimensional connectionist network is described. The network is structured in such a way that the trained net can be extended in both dimensions without losing its existing knowledge. Noncontributing or low-contributing units can be identified and pruned from the net to improve efficiency. These features enable the size of the net to be tailored to a particular task without the need for time-consuming retraining from scratch. A net of this type has been applied to the task of speaker-independent isolated-word speech recognition, with a vocabulary consisting of the digits 'zero' to 'nine' plus silence.>

An automatic evolutionary search is applied to the problem of feature extraction in an OCR application. A performance measure based on feature independence is used to generate features which do not appear to suffer from peaking effects [17]. Features are extracted from a training set of 30 600 machine printed 34 class alphanumeric characters derived from British mail. Classification results on the training set and a test set of 10 200 characters are reported for an increasing number of features. A 1.01 percent forced decision error rate is obtained on the test data using 316 features. The hardware implementation should be cheap and fast to operate. The performance compares favorably with current low cost OCR page readers.

A standard thinning algorithm which consists of a matrix matching scheme used in conjunction with a connectivity measure is briefly described. Several new heuristics are introduced to obviate some of the common shortcomings of thinning algorithms when applied to handprinted data.