Object categorisation is a research area with significant challenges, especially in conditions with bad lighting, occlusions, different poses and similar objects. This makes systems that rely on precise information unable to perform efficiently, like a robotic arm that needs to know which objects it can reach. We propose a biologically inspired object detection and categorisation framework that...

The modern environment of mobile, pervasive, evolving services presents a great challenge to traditional solutions for enabling interoperability. Automated solutions appear to be the only way to achieve interoperability with the needed level of flexibility and scalability. While necessary, the techniques used to determine compatibility, as a precursor to interaction, come at a substantial compu...

In this paper we investigate different uses of semantics in text categorisation tasks. At this end, we consider distinct representations of documents which differ in the kind of information incorporated: a) information about terms only, b) semantic information (terms sense) and c) a combination of both types of information. Moreover, we study how the vocabulary size reduction affects this task....

Address all correspondence to: ××××............................, Greece Received 21-09-05, Revised 20-10-05, Accepted 27-10-05 This issue hosts an article that discusses the application of Data mining techniques to the treatment of infertile men with azoospermia, and compares this procedure of categorisation into groups with the corresponding clinical categorisation. Although the dataset used w...

This research aims to create an MECE (Mutually Exclusive, Collectively Exhaustive) categorisation method for typing errors. The research is grounded in theory by gathering typing error types found in both HCI and psychology literature. Empirical studies gathering typing errors from children are used to validate these error types. It is hoped that at a later date, this categorisation method can ...

In a pioneering set of experiments, Rosch investigated the colour processing of a remote traditional culture. It was concluded that colours form universally natural and salient categories. However, our own cross-cultural research, backed up by neuropsychological data and interference studies, indicates that perceptual categories are derived from the words in the speaker's language. The new data...

This study tests whether Australian English (AusE) and European Spanish (ES) listeners differ in their categorisation discrimination of Brazilian Portuguese (BP) vowels. In particular, we investigate two theoretically relevant measures vowel category overlap (acoustic vs. perceptual categorisation) as predictors non-native difficulty. We also the individual listener’s own native productions pre...

Adults appear to be more sensitive to configural information, including second-order relations (the spacing of features), in faces than in other objects. Superior processing of second-order relations in faces may arise from our experience of identifying faces at the individual level of categorisation (eg Bob versus John) but other objects at the basic level of categorisation (eg table versus ch...

In this paper we describe the application of analogical structure matching techniques to the domain of Geographic Information Systems (GIS). Automatic categorisation of map data into roads, buildings etc. is currently based on isolated objects. We describe how identifying analogous clusters of objects can categorise ambiguous polygons by introducing context into the categorisation process. We d...

Vision provides us with an ever-changing neural representation of the world from which we must extract stable object categorisations. We argue that visual analysis involves a fundamental interaction between the observer's top-down categorisation goals and the incoming stimulation. Specifically, we discuss the information available for categorisation from an analysis of different spatial scales ...