The identification of mammalian species through the classification of hair patterns using image pattern recognition

The identification of mammals through the use of their hair is important in the fields of forensics and ecology. The application of computer pattern recognition techniques to this process provides a means of reducing the subjectivity found in the process, as manual techniques rely on the interpretation of a human expert rather than quantitative measures. The first application of image pattern recognition techniques to the classification of African mammalian species using hair patterns is presented. This application uses a 2D Gabor filter-bank and motivates the use of moments to classify hair scale patterns. Application of a 2D Gabor filter-bank to hair scale processing provides results of 52% accuracy when using a filter bank of size four and 72% accuracy when using a filter-bank of size eight. These initial results indicate that 2D Gabor filters produce information that may be successfully

Zebra fingerprints : towards a computer-aided identification system for individual zebra

Information regarding wildlife behavioural patterns provides researchers with clearer understanding of species. Social interactions, breeding habits, feeding and migration trends are key factors influencing decisions in game management and ecological impact assessment. In order to obtain such information researchers must be able to track individual animals over a period of time. One of the commonest methods of identifying individual animals is to tag them with radio, satellite, or GPS transmitters (Mech & Barber, 2002). While these systems are very effective, they are often costly and can be traumatic for tagged animals.

Building the second generation of parallel/distributed virtual reality systems

We present the RhoVeR (Rhodes Virtual Reality) system and classify it as a second generation parallel/distributed virtual reality (DVR) system. We discuss the components of the system and thereby demonstrate its support for virtual reality application development, its configurable, parallel and distributed nature, and its synthesis of first generation DVR techniques.

CESE 2011 - abstracts book : the fourth annual conference on the Challenges in Environmental Science and Engineering

Abstract Book of the Conference on the Challenges in Environmental Science and Engineering - CESE 2011, 25th - 30th Sept., Tainan City, Taiwan

Blogs bother me : social media, journalism and the curriculum

This paper grew out of the authors’ interest in updating the journalism curriculum at AUT (Aukland University of Technology) to better reflect the impact of online media, including social media, on the work of journalists. The challenge for journalism educators is to remain relevant in rapidly changing news and education environments. Our study suggests that while the vast majority of students have some engagement with social media, particularly social networking, and are aware that it can be a powerful tool for journalists, they are still not entirely comfortable with its techniques and they are not experimenting with social media as a production platform as much as we first thought. In short, it appears that they do not have command of professional fluency with social media tools. In response to these findings we have begun to introduce some social media tools and processes directly into the units we teach, in particular: digital story-telling techniques; the use of Twitter and location-based applications; encouraging the ethical use of Facebook etc. for sourcing stories and talent for interviews; podcasting, soundslides and video for the Web, Dreamweaver, InDesign and PHP-based content management systems. We do not see the work to date as the end-point of the changes that we know are necessary, but we are acutely aware of the limitations (structural, institutional and financial) that suggest we should continue with this small-steps approach for the foreseeable future.