Skip to main content

automatic image annotation

Bouyerbou, H.Oukid, S.Benblidia, N. and Bechkoum, K. (2012) Hybrid image representation methods for automatic image annotation: a survey. Seminar Presentation presented to: International Conference on Signals and Electronic Systems (ICSES 2012), Wroclaw, Poland, 18-21 September 2012.

Abstract:

In most automatic image annotation systems, images are represented with low level features using either global methods or local methods. In global methods, the entire image is used as a unit. Local methods divide images into blocks where fixed-size sub-image blocks are adopted as sub-units; or into regions by using segmented regions as sub-units in  images. In contrast to typical automatic image annotation methods that use either global or local features exclusively, several recent methods have considered incorporating the two kinds of information, and believe that the combination of the two levels of features is beneficial in annotating images. In this paper, we  provide a survey on automatic image annotation techniques according to one aspect: feature extraction, and, in order to complement existing surveys in literature, we focus on the emerging image annotation methods:  hybrid methods that combine both global and local features for image representation.




Full paper can be found at: http://nectar.northampton.ac.uk/4440/1/Bouyerbou20124440.pdf



Popular posts from this blog

Experiments in teaching Neural Networks

Excel Based







Scratch-based
More details available at https://computingnorthampton.blogspot.co.uk/2016/11/miniproject-using-scratch-to-build-and.html including links to the code.


All views and opinions are the author's and do not necessarily reflected those of any organisation they are associated with. Twitter: @scottturneruon

Social Analysis of Publications

The Computing staff's network of co-authors, at the University of Northampton, based on the University's  research repository NECTAR - http://nectar.northampton.ac.uk/view/divisions/SSTCT.html on 12th November 2016. The data goes back to 2010.




The data was analysed using the software VOSviewer - http://www.vosviewer.com/ free software for visualising networks. Differences in colours represents, the clusters of publications with those authors picked out by the software. The relative size of the circles is the relative number of publications listed; so for the two biggest circles/hubs it relates to 55 and 34 publications in this time period. Some relatively new authors, to the University but not to research, explains some of the 'islands' and the number of publications within it - it only reflects publications whilst at the University of Northampton.

To dig a little deeper, going to  look at the two biggest 'hubs' through their NECTAR records, so potentially going …

Computer lecturer’s research helps improve the next generation of technology

Taken from: http://www.northampton.ac.uk/news/computer-lecturers-research-helps-improve-the-next-generation-of-technology/ A computing lecturer at the University of Northampton, who is researching into how the efficiency of our everyday devices, such as mobile phones, can be improved, has been awarded the best paper at two recent conferences. Dr Michael Opoku Agyeman has written several journal papers focusing on how the next generation of technology can meet the ever increasing demands from consumers. He was invited to present his work at the 19th Euromicro Conference on Digital System Design in Cyprus and the Institute of Electrical and Electronics Engineers’ 14th International Conference in Paris. Part of his research concentrates on whether several processing elements can be incorporated on a single chip, known as System-On-Chip, to improve the efficiency and speed of the computing systems that we use every day, from mobile phones to video-game consoles and even medical equipment…