Abstract-In order to represent large amounts of information in the form of a video key-frame summary, this paper studies narrative grammar of comics, and using its universal and intuitive rules, lays out visual summaries in an efficient and user centered way. The system ranks importance of key-frame sizes in the final layout by balancing the dominant visual representability and discovery of unanticipated content utilizing a specific cost function and an unsupervised robust spectral clustering technique. A final layout is created using an optimization algorithm based on dynamic programming. Algorithm efficiency and robustness are demonstrated by comparing the results with the optimal panelling solutions.

Placing external monitoring devices onto seabirds can have deleterious effects on welfare and performance, and even the most benign marking and identification methods return sparse population data at a huge time and effort cost. Consequently, there is growing interest in methods that minimise disturbance but still allow robust population monitoring. We have developed a computer vision system that automatically creates a unique biometric identifier for individual adult African penguins Spheniscus demersus using natural markings in the chest plumage and matches this against a population database. We tested this non-invasive system in the field at Robben Island, South Africa. False individual identifications of detected penguins occurred in less than 1 in 10 000 comparisons (n = 73 600, genuine acceptance rate = 96.7%) to known individuals. The monitoring capacity in the field was estimated to be above 13% of the birds that passed a camera (n = 1453). A significant increase in this lower bound was recorded under favourable conditions. We conclude that the system is suitable for population monitoring of this species: the demonstrated sensitivity is comparable to computer-aided animal biometric monitoring systems in the literature. A full deployment of the system would identify more penguins than is possible with a complete exploitation of the current levels of flipper banding at Robben Island. Our study illustrates the potential of fully-automated, non-invasive, complete population monitoring of wild animals.

Many image-database retr-ieual systems rely heavily on the success oj one-shot queries, using optimised jemkre set-s to obtain the best possible results.What is ojten missing jt-om this appToach is acceptance oj the fact that the user knows considerably mor-e about the query being made than cm. be conveyed in szch Relatively simple terms. Ij the query jails then the useT must try and improve the description using only the avai[able Jeatwe descriptors. This papeT describes how a query system can. exploit the user's lrnourledge to a higher extent by employing relevance jeedback to itemtively rejine queries at ran-time. Subjects oj inierest aTe chosen by selection oj i-egions jrom pre-processed, segment ed imag~, giving access to object-specific, local infor-mation which zs not possible in a global pattern-matching approach. AfteT an initial retrieved attempt, jeedback is given in the jmm oj acceptance or rejection oj imagtx ofemd. This information b used as a collection oj positive and negative training ezamples joT a class-speci$c classijkation network by identifying clusterings in the data and the spread along jeatuTe axes. Each. networ-k consists OJ a set of Radial BaSiSFunction nodes with a non-linear perception output layer. Network training is carried out of-line mung the data gathered o%ing an on-line query session with the user. The aseT can i-eview and adjust the behaviotw of the network in the next session.Over time, collections oj these networks can be built into a bier-a~chical ck.ss database, resulting into highly usefil Tetm"eval tooi specifically trained jor the nature oj the user's database.

No abstract

No abstract