On-line learning of mutually orthogonal subspaces for face recognition by image sets.

We address the problem of face recognition by matching image sets. Each set of face images is represented by a subspace (or linear manifold) and recognition is carried out by subspace-to-subspace matching. In this paper, 1) a new discriminative method that maximises orthogonality between subspaces is proposed. The method improves the discrimination power of the subspace angle based face recognition method by maximizing the angles between different classes. 2) We propose a method for on-line updating the discriminative subspaces as a mechanism for continuously improving recognition accuracy. 3) A further enhancement called locally orthogonal subspace method is presented to maximise the orthogonality between competing classes. Experiments using 700 face image sets have shown that the proposed method outperforms relevant prior art and effectively boosts its accuracy by online learning. It is shown that the method for online learning delivers the same solution as the batch computation at far lower computational cost and the locally orthogonal method exhibits improved accuracy. We also demonstrate the merit of the proposed face recognition method on portal scenarios of multiple biometric grand challenge.

ON-LINE STEREO PROCESSING FOR THE SEM.

A convenient system for the rapid extraction of three dimensional information from pairs of SEM images has been constructed, eliminating the need for time-consuming photography. Results are produced in a digestable form. Distortions inherent in the SEM record display and in the photographic system are not relevant to the system described; only those arising within the column and stage need be considered.

Studies on the chemical control of psychrophilic bacterial spoilage of fish. 2 - The effect of antibiotics on the growth of psycrophilic bacteria isolated from marine fish

Among the various antibiotics tried, tetracyclines particularly chlorotetracycline (CTC), chloramphenicol and chlorostrep were found to be fairly effective at 8 and 10 p.p.m. levels. The order of sensitivity to CTC among the six genera studied was found to be Achromobacter

Studies on the chemical control of psychrophilic bacterial spoilage of fish. 4 - The effect of chemical preservatives on the growth of psychrophilic bacteria isolated from marine fish

Dehydroacetic acid and ammonia were found to be very effective in checking the growth of all the cultures at all concentrations tried. The two nitrofuran derivatives namely, semicarbazone and AF-2 were fairly effective, semicarbazone being more effective than AF-2. Sodium nitrite was found to be totally ineffective against the cultures at all concentrations tried.

Results of drift card experiments and considerations on the movement of milkfish eggs and larvae in the northern Sulu Sea

For a period of one year beginning December 1977, drift card experiments were conducted off the western and southern coasts of Panay Island to determine the surface currents in the area. Of a total 2,384 drift cards released during the study, 382 (16.02%) were recovered, 92% of them within 30 days following dispatch. The surface currents in the study area are strongly influenced, in direction and speed, by the prevailing monsoon winds. During the NE monsoon period, the surface currents move away from the coast; during the SW monsoon, toward and/or parallel to the coast. Based on the results, the probable movement and transport of milkfish (Chanos chanos) eggs and larvae from the spawning ground to the fry collection ground are also discussed.

On-line policy optimisation of spoken dialogue systems via live interaction with human subjects

Statistical dialogue models have required a large number of dialogues to optimise the dialogue policy, relying on the use of a simulated user. This results in a mismatch between training and live conditions, and significant development costs for the simulator thereby mitigating many of the claimed benefits of such models. Recent work on Gaussian process reinforcement learning, has shown that learning can be substantially accelerated. This paper reports on an experiment to learn a policy for a real-world task directly from human interaction using rewards provided by users. It shows that a usable policy can be learnt in just a few hundred dialogues without needing a user simulator and, using a learning strategy that reduces the risk of taking bad actions. The paper also investigates adaptation behaviour when the system continues learning for several thousand dialogues and highlights the need for robustness to noisy rewards. © 2011 IEEE.