Dynamic and Contextual Information in HMM Modeling for Handwritten Word Recognition.

This study aims at building an efficient word recognition system resulting from the combination of three handwriting recognizers. The main component of this combined system is an HMM-based recognizer which considers dynamic and contextual information for a better modeling of writing units. For modeling the contextual units, a state-tying process based on decision tree clustering is introduced. Decision trees are built according to a set of expert-based questions on how characters are written. Questions are divided into global questions, yielding larger clusters, and precise questions, yielding smaller ones. Such clustering enables us to reduce the total number of models and Gaussians densities by 10. We then apply this modeling to the recognition of handwritten words. Experiments are conducted on three publicly available databases based on Latin or Arabic languages: Rimes, IAM, and OpenHart. The results obtained show that contextual information embedded with dynamic modeling significantly improves recognition.

Shear-induced permeation and fusion of lipid vesicles.

This paper introduces a novel approach to controlling membrane permeability in free unilamellar vesicles using shearing in the presence of a detergent with a large head-group to tune pore formation. Such shear-induced permeation could offer a simple means of postencapsulating bioactive molecules to prepare vesicle vectors for drug delivery. Using UV absorption, fluorescence emission, dynamic light scattering, and electron microscopy, we investigated the membrane permeability and the morphology of unilamellar lipid vesicles (diameter in the range 50-400 nm) subjected to a shear stress in the presence of a small amount of nonionic surfactant (Brij 76). Shear-induced leakage and fusion events were observed. We analyzed the significance of the vesicle size, the shear rate, and the surfactant-to-lipid ratio for the observed phenomena. The present approach is evaluated for postloading of preformed vesicles.

Raspberry vesicles.

We present a method to control the osmotic stress of giant unilamellar vesicles (GUV) and we report an original shrinkage mode of the vesicles: the volume reduction is accompanied by the formation of inverted daughter vesicles which gives the shrunk vesicles the appearance of raspberries. We analyze this peculiar shrinkage and we propose some physical origins for the observed phenomena.