Offline grammar-based recognition of handwritten sentences

This paper proposes a sequential coupling of a Hidden Markov Model (HMM) recognizer for offline handwritten English sentences with a probabilistic bottom-up chart parser using Stochastic Context-Free Grammars (SCFG) extracted from a text corpus. Based on extensive experiments, we conclude that syntax analysis helps to improve recognition rates significantly.

Diffusion tensor imaging of two unrelated Chinese men with hereditary spastic paraplegia associated with thin corpus callosum

Hereditary spastic paraplegia (HSP) associated with thin corpus callosum is a rare autosomal recessive neurodegenerative disorder characterized by an abnormally thin corpus callosum, normal motor development, slowly progressive spastic paraparesis and cognitive deterioration. To investigate and localize abnormalities in the brains of two Chinese patients with HSP-TCC, with mutations in the spatacsin gene. Diffusion tensor imaging (DTI) was used to determine the mean diffusion (MD) and fractional anisotropy (FA) in the brains of the patients in comparison to 20 healthy subjects. Voxel-based analysis (VBA) of both the diffusion and anisotropy values were performed using statistical parametric mapping (SPM). Significant changes with MD increase and FA reduction were found in the already known lesions including the corpus callosum, cerebellum and thalamus. In addition, changes were also found in regions that appear to be normal in conventional MRI, such as the brain stem, internal capsule, cingulum and subcortical white matter including superior longitudinal fascicle and inferior longitudinal fascicle. Neither increase in FA nor reduction in MD was detected in the brain. Our study provides clear in vivo MR imaging evidence of a more widespread brain involvement of HSP-TCC. MD is more sensitive than FA in detecting lesions in thalamus and subcortical white matter, suggesting that MD may be a better marker of the disease progression.