No abstract

No abstract

This paper proposes a new character recognition method using multiple subspace for each category. The method is essentially the CLAFIC method. Five subspaces for each category are spanned by vector series expansions constructed from five feature vectors extracted from character patterns separately. The features used are proposed for the preclassification. The decision procedure of this method is as follows. The feature vectors are extracted from an input character pattern. The projections of those feature vectors on corresponding feature subspaces are computed and five projection lengths are obtained for each category. Fivedimensional vectors whose elements are the above projection lengths are defined for each category. The decision rule is to classify the input pattern into the category on whose fivedimensional vector it has the largest Euclidean norm. The discrimination ability for similar KANJI characters of this method is examined through a discrimination experiment using handprinted KANJI character a k a base ETL-9(B).

Abstract:We have evaluated rat glomerular microcirculation under in-vivo condition with an intravital videomicroscope. To measure erythrocyte velocities, a line segment was set along the glomerular capillaries in time-sequential videotaped images and then a spatiotemporal image was constructed along that segment. The angle of striped pattern in the spatio-temporal image which reflects the erythrocyte velocity, was estimated to compute erythrocyte velocity vector mapping. We found that erythrocyte velocities in rat glomeruli were significantly faster in diabetic rats than in control rats (p <0.05). In conclusion, we have succeeded in quantitatively evaluating the in-vivo renal microcirculation with our videomicroscope system and by spatiotemporal image analyzing method.

No abstract