• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.912-919
• /
• 2009

A novel algorithm using 2D tensor voting and edge-based approach is proposed for text detection in natural scene images. The tensor voting is used based on the fact that characters in a text line are usually close together on a smooth curve and therefore the tokens corresponding to centers of these characters have high curve saliency values. First, a suitable edge-based method is used to find all possible text regions. Since the false positive rate of text detection result generated from the edge-based method is high, 2D tensor voting is applied to remove false positives and find only text regions. The experimental results show that our method successfully detects text regions in many complex natural scene images.

• Journal of Korean Ophthalmic Optics Society
• /
• v.5 no.1
• /
• pp.173-180
• /
• 2000

To determine the effect of base curve and diameter of soft contact lenses on the fitting under the various corneal curvature, the model eyes which was made of either stainless steel or ordinary wood, were used as the substitutes for human eyes. The evaluations of fit of the soft contact lenses on both wood model eyes and human eyes were found to be very similar to each other. All the contact lenses except very thin ones became flat after fit on the stainless steel model eyes because the model eye could not preserve enough moisture to hold the edge of contact lenses on the steel ball's surface. The relationships between the base curves of contact lenses and radii of cornea for the optimum (normal) fit were measured as follows : corneal curvature (C.C)<7.6 mm : base curve(B.C) 8.4 mm, C.C 7.6~7.8 mm : B.C 8.4~8.5 mm. C.C 7.8~8.1 mm : B.C 8.6 mm. It is concluded that larger base curve is required for the eyes which have abnormal bulge on its cornea. It is found that very thin soft contact lenses can be easily twisted or folded regardless of moisture content when they were fit on the relatively dry eyes(corneas).