Skoči na glavni sadržaj

Journal of computing and information technology, Vol. 1 No. 3, 1993.

Izvorni znanstveni članak

Curvature Based Analysis of Handwritten Symbols

Kim Man Lui ; Department of Computer Science, University of the Witwatersrand, Johannesburg, South Africa
Anton D. Brink ; Department of Computational and Applied Mathematics, University of the Witwatersrand Johannesburg, South Africa
Michael Sears ; Department of Computational and Applied Mathematics, University of the Witwatersrand Johannesburg, South Africa

Puni tekst: engleski pdf 4.397 Kb

str. 173-182

preuzimanja: 224

citiraj

Sažetak

Pattern recognition is an important branch of computer vision and intelligent robotics. This paper explores local curve theory for different pattern recognition applications: recognition of good handwritten symbols (Fig 1 ), analysis of the hierarchical structure of 2-D patterns and simple 3-D object recognition. In the case of 2-D patterns, our technique is compared with a recent related method based on generalized Hough transforms and it is found that it is more robust with respect to complex image outlines.

Ključne riječi

computer vision; pattern recognition

Hrčak ID:

150497

URI

https://hrcak.srce.hr/150497

Datum izdavanja:

30.9.1993.

Posjeta: 729 *