|
|||||||
|
On-line
Structural Approach for Recognizing Hand-Written Indian
Numbers
Ibrahiem
M. M. El Emary
and Mustafa M. Hammad
Faculty of Engineering, Amman
Al Ahlyia University, Amman , Jordan
Abstract:
In this paper, a structural pattern
recognition approach is proposed to identify on-line
handwritten Indian numbers. The proposed technique
depends on the direction between the current pixel and
the next new pixel that drawn by the user. Then, use
this directions sequence to extract the shape’s
primitives. Matching process uses the predefined models
of sorted primitives for each digit to identify it.
Experimental results show that
the recognition rate is 94.87% for the
drawn shapes. When the rejected cases are excluded from
the calculation, the rate can be increased to 98.07%.
Keywords:
Structural
pattern recognition; Primitives extractions; On-line
handwritten Indian numbers.
Biography:
BibTex: @ARTICLE{P1150527004,
AUTHOR = {Ibrahiem
M. M. El Emary and Mustafa M. Hammad},
TITLE = {On-line Structural Approach for Recognizing Hand-Written Indian Numbers}, JOURNAL = {ICGST International Journal on Graphics, Vision and Image Processing}, YEAR = {2005}, MONTH = {July}, VOLUME = {05}, ISSUE = {7}, PAGES={21--26} }
( |
|||||||
|
|