Distinction of Korean and English Characters Using Aspect Ratio and Structural Characteristics
Jeon Il Soo, Won Nam Sik, Lee Doo Han · The Transactions of the Korea Information Processing Society · 1999
This paper proposes an algorithm for distinguishing Korean and English characters which can be applied to multi-font by using of the ratio height to width of each character and the structural characteristics. The proposed algorithm distinguishes Korean and English characters as the aspect ratio, existing or not of stroke image on the left-upper area, and detection of a bar in an input image. The process of detecting bar is a sequence of left, upper, right, and lower. Experimental results yield 100.00% distinction rate for the Myungjo font, 99.96% for the Sinmyungjo font and the Kungseo font, and 99.77% for the Gothic font of Hanguel word processor.