BROKEN CHARACTER RESTORATION USING GRADIENT VECTOR FLOW AND BALLOON FORCE ALGORITHM
Qusay Omran Mosa, Mohammad Faidzul Nasrudin · 2015
The presence of a large number of broken characters in a digital document image represents the main problem in Optical Character Recognition (OCR) of historical documents. This problem still continues a challenge for recent OCR solutions. Broken character restoration from historical documents it is substantial because these documents contain important facts and leaving them leads to losing invaluable information. Gradient Vector Flow (GVF) snake has much more capture range than traditional snake therefore widely used in image segmentation. In this paper we used balloon with triangle steps to improve GVF snake to converge of deep concavity area and Restore broken characters using the improved GVF.