METHOD AND SYSTEM FOR PRE-TREATING IMAGE FOR OPTICAL CHARACTER RECOGNITION

PROBLEM TO BE SOLVED: To provide a method and a system for pre-treating an image including a plurality of columns each of which includes Arabic character and/or non-character items for optical character recognition (OCR).SOLUTION: The method includes a step for determining a plurality of components associated with Arabic character and/or non-character items, and each of the components includes a group of connected pixels. When determining the plurality of components, a row height and a column interval are determined for the plurality of components. The plurality of components are associated with a certain column out of a plurality of columns based on the row height and the column interval. Then, a group of characteristic parameters is calculated in each column and the plurality of components in each column are combined based on the characteristic parameter group to form a sub-word and a word.