Correlation filter: an accurate approach to detect and locate low contrast character strings in complex table environment

Abstract

Correlation has been used extensively in object detection field. In this paper, two kinds of correlation filters, Minimum Average Correlation Energy (MACE) and Extended Maximum Average Correlation Height (EMACH), are applied as adaptive shift locators to detect and locate smudgy character strings in complex tabular color flight coupon images. These strings in irregular tabular coupon are computer-printed characters but of low contrast and could be shifted out of the table so that we cannot detect and locate them using traditional algorithms. In our experiment, strings are extracted in the preprocessing phase by removing background and then based on geometric information, two correlation filters are applied to locate expected fields. We compare results from two correlation filters and demonstrate that this algorithm is a high accurate approach.