Document image enhancement using adaptive directional lifting-based wavelet transform

Abstract

In this work, we proposed a new adaptive method for handwriting documents denoising, which differs from others in the two aspects: 1) The proposed method's process is an adaptive histogram equalization to suppress unwanted interfering strokes, and 2) It develops a clear document image by using adaptive directional lifting-based discrete wavelet transform enhancing operations for the foreground and interfering strokes, respectively. As a result, this method not only removes the interfering or visible watermarking in background information but also significantly increases the readability of each document.