SauvolaNet: Learning Adaptive Sauvola Network for Degraded Document Binarization

TL;DR

SauvolaNet introduces an explainable, end-to-end trainable neural network that adapts classic Sauvola thresholding for degraded document binarization, achieving state-of-the-art results with minimal parameters.

Contribution

It proposes a novel neural network architecture with explainable modules that adapt classic thresholding for improved degraded document binarization.

Findings

Achieves state-of-the-art performance on 13 datasets.

Uses only 40K parameters, significantly fewer than comparable models.

Outperforms existing binarization solutions in extensive evaluations.

Abstract

Inspired by the classic Sauvola local image thresholding approach, we systematically study it from the deep neural network (DNN) perspective and propose a new solution called SauvolaNet for degraded document binarization (DDB). It is composed of three explainable modules, namely, Multi-Window Sauvola (MWS), Pixelwise Window Attention (PWA), and Adaptive Sauolva Threshold (AST). The MWS module honestly reflects the classic Sauvola but with trainable parameters and multi-window settings. The PWA module estimates the preferred window sizes for each pixel location. The AST module further consolidates the outputs from MWS and PWA and predicts the final adaptive threshold for each pixel location. As a result, SauvolaNet becomes end-to-end trainable and significantly reduces the number of required network parameters to 40K -- it is only 1\% of MobileNetV2. In the meantime, it achieves the State-of-The-Art (SoTA) performance for the DDB task -- SauvolaNet is at least comparable to, if not better than, SoTA binarization solutions in our extensive studies on the 13 public document binarization datasets. Our source code is available at https://github.com/Leedeng/SauvolaNet.