SauvolaNet: Learning Adaptive Sauvola Network for Degraded Document Binarization

Deng Li, Yue Wu, Yicong Zhou

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 .