A selectional auto-encoder approach for document image binarization

PATTERN RECOGNITION

卷:86

Article

Calvo-Zaragoza, Jorge^1,2  Gallego, Antonio-Javier³ 

[1] McGill Univ, Schulich Sch Mus, 555 Sherbrooke St W, Montreal, PQ H3A 1E3, Canada

[2] Univ Politecn Valencia, PRHLT Res Ctr, E-46022 Valencia, Spain

[3] Univ Alicante, Dept Software & Comp Syst, Carretera San Vicente Raspeig S-N, Alicante 03690, Spain

关键词: Binarization;    Document analysis;    Auto-encoders;    Convolutional Neural Networks;   

DOI  :  10.1016/j.patcog.2018.08.011

来源: Elsevier

【 摘 要 】

Binarization plays a key role in the automatic information retrieval from document images. This process is usually performed in the first stages of document analysis systems, and serves as a basis for subsequent steps. Hence it has to be robust in order to allow the full analysis workflow to be successful. Several methods for document image binarization have been proposed so far, most of which are based on hand-crafted image processing strategies. Recently, Convolutional Neural Networks have shown an amazing performance in many disparate duties related to computer vision. In this paper we discuss the use of convolutional auto-encoders devoted to learning an end-to-end map from an input image to its selectional output, in which activations indicate the likelihood of pixels to be either foreground or background. Once trained, documents can therefore be binarized by parsing them through the model and applying a global threshold. This approach has proven to outperform existing binarization strategies in a number of document types. (C) 2018 Elsevier Ltd. All rights reserved.

【 授权许可】

Free