CT-Net: Cascade T-shape deep fusion networks for document binarization. (October 2021)

• Record Type: Journal Article
• Authors: He, Sheng; Schomaker, Lambert
• Is Part Of: Pattern recognition. Volume 118(2021)
• Publication Date: 2021-10
• Subjects: Cascade T-Net -- Binarization -- Enhancement -- DIBCO -- Convolutional neural networks; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108010
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We present a Cascade T-Shape Deep Networks framework for document image binarization. The T-Net is multi-task framework for document enhancement and binarization. Deep features learned by the enhancement are transferred to the binarization which can improve the performance of binarization. The Cascade T-Net is evaluated on nine public DIBCO datasets and achieves new state-of-the-art performance. Abstract: Document binarization is a key step in most document analysis tasks. However, historical-document images usually suffer from various degradations, making this a very challenging processing stage. The performance of document image binarization has improved dramatically in recent years by the use of Convolutional Neural Networks (CNNs). In this paper, a dual-task, T-shaped neural network is proposed that has the main task of binarization and an auxiliary task of image enhancement. The neural network for enhancement learns the degradations in document images and the specific CNN-kernel features can be adapted towards the binarization task in the training process. In addition, the enhancement image can be considered as an improved version of the input image, which can be fed into the network for fine-tuning, making it possible to design a chained-cascade network (CT-Net). Experimental results on document binarization competition datasets (DIBCO datasets) and MCS dataset show that our proposed method outperforms competing state-of-the-art methods in most cases.