GDB: Gated convolutions-based Document Binarization
Document binarization is a key pre-processing step for many document analysis tasks. However, existing methods can not extract stroke edges finely, mainly due to the fair-treatment nature of vanilla convolutions and the extraction of stroke edges without adequate supervision by boundary-related information. In this paper, we formulate text extraction as the learning of gating values and propose an end-to-end gated convolutions-based network (GDB) to solve the problem of imprecise stroke edge extraction. The gated convolutions are applied to selectively extract the features of strokes with different attention. Our proposed framework consists of two stages. Firstly, a coarse sub-network with an extra edge branch is trained to get more precise feature maps by feeding a priori mask and edge. Secondly, a refinement sub-network is cascaded to refine the output of the first stage by gated convolutions based on the sharp edge. For global information, GDB also contains a multi-scale operation to combine local and global features. We conduct comprehensive experiments on ten Document Image Binarization Contest (DIBCO) datasets from 2009 to 2019. Experimental results show that our proposed methods outperform the state-of-the-art methods in terms of all metrics on average and achieve top ranking on six benchmark datasets.
Code (1)
Tasks
BinarizationImage EnhancementSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Automatic Document Image Binarization using Bayesian Optimization
Document image binarization is often a challenging task due to various forms of degradation. Although there exist several binarization techniques in literature, the binarized image is typically sensitive to control param…
Bayesian OptimizationBinarizationBinarizing Documents by Leveraging both Space and Frequency
Document Image Binarization is a well-known problem in Document Analysis and Computer Vision, although it is far from being solved. One of the main challenges of this task is that documents generally exhibit degradations…
BinarizationTwo-stage generative adversarial networks for document image binarization with color noise and background removal
Document image enhancement and binarization methods are often used to improve the accuracy and efficiency of document image analysis tasks such as text recognition. Traditional non-machine-learning methods are constructe…
BinarizationDecoderImage EnhancementA Fair Evaluation of Various Deep Learning-Based Document Image Binarization Approaches
Binarization of document images is an important pre-processing step in the field of document analysis. Traditional image binarization techniques usually rely on histograms or local statistics to identify a valid threshol…
BinarizationDeep LearningvalidSEP-Nets: Small and Effective Pattern Networks
While going deeper has been witnessed to improve the performance of convolutional neural networks (CNN), going smaller for CNN has received increasing attention recently due to its attractiveness for mobile/embedded appl…
BinarizationQuantization