Few-Shot Pixel-Precise Document Layout Segmentation via Dynamic Instance Generation and Local Thresholding
Authors:
- 10 August 2023
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 33 (10) , 2350052
Abstract
Over the years, the humanities community has increasingly requested the creation of artificial intelligence frameworks to help the study of cultural heritage. Document Layout segmentation, which aims at identifying the different structural components of a document page, is a particularly interesting task connected to this trend, specifically when it comes to handwritten texts. While there are many effective approaches to this problem, they all rely on large amounts of data for the training of the underlying models, which is rarely possible in a real-world scenario, as the process of producing the ground truth segmentation task with the required precision to the pixel level is a very time-consuming task and often requires a certain degree of domain knowledge regarding the documents at hand. For this reason, in this paper, we propose an effective few-shot learning framework for document layout segmentation relying on two novel components, namely a dynamic instance generation and a segmentation refinement module. This approach is able of achieving performances comparable to the current state of the art on the popular Diva-HisDB dataset, while relying on just a fraction of the available data.Keywords
Funding Information
- Piano Nazionale di Ripresa e Resilienza (DD 3277 del 30 dicembre 2021)
This publication has 22 references indexed in Scilit:
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation2018
- Segmentation and clustering in brain MRI imagingReviews in the Neurosciences, 2018
- Texture feature benchmarking and evaluation for historical document image analysisInternational Journal on Document Analysis and Recognition (IJDAR), 2017
- Page segmentation using minimum homogeneity algorithm and adaptive mathematical morphologyInternational Journal on Document Analysis and Recognition (IJDAR), 2016
- Learning Texture Features for Enhancement and Segmentation of Historical Document Images2015
- Robust text and drawing segmentation algorithm for historical documents2013
- Document image characterization using a multiresolution analysis of the texture: application to old documentsInternational Journal on Document Analysis and Recognition (IJDAR), 2008
- User-driven page layout analysis of historical printed booksInternational Journal on Document Analysis and Recognition (IJDAR), 2007
- Document image analysis: A primerSādhanā, 2002
- Adaptive document image binarizationPattern Recognition, 2000