dhSegment: A generic deep-learning approach for document segmentation

04/27/2018
by   Sofia Ares Oliveira, et al.
0

In recent years there have been multiple successful attempts tackling document processing problems separately by designing task specific hand-tuned strategies. We argue that the diversity of historical document processing tasks prohibits to solve them one at a time and shows a need for designing generic approaches in order to handle the variability of historical series. In this paper, we address multiple tasks simultaneously such as page extraction, baseline extraction, layout analysis or multiple typologies of illustrations and photograph extraction. We propose an open-source implementation of a CNN-based pixel-wise predictor coupled with task dependent post-processing blocks. We show that a single CNN-architecture can be used across tasks with competitive results. Moreover most of the task-specific post-precessing steps can be decomposed in a small number of simple and standard reusable operations, adding to the flexibility of our approach.

READ FULL TEXT

page 2

page 4

page 5

page 6

research
04/05/2017

Convolutional Neural Networks for Page Segmentation of Historical Document Images

This paper presents a Convolutional Neural Network (CNN) based page segm...
research
10/22/2018

Baseline Detection in Historical Documents using Convolutional U-Nets

Baseline detection is still a challenging task for heterogeneous collect...
research
09/05/2017

PageNet: Page Boundary Extraction in Historical Handwritten Documents

When digitizing a document into an image, it is common to include a surr...
research
09/02/2023

A Post-Processing Based Bengali Document Layout Analysis with YOLOV8

This paper focuses on enhancing Bengali Document Layout Analysis (DLA) u...
research
11/12/2022

Variational Augmentation for Enhancing Historical Document Image Binarization

Historical Document Image Binarization is a well-known segmentation prob...
research
12/15/2020

docExtractor: An off-the-shelf historical document element extraction

We present docExtractor, a generic approach for extracting visual elemen...
research
01/24/2022

Importance of Textlines in Historical Document Classification

This paper describes a system prepared at Brno University of Technology ...

Please sign up or login with your details

Forgot password? Click here to reset