Deep features based convolutional neural network model for text and non-text region segmentation from document images

Article Type

Research Article

Publication Title

Applied Soft Computing

Abstract

A deep convolutional neural network model is presented here which uses deep learning features for text and non-text region segmentation from document images. The key objective is to extract text regions from the complex layout document images without any prior knowledge of segmentation. In a real-world scenario, a document or magazine images contain various text information along with non-text regions such as symbols, logos, pictures, and graphics. Extraction of text regions from non-text regions is challenging. To mitigate these issues, an efficient and robust segmentation technique has been proposed in this paper. The implementation of the proposed model is divided into three phases: (a) a method for pre-processing of document images using different patch sizes is employed to handle the situations for variants of text fonts and sizes in mage; (b) a deep convolutional neural network model is proposed to predict the text or non-text or ambiguous region within the image; (c) a method for post-processing of document image is proposed to handle the situation where the image has complex ambiguous regions by utilizing the recursive partitioning of those regions into their proper classes (i.e. text or non-text) and then the system accumulates the responses of those predictive patches with varying resolutions for handling the situation of text fonts variations within the image. Extensive computer simulations have been conducted using a collection of complex layout magazine images from Google sites and the ICDAR 2015 database. Results are collected and compared with state-of-the-art methods. It reveals that the proposed model is robust and more effective as compared to state-of-the-art methods.

DOI

10.1016/j.asoc.2021.107917

Publication Date

12-1-2021

Comments

Open Access, Green

This document is currently not available here.

Share

COinS