A Bottom Up Procedure for Text Line Segmentation of Latin Script

TL;DR

This paper introduces a bottom-up method for segmenting Latin script text lines using image morphology, feature extraction, and Gaussian mixture models, demonstrating its effectiveness through experimental validation.

Contribution

The paper presents a novel bottom-up segmentation approach combining morphology, features, and GMMs for Latin script text lines.

Findings

Method effectively segments Latin script text lines

Experimental results validate the approach

Combines morphology, feature extraction, and GMMs

Abstract

In this paper we present a bottom up procedure for segmentation of text lines written or printed in the Latin script. The proposed method uses a combination of image morphology, feature extraction and Gaussian mixture model to perform this task. The experimental results show the validity of the procedure.