A Bottom Up Procedure for Text Line Segmentation of Latin Script

10/09/2017

∙

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.

READ FULL TEXT

A Bottom Up Procedure for Text Line Segmentation of Latin Script

Sharp optimal recovery in the Two Gaussian Mixture Model

Pluralistic Image Completion with Probabilistic Mixture-of-Experts

Text Extraction and Restoration of Old Handwritten Documents

Autonomous Removal of Perspective Distortion for Robotic Elevator Button Recognition

Natural Scene Image Segmentation Based on Multi-Layer Feature Extraction

Unsupervised learning of text line segmentation by differentiating coarse patterns

Vision-based Traffic Flow Prediction using Dynamic Texture Model and Gaussian Process

A Bottom Up Procedure for Text Line Segmentation of Latin Script

Related Research

Sharp optimal recovery in the Two Gaussian Mixture Model

Pluralistic Image Completion with Probabilistic Mixture-of-Experts

Text Extraction and Restoration of Old Handwritten Documents

Autonomous Removal of Perspective Distortion for Robotic Elevator Button Recognition

Natural Scene Image Segmentation Based on Multi-Layer Feature Extraction

Unsupervised learning of text line segmentation by differentiating coarse patterns

Vision-based Traffic Flow Prediction using Dynamic Texture Model and Gaussian Process