Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Multioriented and curved text lines extraction from Indian documents.

U Pal¹, Partha Pratim Roy

¹Indian Statistical Institute, Kolkata-108, India. umapada@isical.ac.in

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society

|October 7, 2004

Summary

This study introduces a novel water reservoir-based method for accurately extracting text lines from Indian documents. The technique effectively handles documents with multi-oriented and curved text lines, improving optical character recognition (OCR) accuracy.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

A round-robin exercise for the precise prediction of aqueous solubility of organic chemicals using chemometric, machine learning, and stacking ensemble of deep learning models.

Journal of computer-aided molecular design·2026

Same author

Acetylcholinesterase inhibitory activity of phthalimide derivatives as anti-alzheimer agents: QSAR, ARKA, Hybrid ARKA-RASAR, virtual screening, molecular docking and ADMET studies.

Molecular diversity·2026

Same author

A hyperspectral imaging framework integrating band selection and deep learning for beverage stain classification in forensic analysis.

Scientific reports·2026

Same author

Structural insights into TNF-α inhibition by bioactive compounds found in plants of North East India: in vitro validation and in silico investigations using QSAR, molecular docking, and dynamics simulations.

Molecular diversity·2026

Same author

Soil degradation toxicity potential (DT<sub>50</sub>) of VPs followed by biodegradability and leaching: Exploration of possible aquatic and terrestrial component toxicity through QSAR, q-RASAR, and comprehensive screening.

Environmental science and pollution research international·2026

Same author

Therapeutic potential of Oxalis corniculata in circumventing Alzheimer's disease through in vitro and in silico investigations.

Journal of ethnopharmacology·2026

Area of Science:

Computer Science
Digital Image Processing
Document Analysis

Background:

Printed documents can feature text lines with varying orientations and curves.
Accurate text line extraction is crucial for effective optical character recognition (OCR).
Existing OCR methods may struggle with non-parallel or curved text lines.

Purpose of the Study:

To propose a novel scheme for extracting individual text lines from Indian documents.
To address challenges posed by multi-oriented and curved text lines.
To enhance the performance of OCR systems on complex document layouts.

Main Methods:

A water reservoir analogy is employed to extract text lines.
Connected components are labeled and classified as straight (S-type) or curve (C-type).

Related Experiment Videos

Candidate points and regions are identified to group components into text lines.

Main Results:

The proposed scheme successfully extracts individual text lines from documents with complex text orientations.
The method demonstrates effectiveness in handling both multi-oriented and curved text.
Accurate text line segmentation is achieved, paving the way for improved OCR.

Conclusions:

The water reservoir-based approach offers a robust solution for text line extraction.
This method significantly improves the ability to process challenging document types.
The findings contribute to advancing OCR technology for diverse scripts and layouts.