Performance Evaluation and Benchmarking of Six-Page Segmentation Algorithms

Informative benchmarks are crucial for optimizing the page segmentation step of an OCR system, frequently the performance limiting step for overall OCR system performance. We show that current evaluation scores are insufficient for diagnosing specific errors in page segmentation and fail to identify...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2008-06, Vol.30 (6), p.941-954
Main Authors: Shafait, F., Keysers, D., Breuel, T.M.
Format: Article
Language:English
Subjects:
Algorithm design and analysis
Algorithms
Applied sciences
Artificial Intelligence
Automatic Data Processing - methods
Benchmarking
Computer Graphics
Computer science
control theory
systems
Constraining
Document analysis
Documentation - methods
Errors
Exact sciences and technology
Graphics
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image segmentation
Information Storage and Retrieval - methods
Layout
Measurement
Models, Statistical
Numerical Analysis, Computer-Assisted
Optical character recognition
Optical character recognition software
Optimization
Pattern Recognition, Automated - methods
Pattern recognition. Digital image processing. Computational geometry
Representations
Reproducibility of Results
Segmentation
Sensitivity and Specificity
Shape
Signal Processing, Computer-Assisted
Subtraction Technique
System performance
User-Computer Interface
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Informative benchmarks are crucial for optimizing the page segmentation step of an OCR system, frequently the performance limiting step for overall OCR system performance. We show that current evaluation scores are insufficient for diagnosing specific errors in page segmentation and fail to identify some classes of serious segmentation errors altogether. This paper introduces a vectorial score that is sensitive to, and identifies, the most important classes of segmentation errors (over, under, and mis-segmentation) and what page components (lines, blocks, etc.) are affected. Unlike previous schemes, our evaluation method has a canonical representation of ground-truth data and guarantees pixel-accurate evaluation results for arbitrary region shapes. We present the results of evaluating widely used segmentation algorithms (x-y cut, smearing, whitespace analysis, constrained text-line finding, docstrum, and Voronoi) on the UW-III database and demonstrate that the new evaluation scheme permits the identification of several specific flaws in individual segmentation methods.
ISSN:0162-8828
1939-3539
DOI:10.1109/TPAMI.2007.70837