Abstract

This paper presents a novel segmentation algorithm for offline cursive handwriting recognition. An over-segmentation algorithm is introduced to dissect the words from handwritten text based on the pixel density between upper and lower baselines. Each segment from the over-segmentation is passed to a multiple expert-based validation process. First expert compares the total foreground pixel of the segmentation point to a threshold value. The threshold is set and calculated before the segmentation by scanning the stroke components in the word. Second expert checks for closed areas such as holes. Third expert validates segmentation points using a neural voting approach which is trained on segmented characters before validation process starts. Final expert is based on oversized segment analysis to detect possible missed segmentation points. The proposed algorithm has been implemented and the experiments on cursive handwritten text have been conducted. The results of the experiments are very promising and the overall performance of the algorithm is more effective than the other existing segmentation algorithms.

Highlights

  • INTRODUCTIONDespite intensive research for more than four decades, off-line cursive handwriting recognition still remains an open problem [1]-[4]

  • THE importance and need of handwriting recognition has been arising in many real world applications such as postal address recognition, bank cheques processing, forms processing, conversion of field notes and historical manuscripts

  • The character database has been populated from segmented cursive handwritten text

Read more

Summary

INTRODUCTION

Despite intensive research for more than four decades, off-line cursive handwriting recognition still remains an open problem [1]-[4]. Available segmentation techniques are dissection techniques [11], recognition-based segmentation [12], [13], over-segmentation [14]-[16], and holistic approaches. The holistic strategy avoids segmentation process, but it is not practical in a large lexicon environment [18]. The rest of this paper is organized into four sections.

PROPOSED SEGMENTATION ALGORITHM
Pre-Segmentation Process
Segmentation Process
Multiple Expert-Based Validation Process
Database Preparation
Segmentation Results
ANALYSIS AND DISCUSSION
Comparative Analysis
CONCLUSIONS AND FUTURE RESEARCH
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call