Learning‐free handwritten word spotting method for historical handwritten documents
Abstract Word spotting on degraded and noisy historical documents can become a challenging task considering the computational time and memory usage required to scan the entire document image. This paper proposes a new effective technique for multi‐language word spotting using a two different feature...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-08-01
|
Series: | IET Image Processing |
Subjects: | |
Online Access: | https://doi.org/10.1049/ipr2.12216 |
_version_ | 1811266891283431424 |
---|---|
author | Hanadi Hassen Mohammed Nandhini Subramanian Somaya Al‐Madeed |
author_facet | Hanadi Hassen Mohammed Nandhini Subramanian Somaya Al‐Madeed |
author_sort | Hanadi Hassen Mohammed |
collection | DOAJ |
description | Abstract Word spotting on degraded and noisy historical documents can become a challenging task considering the computational time and memory usage required to scan the entire document image. This paper proposes a new effective technique for multi‐language word spotting using a two different feature extraction techniques, Histogram of Oriented Gradients (HOG) and Speeded Up Robust Features (SURF) features. First, regions of interest (ROIs) are extracted using a cross‐correlation measure, and the extracted ROIs are re‐ranked using feature extraction and matching methods. The algorithm handles two types of scenarios: Segmentation‐based and segmentation‐free. It also facilitates the search for words that occur once as well as multiple times in the image. Evaluations were conducted on the George Washington and HADARA datasets using a standard evaluation method. The proposed methodology shows improved performance over contemporary technologies currently being used in the word spotting research field. |
first_indexed | 2024-04-12T20:51:39Z |
format | Article |
id | doaj.art-729a08cb3a2b48bca596e742a6ce5e7a |
institution | Directory Open Access Journal |
issn | 1751-9659 1751-9667 |
language | English |
last_indexed | 2024-04-12T20:51:39Z |
publishDate | 2021-08-01 |
publisher | Wiley |
record_format | Article |
series | IET Image Processing |
spelling | doaj.art-729a08cb3a2b48bca596e742a6ce5e7a2022-12-22T03:17:07ZengWileyIET Image Processing1751-96591751-96672021-08-0115102332234110.1049/ipr2.12216Learning‐free handwritten word spotting method for historical handwritten documentsHanadi Hassen Mohammed0Nandhini Subramanian1Somaya Al‐Madeed2Department of Computer Science and Engineering Qatar University Doha QatarDepartment of Computer Science and Engineering Qatar University Doha QatarDepartment of Computer Science and Engineering Qatar University Doha QatarAbstract Word spotting on degraded and noisy historical documents can become a challenging task considering the computational time and memory usage required to scan the entire document image. This paper proposes a new effective technique for multi‐language word spotting using a two different feature extraction techniques, Histogram of Oriented Gradients (HOG) and Speeded Up Robust Features (SURF) features. First, regions of interest (ROIs) are extracted using a cross‐correlation measure, and the extracted ROIs are re‐ranked using feature extraction and matching methods. The algorithm handles two types of scenarios: Segmentation‐based and segmentation‐free. It also facilitates the search for words that occur once as well as multiple times in the image. Evaluations were conducted on the George Washington and HADARA datasets using a standard evaluation method. The proposed methodology shows improved performance over contemporary technologies currently being used in the word spotting research field.https://doi.org/10.1049/ipr2.12216Optical, image and video signal processingImage recognitionComputer vision and image processing techniquesNatural language processing |
spellingShingle | Hanadi Hassen Mohammed Nandhini Subramanian Somaya Al‐Madeed Learning‐free handwritten word spotting method for historical handwritten documents IET Image Processing Optical, image and video signal processing Image recognition Computer vision and image processing techniques Natural language processing |
title | Learning‐free handwritten word spotting method for historical handwritten documents |
title_full | Learning‐free handwritten word spotting method for historical handwritten documents |
title_fullStr | Learning‐free handwritten word spotting method for historical handwritten documents |
title_full_unstemmed | Learning‐free handwritten word spotting method for historical handwritten documents |
title_short | Learning‐free handwritten word spotting method for historical handwritten documents |
title_sort | learning free handwritten word spotting method for historical handwritten documents |
topic | Optical, image and video signal processing Image recognition Computer vision and image processing techniques Natural language processing |
url | https://doi.org/10.1049/ipr2.12216 |
work_keys_str_mv | AT hanadihassenmohammed learningfreehandwrittenwordspottingmethodforhistoricalhandwrittendocuments AT nandhinisubramanian learningfreehandwrittenwordspottingmethodforhistoricalhandwrittendocuments AT somayaalmadeed learningfreehandwrittenwordspottingmethodforhistoricalhandwrittendocuments |