Z-Transform-Based Profile Matching to Develop a Learning-Free Keyword Spotting Method for Handwritten Document Images
Abstract For easy accessibility of the information from the digitized document images, optical character recognition (OCR)-based software can be used. But in the case of handwritten documents, the performance of the state-of-the-art OCR systems is not satisfactory owing to the complexity of the unco...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2022-11-01
|
| Series: | International Journal of Computational Intelligence Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44196-022-00148-8 |
| _version_ | 1828309299560972288 |
|---|---|
| author | Debanshu Banerjee Pratik Bhowal Samir Malakar Eirk Cuevas Marco Pérez‑Cisneros Ram Sarkar |
| author_facet | Debanshu Banerjee Pratik Bhowal Samir Malakar Eirk Cuevas Marco Pérez‑Cisneros Ram Sarkar |
| author_sort | Debanshu Banerjee |
| collection | DOAJ |
| description | Abstract For easy accessibility of the information from the digitized document images, optical character recognition (OCR)-based software can be used. But in the case of handwritten documents, the performance of the state-of-the-art OCR systems is not satisfactory owing to the complexity of the unconstrained handwriting. Hence, research affinity comes up with an alternative solution for this problem called keyword spotting (KWS) which is much more practical than an OCR-based solution. This work proposes a novel learning-free KWS method that can be applied to a heterogeneous collection of handwritten documents. In this work, we introduce a new way of profile matching to compare the query word profiles (i.e., both upper and lower) with the target words’ profiles. At first, both query and target words are binarized, and then two profiles from each such word are generated. Next, we formulate rules to filter out the irrelevant words concerning the query word and obtain the probable candidate query (i.e., target) words. Then we compare the profiles of the query and candidate query words in the Z-transform domain using the condition of resonance for the damped oscillator. However, before the match, we perform an affine transformation on the Bezier curve representation of the profiles of the candidate query words to reduce the effects like scaling, rotation, and shearing which might occur due to the variant writing styles of individuals. The proposed method achieves satisfactory performance compared to state-of-the-art learning-free methods when applied to four publicly available standard datasets namely ICFHR 2014 H-KWS competition Modern, IAM, ICFHR 2016 H-KWS competition Botany and ICFHR 2016 H-KWS competition Konzilsprotokolle datasets. |
| first_indexed | 2024-04-13T15:26:22Z |
| format | Article |
| id | doaj.art-1b066309ff5048ae919338d231c153fb |
| institution | Directory Open Access Journal |
| issn | 1875-6883 |
| language | English |
| last_indexed | 2024-04-13T15:26:22Z |
| publishDate | 2022-11-01 |
| publisher | Springer |
| record_format | Article |
| series | International Journal of Computational Intelligence Systems |
| spelling | doaj.art-1b066309ff5048ae919338d231c153fb2022-12-22T02:41:30ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832022-11-0115112210.1007/s44196-022-00148-8Z-Transform-Based Profile Matching to Develop a Learning-Free Keyword Spotting Method for Handwritten Document ImagesDebanshu Banerjee0Pratik Bhowal1Samir Malakar2Eirk Cuevas3Marco Pérez‑Cisneros4Ram Sarkar5Department of Metallurgical and Material Engineering, Jadavpur UniversityDepartment of Instrumentation and Electronics Engineering, Jadavpur UniversityDepartment of Computer Science, Asutosh CollegeDepartamento de Electrónica, Universidad de GuadalajaraDivisión de Tecnologías Para La Integración Ciber-Humana, Universidad de GuadalajaraDepartment of Computer Science and Engineering, Jadavpur UniversityAbstract For easy accessibility of the information from the digitized document images, optical character recognition (OCR)-based software can be used. But in the case of handwritten documents, the performance of the state-of-the-art OCR systems is not satisfactory owing to the complexity of the unconstrained handwriting. Hence, research affinity comes up with an alternative solution for this problem called keyword spotting (KWS) which is much more practical than an OCR-based solution. This work proposes a novel learning-free KWS method that can be applied to a heterogeneous collection of handwritten documents. In this work, we introduce a new way of profile matching to compare the query word profiles (i.e., both upper and lower) with the target words’ profiles. At first, both query and target words are binarized, and then two profiles from each such word are generated. Next, we formulate rules to filter out the irrelevant words concerning the query word and obtain the probable candidate query (i.e., target) words. Then we compare the profiles of the query and candidate query words in the Z-transform domain using the condition of resonance for the damped oscillator. However, before the match, we perform an affine transformation on the Bezier curve representation of the profiles of the candidate query words to reduce the effects like scaling, rotation, and shearing which might occur due to the variant writing styles of individuals. The proposed method achieves satisfactory performance compared to state-of-the-art learning-free methods when applied to four publicly available standard datasets namely ICFHR 2014 H-KWS competition Modern, IAM, ICFHR 2016 H-KWS competition Botany and ICFHR 2016 H-KWS competition Konzilsprotokolle datasets.https://doi.org/10.1007/s44196-022-00148-8Keyword spottingZ-transformHandwritten document imageAffine transform |
| spellingShingle | Debanshu Banerjee Pratik Bhowal Samir Malakar Eirk Cuevas Marco Pérez‑Cisneros Ram Sarkar Z-Transform-Based Profile Matching to Develop a Learning-Free Keyword Spotting Method for Handwritten Document Images International Journal of Computational Intelligence Systems Keyword spotting Z-transform Handwritten document image Affine transform |
| title | Z-Transform-Based Profile Matching to Develop a Learning-Free Keyword Spotting Method for Handwritten Document Images |
| title_full | Z-Transform-Based Profile Matching to Develop a Learning-Free Keyword Spotting Method for Handwritten Document Images |
| title_fullStr | Z-Transform-Based Profile Matching to Develop a Learning-Free Keyword Spotting Method for Handwritten Document Images |
| title_full_unstemmed | Z-Transform-Based Profile Matching to Develop a Learning-Free Keyword Spotting Method for Handwritten Document Images |
| title_short | Z-Transform-Based Profile Matching to Develop a Learning-Free Keyword Spotting Method for Handwritten Document Images |
| title_sort | z transform based profile matching to develop a learning free keyword spotting method for handwritten document images |
| topic | Keyword spotting Z-transform Handwritten document image Affine transform |
| url | https://doi.org/10.1007/s44196-022-00148-8 |
| work_keys_str_mv | AT debanshubanerjee ztransformbasedprofilematchingtodevelopalearningfreekeywordspottingmethodforhandwrittendocumentimages AT pratikbhowal ztransformbasedprofilematchingtodevelopalearningfreekeywordspottingmethodforhandwrittendocumentimages AT samirmalakar ztransformbasedprofilematchingtodevelopalearningfreekeywordspottingmethodforhandwrittendocumentimages AT eirkcuevas ztransformbasedprofilematchingtodevelopalearningfreekeywordspottingmethodforhandwrittendocumentimages AT marcoperezcisneros ztransformbasedprofilematchingtodevelopalearningfreekeywordspottingmethodforhandwrittendocumentimages AT ramsarkar ztransformbasedprofilematchingtodevelopalearningfreekeywordspottingmethodforhandwrittendocumentimages |